openapi: 3.0.0 info: title: DIAL Core API description: |- The API provides a unified interface to calling chat/completion and embedding models, as well as accessing and sharing files, conversations, and prompts. # Authorization All API requests must include the API key (or a [per-request key](https://docs.dialx.ai/platform/core/per-request-keys) when it is required) in the `Api-Key` HTTP header or the JWT token in the `Authorization` HTTP header.
#### Authorization with API Key (or with per-request key): ApiKeyAuth
```bash Api-Key: DIAL_API_KEY ```
Header parameter name: `Api-Key`
#### HTTP Authorization: BearerAuth
```bash Authorization: Bearer ```
HTTP Authorization Scheme: `bearer` Bearer format: `JWT` version: "0.41" license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0.html servers: - url: https://chat..com paths: /openai/deployments/{deployment_name}/chat/completions: post: operationId: sendChatCompletionRequest summary: /openai/deployments/{deployment_name}/chat/completions description: This API is based on the OpenAI Azure API and extended to support working with advanced DIAL agents and applications. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true - in: query name: api-version schema: type: string required: true description: The API version to use for this request. Follows the `YYYY-MM-DD[-preview]` format. example: '2024-10-21' - name: X-CACHE-POLICY in: header schema: type: string enum: ["availability-priority", "cache-priority"] default: availability-priority description: > The header configures the policy of upstream selection for this particular chat completions request. This policy makes sense only for deployments supporting [prompt caching](https://docs.dialx.ai/tutorials/developers/prompt-caching), that is those with `features.cachedSupported` or `features.autoCachingSupported` features enabled in the [DIAL Core config](https://github.com/epam/ai-dial-core?tab=readme-ov-file#dynamic-settings). `availability-priority`: Policy prioritizes upstream availability over a potential cache hit. That is, if an upstream with a cache doesn't respond, then an alternative upstream will be tried. `cache-priority`: Policy prioritizes cache hits over availability. That is, if an upstream with a cache doesn't respond, then DIAL Core will persist with requests to this same upstream. requestBody: required: true content: application/json: schema: type: object properties: model: type: string description: The name of the model to use. messages: type: array minItems: 1 description: A list of messages comprising the conversation so far. items: $ref: "#/components/schemas/ChatCompletionRequestMessage" functions: deprecated: true description: | Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. type: array minItems: 1 maxItems: 128 items: $ref: "#/components/schemas/ChatCompletionFunction" function_call: deprecated: true description: | Deprecated in favor of `tool_choice`. Controls which (if any) `function` is called by the model. `none` means the model will not call a `function` and instead generates a `message`. `auto` means the model can pick between generating a `message` or calling a `function`. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. oneOf: - type: string description: > `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. enum: [none, auto] - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" tools: type: array description: > A list of tools the model may call. Currently, only `functions` are supported as a tool. Use this to provide a list of `functions` the model may generate JSON inputs for. A max of 128 functions are supported. items: $ref: "#/components/schemas/ChatCompletionTool" tool_choice: $ref: "#/components/schemas/ChatCompletionToolChoiceOption" addons: type: array items: $ref: "#/components/schemas/ChatCompletionAddon" description: A list of Addons the Assistant can use. deprecated: true stream: description: > If set, partial message deltas will be sent. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). type: boolean nullable: true default: false temperature: type: number description: What sampling temperature to use, between 0 and 2. Higher values such as 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic. minimum: 0 maximum: 2 default: 1 top_p: type: number description: An alternative to sampling with temperature, called nucleus sampling, where the Assistant considers the results of the tokens with `top_p` probability mass. A value of 0.1 implies that only the tokens representing the top 10% probability mass are taken into consideration. minimum: 0 maximum: 1 default: 1 n: type: integer minimum: 1 maximum: 128 default: 1 example: 1 nullable: true description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. parallel_tool_calls: $ref: "#/components/schemas/ParallelToolCalls" stop: oneOf: - type: string nullable: true - type: array minItems: 1 maxItems: 4 items: type: string description: Up to 4 sequences where the Assistant will stop generating further tokens. max_tokens: type: integer description: The maximum number of tokens to generate by the Assistant. default: infinity max_prompt_tokens: type: integer description: | The maximum number of prompt tokens to handle in a request. The feature is supported only by the model adapters and the Assistant. Given this parameter an adapter truncates the list of the messages to fit into this limit and passes the truncated list to the actual model. The default strategy for truncation is to preserve all system messages and the last message. Whatever else could fit within the limit is added to the final list of messages, prioritizing the most recent messages in the chat over the earlier ones. The list of indices of the messages that were discarded is returned in the `statistics.discarded_messages` field of the response. default: infinity max_completion_tokens: description: | **Note** the parameter is only supported in OpenAI models. An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. type: integer nullable: true presence_penalty: type: number description: A number between `-2.0` and `2.0`. Positive values impose a penalty on new tokens based on their appearance in the current text, thereby increasing the model's tendency to introduce new topics in its responses. minimum: -2 maximum: 2 default: 0 frequency_penalty: type: number description: A number between `-2.0` and `2.0`. Positive values apply a penalty to new tokens according to their existing frequency in the preceding text, thereby reducing the model's propensity to repeat the exact same line. minimum: -2 maximum: 2 default: 0 logit_bias: type: object description: |- Modifies the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from `-100` to `100`. Mathematically, the bias is added to the `logits` generated by the model prior to sampling. The exact effect will vary per model, but values between `-1` and `1` should decrease or increase the likelihood of a selection; values like `-100` or `100` should result in a ban or exclusive selection of the relevant token. default: null seed: type: integer minimum: -9223372036854775808 maximum: 9223372036854775807 nullable: true description: | This feature is in **Beta**. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. user: type: string description: A unique identifier representing the end-user. response_format: description: | An object specifying the format that the model must output. Compatible with [GPT-4o](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4o mini](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models), [GPT-4 Turbo](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-4-and-gpt-4-turbo-models) and all [GPT-3.5](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#gpt-35) Turbo models newer than `gpt-3.5-turbo-1106`. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which guarantees the model will match your supplied JSON schema. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. **Note:** JSON mode is not supported by all models. oneOf: - $ref: "#/components/schemas/ResponseFormatText" - $ref: "#/components/schemas/ResponseFormatJsonObject" - $ref: "#/components/schemas/ResponseFormatJsonSchema" custom_fields: $ref: '#/components/schemas/ChatCompletionsCustomFields' required: - messages examples: Chat Model: value: messages: - role: user content: Hello! Chat Model Streaming: value: stream: true messages: - role: user content: Hello! responses: '200': description: Success content: application/json: schema: $ref: "#/components/schemas/CreateChatCompletionResponse" examples: Chat Model: value: id: chatcmpl-8mt8AF8xkczUdRv250bpmU6KqMfAb choices: - finish_reason: stop index: 0 message: role: assistant content: ChatGPT is an advanced conversational AI model built on the GPT-3.5 architecture. It is a Large Language Model (LLM) that can engage in context-aware, human-like interactions. It is a suitable testbed for creativity and has demonstrated remarkable capabilities in understanding and generating human-like text. It heavily relies on in-context examples and has a strong bias toward using or not using certain tools. refusal: null created: 1706662358 model: gpt-4 object: chat.completion usage: completion_tokens: 9 prompt_tokens: 9 total_tokens: 18 text/event-stream: schema: type: array items: $ref: "#/components/schemas/CreateChatCompletionStreamResponse" examples: Chat Model Streaming: value: - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: '' role: assistant finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: Hello finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: "!" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " How" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " can" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " I" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " assist" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " you" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: " today" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: "?" finish_reason: null index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk - id: chatcmpl-8nCUKwNc1iEHEUuOhsU48eODcNWCL choices: - delta: content: "" finish_reason: stop index: 0 created: 1706736768 model: gpt-4 object: chat.completion.chunk usage: completion_tokens: 9 prompt_tokens: 9 total_tokens: 18 '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '404': description: | Not found Returned either when: 1. The deployment called `{deployment_name}` doesn't exist. Check the DIAL listing to verify that the deployment does actually exist. 2. The `api-version` query parameter points to an API version that doesn't exist. This is relevant only for deployments based on Azure OpenAI models. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '429': description: Rate limit reached. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '500': description: The server had an error while processing your request. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '502': description: Failed to connect to upstream server. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '503': description: The engine is currently overloaded, please try again later. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/deployments/gpt-4/chat/completions?api-version=2023-12-01-preview \ -H "Content-Type: application/json" \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "messages": [{"role": "user", "content": "Hello!"}] }' - lang: 'Python' label: 'Python (LangChain 0.1.4)' source: | from langchain_openai import AzureChatOpenAI from langchain.schema import HumanMessage model = AzureChatOpenAI( openai_api_version="2023-12-01-preview", azure_deployment="gpt-4", azure_endpoint="https://chat..com", api_key="DIAL_API_KEY" ) response = model.invoke( [ HumanMessage( content="Hello!" ) ] ) - lang: 'Python' label: 'Python (OpenAI Library 1.10)' source: | from openai import AzureOpenAI client = AzureOpenAI( api_version="2023-12-01-preview", azure_endpoint="https://chat..com", api_key="DIAL_API_KEY" ) response = client.chat.completions.create( model="gpt-4", messages=[ { "role": "user", "content": "Hello!", } ] ) /v1/deployments/{deployment_name}/configuration: get: operationId: configurationDeployment summary: /v1/deployments/{deployment_name}/configuration description: | The endpoint provides JSON schema of the configuration supported by the chat completion deployment. If the deployment supports configuration, it's expected to be passed via `custom_fields.configuration` field in the chat completion request.

A deployment supports configuration if its listing, retrieved by `GET /openai/deployments/{deployment_name}`, has a field `features.configuration` set to `true`. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true responses: '200': description: Success content: application/json: schema: description: JSON schema of the configuration parameters the given deployment. type: object examples: Example: value: $ref: ./examples/configuration_schema.json '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/deployments/gpt-4/configuration \ -H "Api-Key: DIAL_API_KEY" /openai/deployments/{deployment_name}/embeddings: post: operationId: sendEmbeddingsRequest summary: /openai/deployments/{deployment_name}/embeddings description: | Call this endpoint to get a vector representation of a given input. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true - in: query name: api-version schema: type: string required: true description: The API version to use for this request. Follows the `YYYY-MM-DD[-preview]` format. example: '2023-12-01-preview' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/EmbeddingRequest' examples: Single string input: value: input: Your text string goes here Many string inputs: value: input: - Input 1 - Input 2 Image input (DIAL URL): value: input: [] custom_input: - type: "image/png" url: "files/USER_BUCKET/dir1/dir2/image.png" Image input (base64): value: input: [] custom_input: - type: "image/png" data: "iVBORw0KGgoAAA..." Image input (annotated): value: input: [] custom_input: - - Image title - type: "image/png" url: "files/USER_BUCKET/dir1/dir2/image.png" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/EmbeddingResponse' examples: Single text output: $ref: ./examples/embeddings_single_text.yaml '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '404': description: | Not found Returned either when: 1. The deployment called `{deployment_name}` doesn't exist. Check the DIAL listing to verify that the deployment does actually exist. 2. The `api-version` query parameter points to an API version that doesn't exist. This is relevant only for deployments based on Azure OpenAI models. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '429': description: Rate limit reached content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '500': description: The server had an error while processing your request. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '503': description: The engine is currently overloaded, please try again later. content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/deployments/text-embedding-ada-002/embeddings?api-version=2023-12-01-preview \ -H "Content-Type: application/json" \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "input": "Your text string goes here" }' - lang: 'Python' label: 'Python (LangChain 0.1.4)' source: | from langchain_openai import AzureOpenAIEmbeddings from langchain.schema import HumanMessage model = AzureOpenAIEmbeddings( openai_api_version="2023-12-01-preview", azure_deployment="text-embedding-ada-002", azure_endpoint="https://chat..com", api_key="DIAL_API_KEY", # Set the flag to False for models which do not support token ids in inputs check_embedding_ctx_length=False, model_kwargs={}, ) response = model.embed_query("Your text string goes here") - lang: 'Python' label: 'Python (OpenAI Library 1.10)' source: | from openai import AzureOpenAI client = AzureOpenAI( api_version="2023-12-01-preview", azure_endpoint="https://chat..com", api_key="DIAL_API_KEY" ) response = client.embeddings.create( input="Your text string goes here", model="text-embedding-ada-002" ) /v1/{deployment_name}/rate: post: operationId: rateDeployment summary: /v1/{deployment_name}/rate description: | Call this endpoint to rate the response received from the chat completions endpoint. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true requestBody: required: true content: application/json: schema: type: object properties: rate: type: boolean description: True if you like the message and false otherwise responseId: type: string description: Id received in the target chat completion response examples: Example: value: rate: true responseId: "chatcmpl-8mixpbdJ9S5Y3w8hRBVpPmFgNk0Li" responses: '200': description: Success '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/gpt-4/rate \ -H "Content-Type: application/json" \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "rate": true, "responseId": "chatcmpl-8mixpbdJ9S5Y3w8hRBVpPmFgNk0Li" }' /v1/user/info: get: operationId: getUserInfo summary: /v1/user/info description: | Call this endpoint to retrieve information about a user. To access the endpoint, a user must be authenticated with API key or access token. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/userinfo' examples: API Key: value: project: "PROJECT-NAME" roles: - default Access Token: value: roles: - BA userClaims: email: - user_email sub: - user_sub '400': description: Invalid Authentication '401': description: Unauthorized x-codeSamples: - lang: 'cURL' label: 'API Key' source: | curl -X GET https://chat..com/v1/user/info \ -H "Api-Key: DIAL_API_KEY" - lang: 'cURL' label: 'Access Token' source: | curl -X GET https://chat..com/v1/user/info \ -H "Authorization: Bearer YOUR_ACCESS_TOKEN" /v1/toolset/{toolset_name}/mcp: post: operationId: callToolSet tags: - Toolsets summary: /v1/toolset/{toolset_name}/mcp description: | This endpoint implements MCP-based communication using [HTTP transport](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#streamable-http). parameters: - name: toolset_name in: path schema: type: string description: The name of the toolset. required: true requestBody: required: true content: application/json: schema: type: string description: | A JSON object satisfying [mcp specification](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.json). responses: '200': description: Success content: application/json: schema: type: object description: A JSON object satisfying [mcp specification](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.json). '400': description: Invalid Authentication '401': description: Unauthorized /v1/deployments/{deployment_id}/mcp: post: operationId: callMcp tags: - Applications summary: /v1/deployments/{deployment_id}/mcp description: | This endpoint implements MCP-based communication with application deployment using [HTTP transport](https://modelcontextprotocol.io/specification/2025-06-18/basic/transports#streamable-http). parameters: - name: deployment_id in: path schema: type: string description: The ID of the deployment. required: true requestBody: required: true content: application/json: schema: type: string description: | A JSON object satisfying [mcp specification](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.json). responses: '200': description: Success content: application/json: schema: type: object description: A JSON object satisfying [mcp specification](https://github.com/modelcontextprotocol/modelcontextprotocol/blob/main/schema/2025-06-18/schema.json). '400': description: Invalid Authentication '401': description: Unauthorized /v1/ops/application/deploy: post: operationId: deployApplication tags: - Applications summary: /v1/ops/application/deploy description: Call this endpoint to deploy an application. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The application URL. examples: ExampleUser: value: url: "applications/3CcedGxCx23EwiVbV/" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ApplicationOpenAi' examples: Application: value: name: application_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name nodeType: ITEM resourceType: APPLICATION etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 permissions: - READ - WRITE '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/application/undeploy: post: operationId: undeployApplication tags: - Applications summary: /v1/ops/application/undeploy description: Call this endpoint to undeploy an application. After undeploying, the application will no longer be accessible until it is [deployed](#tag/Applications/operation/deployApplication) again. Use [redeploy](#tag/Applications/operation/redeployApplication) to apply changes without downtime. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The application URL. examples: ExampleUser: value: url: "applications/3CcedGxCx23EwiVbV/" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ApplicationOpenAi' examples: Application: value: name: application_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name nodeType: ITEM resourceType: APPLICATION etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 permissions: - READ - WRITE '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/application/redeploy: post: operationId: redeployApplication tags: - Applications summary: /v1/ops/application/redeploy description: Call this endpoint to redeploy an application. This is useful when you want to apply changes made to the application without downtime, contrary to the [undeploy](#tag/Applications/operation/undeployApplication) and deploy process. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The application URL. examples: ExampleUser: value: url: "applications/3CcedGxCx23EwiVbV/" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ApplicationOpenAi' examples: Application: value: name: application_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name nodeType: ITEM resourceType: APPLICATION etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 permissions: - READ - WRITE '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/application/logs: post: operationId: getApplicationLogs tags: - Applications summary: /v1/ops/application/logs description: Call this endpoint to get application logs requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The application URL. examples: ExampleUser: value: url: "applications/3CcedGxCx23EwiVbV/" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ApplicationLogs' examples: ApplicationLogs: value: logs: - instance: instance-name content: |- application instance logs will be printed here '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/application_type_schemas/schemas: get: operationId: listCustomApplicationSchemas tags: - Applications summary: /v1/application_type_schemas/schemas description: Call this endpoint to get a list of available application types schemas. Refer to [/v1/application_type_schemas/schema](/dial_api#tag/Applications/operation/getCustomApplicationSchema) to see a real example of Quick app schema. responses: '200': description: Success content: application/json: schema: type: array items: type: object properties: $id: type: string description: Unique identifier for the application schema. dial:applicationTypeDisplayName: type: string description: Name of the application type displayed on the UI. dial:applicationTypeViewerUrl: type: string description: URL for the UI of the application type. dial:applicationTypeEditorUrl: type: string description: URL for the application builder used by the app type. dial:applicationTypeSchemaEndpoint: type: string description: URL to retrieve JSON schema of the application. examples: Schema: value: - $id: https://mydial.com/custom_application_schemas/mindmaps dial:applicationTypeDisplayName: Mindmap dial:applicationTypeViewerUrl: https://mydial.com/mindmap dial:applicationTypeEditorUrl: https://mydial.com/editor dial:applicationTypeSchemaEndpoint: https://mydial.com/schema - $id: https://mydial.com/custom_application_schemas/quickapps dial:applicationTypeDisplayName: Quick app - $id: https://mydial.com/custom_application_schemas/dial-rag-app-runner dial:applicationTypeDisplayName: DIAL RAG dial:applicationTypeEditorUrl: https://mydial.com/editor '401': description: Invalid Authentication '500': description: The server had an error while processing your request /v1/application_type_schemas/meta_schema: get: operationId: getMetaSchemaOfCustomApplicationSchema tags: - Applications summary: /v1/application_type_schemas/meta_schema description: Call this endpoint to get metaschema of custom application schema. responses: '200': description: Success content: application/json: schema: type: object description: Json object with metaschema you can use to create other schemas. examples: Example: value: { "$schema": "http://json-schema.org/draft-07/schema#", "$id": "https://dial.epam.com/application_type_schemas/schema#", "title": "Core meta-schema defining Ai DIAL custom application schemas", "allOf": [ { "$ref": "#/definitions/topLevelSchema" }, { "$ref": "#/definitions/dialRootSchema" } ], "definitions": { "dialRootSchema": { "properties": { "dial:applicationTypeEditorUrl": { "type": "string", "format": "uri", "description": "URL to the editor UI of the custom application of given type" }, "dial:applicationTypeViewerUrl": { "type": "string", "format": "uri", "description": "URL to the view UI of the custom application of given type" }, "dial:applicationTypeSchemaEndpoint": { "type": "string", "format": "uri", "description": "URL to retrieve JSON schema of the custom application of given type." }, "dial:applicationTypeCompletionEndpoint": { "type": "string", "format": "uri", "description": "URL to the completion endpoint of the custom application of given type" }, "dial:applicationTypeConfigurationEndpoint": { "type": "string", "format": "uri", "description": "URL to the configuration endpoint of the custom application of given type" }, "dial:applicationTypeRateEndpoint": { "type": "string", "format": "uri", "description": "URL to the rate endpoint of the custom application of given type" }, "dial:applicationTypeTokenizeEndpoint": { "type": "string", "format": "uri", "description": "URL to the tokenize endpoint of the custom application of given type" }, "dial:applicationTypeTruncatePromptEndpoint": { "type": "string", "format": "uri", "description": "URL to the truncate prompt of the custom application of given type" }, "dial:applicationTypeDisplayName": { "type": "string", "description": "Display name of the custom application of given type" }, "dial:appendApplicationPropertiesHeader": { "type": "boolean", "description": "If this flag is set to true, the header with properties will augment the request while proxying" } }, "required": [ "dial:applicationTypeCompletionEndpoint", "dial:applicationTypeDisplayName" ] }, "dialFileFormatAndTypeSchema": { "$comment": "Sub-schema defining the type format and dial:file properties", "properties": { "format": { "type": "string" }, "type": { "anyOf": [ { "$ref": "#/definitions/simpleTypes" }, { "type": "array", "items": { "$ref": "#/definitions/simpleTypes" }, "minItems": 1, "uniqueItems": true } ] }, "dial:file": { "description": "Required to check file existence in DIAL instance", "type": "boolean", "default": false } }, "allOf": [ { "if": { "properties": { "dial:file": { "const": true } }, "required": [ "dial:file" ] }, "then": { "required": [ "format", "type" ], "properties": { "format": { "const": "dial-file-encoded" }, "type": { "const": "string" } } } } ] }, "topLevelSchema": { "allOf": [ { "$ref": "#/definitions/dialFileFormatAndTypeSchema" }, { "type": [ "object", "boolean" ], "properties": { "$id": { "type": "string", "format": "uri-reference" }, "$schema": { "type": "string", "format": "uri" }, "$ref": { "type": "string", "format": "uri-reference" }, "$comment": { "type": "string" }, "title": { "type": "string" }, "description": { "type": "string" }, "default": true, "readOnly": { "type": "boolean", "default": false }, "writeOnly": { "type": "boolean", "default": false }, "examples": { "type": "array", "items": true }, "multipleOf": { "type": "number", "exclusiveMinimum": 0 }, "maximum": { "type": "number" }, "exclusiveMaximum": { "type": "number" }, "minimum": { "type": "number" }, "exclusiveMinimum": { "type": "number" }, "maxLength": { "$ref": "#/definitions/nonNegativeInteger" }, "minLength": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "pattern": { "type": "string", "format": "regex" }, "additionalItems": { "$ref": "#/definitions/notTopLevelSchema" }, "items": { "anyOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "$ref": "#/definitions/notTopLevelSchemaArray" } ], "default": true }, "maxItems": { "$ref": "#/definitions/nonNegativeInteger" }, "minItems": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "uniqueItems": { "type": "boolean", "default": false }, "contains": { "$ref": "#/definitions/notTopLevelSchema" }, "maxProperties": { "$ref": "#/definitions/nonNegativeInteger" }, "minProperties": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "required": { "$ref": "#/definitions/stringArray" }, "additionalProperties": { "$ref": "#/definitions/notTopLevelSchema" }, "definitions": { "type": "object", "additionalProperties": { "$ref": "#/definitions/notTopLevelSchema" }, "default": {} }, "properties": { "type": "object", "additionalProperties": { "$ref": "#/definitions/topLevelPropertySchema" }, "default": {} }, "patternProperties": { "type": "object", "additionalProperties": { "$ref": "#/definitions/topLevelPropertySchema" }, "propertyNames": { "format": "regex" }, "default": {} }, "dependencies": { "type": "object", "additionalProperties": { "anyOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "$ref": "#/definitions/stringArray" } ] } }, "propertyNames": { "$ref": "#/definitions/notTopLevelSchema" }, "const": true, "enum": { "type": "array", "items": true, "minItems": 1, "uniqueItems": true }, "contentMediaType": { "type": "string" }, "contentEncoding": { "type": "string" }, "if": { "$ref": "#/definitions/notTopLevelSchema" }, "then": { "$ref": "#/definitions/notTopLevelSchema" }, "else": { "$ref": "#/definitions/notTopLevelSchema" }, "allOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "anyOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "oneOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "not": { "$ref": "#/definitions/notTopLevelSchema" } }, "default": true } ] }, "notTopLevelSchema": { "allOf": [ { "$ref": "#/definitions/dialFileFormatAndTypeSchema" }, { "type": [ "object", "boolean" ], "properties": { "$id": { "type": "string", "format": "uri-reference" }, "$schema": { "type": "string", "format": "uri" }, "$ref": { "type": "string", "format": "uri-reference" }, "$comment": { "type": "string" }, "title": { "type": "string" }, "description": { "type": "string" }, "default": true, "readOnly": { "type": "boolean", "default": false }, "writeOnly": { "type": "boolean", "default": false }, "examples": { "type": "array", "items": true }, "multipleOf": { "type": "number", "exclusiveMinimum": 0 }, "maximum": { "type": "number" }, "exclusiveMaximum": { "type": "number" }, "minimum": { "type": "number" }, "exclusiveMinimum": { "type": "number" }, "maxLength": { "$ref": "#/definitions/nonNegativeInteger" }, "minLength": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "pattern": { "type": "string", "format": "regex" }, "additionalItems": { "$ref": "#/definitions/notTopLevelSchema" }, "items": { "anyOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "$ref": "#/definitions/notTopLevelSchemaArray" } ], "default": true }, "maxItems": { "$ref": "#/definitions/nonNegativeInteger" }, "minItems": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "uniqueItems": { "type": "boolean", "default": false }, "contains": { "$ref": "#/definitions/notTopLevelSchema" }, "maxProperties": { "$ref": "#/definitions/nonNegativeInteger" }, "minProperties": { "$ref": "#/definitions/nonNegativeIntegerDefault0" }, "required": { "$ref": "#/definitions/stringArray" }, "additionalProperties": { "$ref": "#/definitions/notTopLevelPropertySchema" }, "definitions": { "type": "object", "additionalProperties": { "$ref": "#/definitions/notTopLevelSchema" }, "default": {} }, "properties": { "type": "object", "additionalProperties": { "$ref": "#/definitions/notTopLevelPropertySchema" }, "default": {} }, "patternProperties": { "type": "object", "additionalProperties": { "$ref": "#/definitions/notTopLevelPropertySchema" }, "propertyNames": { "format": "regex" }, "default": {} }, "dependencies": { "type": "object", "additionalProperties": { "anyOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "$ref": "#/definitions/stringArray" } ] } }, "propertyNames": { "$ref": "#/definitions/notTopLevelSchema" }, "const": true, "enum": { "type": "array", "items": true, "minItems": 1, "uniqueItems": true }, "contentMediaType": { "type": "string" }, "contentEncoding": { "type": "string" }, "if": { "$ref": "#/definitions/notTopLevelSchema" }, "then": { "$ref": "#/definitions/notTopLevelSchema" }, "else": { "$ref": "#/definitions/notTopLevelSchema" }, "allOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "anyOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "oneOf": { "$ref": "#/definitions/notTopLevelSchemaArray" }, "not": { "$ref": "#/definitions/notTopLevelSchema" } }, "default": true } ] }, "topLevelPropertySchema": { "allOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "$ref": "#/definitions/dialPropertyMetaSchema" } ] }, "notTopLevelPropertySchema": { "allOf": [ { "$ref": "#/definitions/notTopLevelSchema" }, { "propertyNames": { "not": { "enum": [ "dial:meta" ] } } } ] }, "dialPropertyKind": { "$comment": "Enum defining the property to be available to the clients or to be server-side only", "enum": [ "server", "client" ] }, "dialPropertyMetaSchema": { "$comment": "Sub-schema defining the meta-property with information AI Dial purposes", "type": "object", "properties": { "dial:meta": { "type": [ "object" ], "properties": { "dial:propertyOrder": { "type": "number", "description": "Order in which the property should be displayed in the default editor UI" }, "dial:propertyKind": { "description": "Is property available for the clients or server-side only", "$ref": "#/definitions/dialPropertyKind" } }, "required": [ "dial:propertyOrder", "dial:propertyKind" ] } }, "required": [ "dial:meta" ] }, "topLevelSchemaArray": { "type": "array", "minItems": 1, "items": { "$ref": "#/definitions/topLevelSchema" } }, "notTopLevelSchemaArray": { "type": "array", "minItems": 1, "items": { "$ref": "#/definitions/notTopLevelSchema" } }, "nonNegativeInteger": { "type": "integer", "minimum": 0 }, "nonNegativeIntegerDefault0": { "allOf": [ { "$ref": "#/definitions/nonNegativeInteger" }, { "default": 0 } ] }, "simpleTypes": { "enum": [ "array", "boolean", "integer", "null", "number", "object", "string" ] }, "stringArray": { "type": "array", "items": { "type": "string" }, "uniqueItems": true, "default": [] } } } '401': description: Invalid Authentication '500': description: The server had an error while processing your request /v1/application_type_schemas/schema: get: operationId: getCustomApplicationSchema tags: - Applications summary: /v1/application_type_schemas/schema description: Call this endpoint to get the application type schema by its id parameters: - in: query name: id required: true schema: type: string description: schema ID of custom application responses: '200': description: Success content: application/json: schema: type: object description: Json object with schema of the requested application type. Refer to [/v1/application_type_schemas/schemas](/dial_api#tag/Applications/operation/listCustomApplicationSchemas) to view descriptions of several standard parameters. examples: Example: value: { "$schema": "https://dial.epam.com/application_type_schemas/schema#", "$id": "https://mydial.epam.com/custom_application_schemas/quickapps", "dial:applicationTypeDisplayName": "Quick app", "dial:applicationTypeSchemaEndpoint": "https://mydial.com/schema", "$defs": { "ToolEndpointInfo": { "properties": { "name": { "title": "Name", "type": "string" }, "method_url": { "title": "Method Url", "type": "string" }, "method_type": { "$ref": "#/$defs/ToolEndpointInfoMethodType" }, "description": { "title": "Description", "type": "string" }, "parameters": { "items": { "$ref": "#/$defs/ToolEndpointParameterInfo" }, "title": "Parameters", "type": "array" } }, "required": [ "name", "method_url", "method_type", "description", "parameters" ], "title": "ToolEndpointInfo", "type": "object" }, "ToolEndpointInfoMethodType": { "enum": [ "get", "post", "put", "delete" ], "title": "ToolEndpointInfoMethodType", "type": "string" }, "ToolEndpointParameterInfo": { "properties": { "name": { "title": "Name", "type": "string" }, "description": { "title": "Description", "type": "string" }, "url_param": { "default": false, "title": "Url Param", "type": "boolean" }, "constant_value": { "default": null, "title": "Constant Value" }, "parameter_type": { "$ref": "#/$defs/ToolEndpointParameterTypeInfo" }, "item_parameter_type": { "anyOf": [ { "$ref": "#/$defs/ToolEndpointParameterTypeInfo" }, { "type": "null" } ], "default": null }, "item_descriptor": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Item Descriptor" } }, "required": [ "name", "description", "parameter_type" ], "title": "ToolEndpointParameterInfo", "type": "object" }, "ToolEndpointParameterTypeInfo": { "enum": [ "string", "number", "integer", "object", "array", "boolean" ], "title": "ToolEndpointParameterTypeInfo", "type": "string" }, "WebApiToolsetInfo": { "properties": { "tool_endpoints": { "items": { "$ref": "#/$defs/ToolEndpointInfo" }, "title": "Tool Endpoints", "type": "array" }, "auth_info": { "anyOf": [ { "discriminator": { "mapping": { "apikey": "#/$defs/WebApiToolsetKeyAuthInfo", "obo": "#/$defs/WebApiToolsetOBOAuthInfo" }, "propertyName": "auth_type" }, "oneOf": [ { "$ref": "#/$defs/WebApiToolsetOBOAuthInfo" }, { "$ref": "#/$defs/WebApiToolsetKeyAuthInfo" } ] }, { "type": "null" } ], "title": "Auth Info" } }, "required": [ "tool_endpoints", "auth_info" ], "title": "WebApiToolsetInfo", "type": "object" }, "WebApiToolsetKeyAuthInfo": { "properties": { "auth_type": { "const": "apikey", "enum": [ "apikey" ], "title": "Auth Type", "type": "string" }, "api_key": { "format": "password", "title": "Api Key", "type": "string", "writeOnly": true }, "url_param": { "default": false, "title": "Url Param", "type": "boolean" } }, "required": [ "auth_type", "api_key" ], "title": "WebApiToolsetKeyAuthInfo", "type": "object" }, "WebApiToolsetOBOAuthInfo": { "properties": { "auth_type": { "const": "obo", "enum": [ "obo" ], "title": "Auth Type", "type": "string" }, "tenant": { "title": "Tenant", "type": "string" }, "grant_type": { "title": "Grant Type", "type": "string" }, "client_id": { "title": "Client Id", "type": "string" }, "client_secret": { "format": "password", "title": "Client Secret", "type": "string", "writeOnly": true }, "scope": { "title": "Scope", "type": "string" }, "assertion": { "title": "Assertion", "type": "string" } }, "required": [ "auth_type", "tenant", "grant_type", "client_id", "client_secret", "scope", "assertion" ], "title": "WebApiToolsetOBOAuthInfo", "type": "object" } }, "properties": { "temperature": { "title": "Temperature", "type": "number", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 1 } }, "instructions": { "title": "Instructions", "type": "string", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 2 } }, "model": { "title": "Model", "type": "string", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 3 } }, "web_api_toolset": { "items": { "$ref": "#/$defs/WebApiToolsetInfo" }, "title": "Web Api Toolset", "type": "array", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 4 } }, "document_relative_url": { "type": "string", "format": "dial-file-encoded", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 5 }, "dial:file": true }, "starters": { "items": { "type": "string" }, "title": "Starter buttons", "type": "array", "dial:meta": { "dial:propertyKind": "server", "dial:propertyOrder": 6 } } }, "required": [ "temperature", "instructions", "model", "web_api_toolset" ] } '401': description: Invalid Authentication '400': description: Bad request '500': description: The server had an error while processing your request x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/application_type_schemas/schema?id=https://mydial.epam.com/custom_application_schemas/quickapps \ -H "Api-Key: DIAL_API_KEY" /v1/applications/{Bucket}/{application_path}: put: operationId: saveCustomApplication tags: - Applications summary: /v1/applications/{Bucket}/{application_path} description: | Call this endpoint to add an application to the specified bucket and path. **Note**, that requests differ for apps with and without schemas. See the details in the REQUEST BODY SCHEMA section. Refer to [Documentation](https://docs.dialx.ai/platform/core/apps) to learn more about applications in DIAL. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: application_path in: path schema: type: string description: | Target application path. The parameter specifies a full path to the application, for example: `folder1/folder2/application_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the application. This is used for conditional requests to ensure that the application is only uploaded if it matches the specified ETag. If the application does not exist, this header is ignored. If this header is not provided or the value is "*", any existing application at the specified path will be overwritten. - name: If-None-Match in: header schema: type: string description: | The entity tag (ETag) used to ensure that the application is only uploaded if it does not already exist. The only supported value is "*". requestBody: required: true content: application/json: schema: type: string description: | An arbitrary string in JSON format representing the structure of the application. **Important**: Applications may or may not include an `application_type_schema_id`, which affects their creation and modification mechanics. If `application_type_schema_id` is absent or `NULL`, `application_properties` are not required. If you provide `application_type_schema_id` but `application_properties` are `NULL`, the application is a "stub" and can be updated later, but completion requests will not be possible. When you supply `application_properties`, they must be a valid JSON object that conforms to the schema specified by `application_type_schema_id`. An invalid JSON object will result in a bad request status. If you do not provide `application_type_schema_id`, refer to [DIAL Core](https://github.com/epam/ai-dial-core/blob/development/docs/dynamic-settings/applications.md) documentation to learn about available properties of applications you can pass in the JSON object describing the structure of the application. **Note**: When `applicationTypeSchemaId` and `applicationProperties` are specified, parameters defined in the corresponding JSON schema will take precedence and will override the corresponding parameters specified in the `application` object. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer examples: Example: value: "name": "application_name" "author": "application_creator_name" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name" "nodeType": "ITEM" "resourceType": "APPLICATION" "createdAt": 1707871723597 "updatedAt": 1707876304850 '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'Without schema' source: | curl -X PUT https://chat..com/v1/applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "application": { "endpoint": "http://localhost:7001/openai/deployments/10k/chat/completions", "displayName": "MyApp", "iconUrl": "https://host/app.svg", "viewerUrl": "URL of the application custom UI", "editorUrl": "URL of the application builder UI", "description": "My application description", "userRoles": ["AdminRole"], "forwardAuthToken": true, "features": { "rateEndpoint": "http://host/rate", "configurationEndpoint": "http://host/configure" }, "mcp": { "endpoint": "http://host/mcp", "transport": "http", "allowedTools": ["tool1", "tolol2"], "configDelivery": "meta", "forwardPerRequestKey": true }, "maxInputAttachments": 10, "inputAttachmentTypes": ["type1", "type2"], "defaults": { "paramStr": "value", "paramBool": true, "paramInt": 123, "paramFloat": 0.25 }, "interceptors": ["interceptor1", "interceptor2", "interceptor3"] } }' - lang: 'cURL' label: 'With schema' source: | curl -X PUT https://chat..com/v1/applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "display_name": "Copilot Deck Explorer", "description": "You can ask about the copilot deck there", "application_type_schema_id": "https://mydial.epam.com/custom_application_schemas/quickapps", "application_properties": { "temperature": 0.8, "instructions": "You should help explore the document containing the Copilot Deck. You must query the document first to do that. You should answer using only the information in the document. Answer \"I don't know\" if there are any other questions.", "model": "gpt-4o-2024-05-13", "web_api_toolset": [], "document_relative_url": "files/DpZGXdhaTxt4FYCWNadE2Ln/GPT%20Deck.docx" } }' get: operationId: getCustomApplication tags: - Applications summary: /v1/applications/{Bucket}/{application_path} description: | Call this endpoint to get the application structure described in JSON format. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: application_path in: path schema: type: string description: | The target application path. The parameter specifies full path to the application, for example: `folder1/folder2/application_name` required: true responses: '200': description: Success content: application/json: schema: type: string examples: Example: value: | { "application": { "endpoint": "http://localhost:7001/openai/deployments/10k/chat/completions", "displayName": "MyApp", "iconUrl": "https://host/app.svg", "description": "My application description", "userRoles": ["AdminRole"], "forwardAuthToken": true, "features": { "rateEndpoint": "http://host/rate", "configurationEndpoint": "http://host/configure"}, "mcp": { "endpoint": "http://host/mcp", "transport": "http", "allowedTools": ["tool1", "tool2"], "configDelivery": "meta", "forwardPerRequestKey": true }, "maxInputAttachments": 10, "inputAttachmentTypes": ["type1", "type2"], "defaults": { "paramStr": "value", "paramBool": true, "paramInt": 123, "paramFloat": 0.25 }, "interceptors": ["interceptor1", "interceptor2", "interceptor3"]} } '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name \ -H "Api-Key: DIAL_API_KEY" delete: operationId: deleteCustomApplication tags: - Applications summary: /v1/applications/{Bucket}/{application_path} description: | Call this endpoint to delete the application. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: application_path in: path schema: type: string description: | The target application path. The parameter specifies full path to the application, for example: `folder1/folder2/application_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the application. This is used for conditional requests to ensure that the application is only deleted if it matches the specified ETag. responses: '200': description: Success '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name \ -H "Api-Key: DIAL_API_KEY" /v1/metadata/applications/{Bucket}/{Path}: get: operationId: getApplicationMetadata tags: - Applications summary: /v1/metadata/applications/{Bucket}/{Path} description: | Call this endpoint to get metadata for a folder or an item. If the path is a folder, it must end with a "/". If it is called for a folder, there can be optional `nextToken` field in the response to be used to request next items if present. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: Path in: path schema: type: string description: | The parameter specifies path to the requested directory or application, for example: `folder1/folder2/` or `folder1/application_name/`. Note, it could be empty if you want to list the root folder. required: true - in: query name: token schema: type: string description: The token from the previous request to request next items. - in: query name: limit schema: type: integer minimum: 1 maximum: 1000 default: 100 description: Limit on the number of items in the response. - in: query name: recursive schema: type: boolean default: false description: | If true, returns items recursively without nested folder metadata. For example, request for `/a/` will contain only metadata for items `/a/b/c` and `/a/d/e/f`, but it won't contain metadata for folders: `/a/b/`, `/a/d/`, `/a/d/e`. - in: query name: permissions schema: type: boolean default: false description: If true, returns the permissions applicable to the requestor, indicating what actions they can perform on applications. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string description: This field is not available for folders. parentPath: type: string bucket: type: string url: type: string nodeType: type: string description: ITEM if the pass is provided for an app and FOLDER in case for a folder. resourceType: type: string etag: type: string description: This field is not available for folders. createdAt: type: integer description: The creation time is not supported by all storage providers. updatedAt: type: integer permissions: type: array items: type: string enum: - READ - WRITE - SHARE items: type: array items: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer permissions: type: array items: type: string enum: - READ - WRITE nextToken: type: string description: An optional field that can be used to request next items if present. examples: Folder: value: name: folder2 parentPath: folder1 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ nodeType: FOLDER resourceType: APPLICATION permissions: - READ - WRITE items: - name: application_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name nodeType: ITEM resourceType: APPLICATION updatedAt: 1707876435000 permissions: - READ - WRITE Application: value: name: application_name author: the name of the app creator parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/application_name nodeType: ITEM resourceType: APPLICATION etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 permissions: - READ - WRITE '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/metadata/applications/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ \ -H "Api-Key: DIAL_API_KEY" /v1/bucket: get: operationId: getUserBucket tags: - Files - Conversations - Prompts - Applications summary: /v1/bucket description: | Call this endpoint to get a bucket. responses: '200': description: Success content: application/json: schema: type: object properties: bucket: type: string appdata: type: string description: Bucket of the root user, allowing to manage user files in the assistant folder. Exists only for requests made using temporary api-key that were generated for the request to the dial assistants. required: - bucket examples: Example: value: "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "appdata": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/appdata/dall-e-3" '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/bucket \ -H "Api-Key: DIAL_API_KEY" /v1/files/{Bucket}/{file_path}: put: operationId: uploadFile tags: - Files summary: /v1/files/{Bucket}/{file_path} description: | Call this endpoint to upload a file to the specified bucket and path. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: file_path in: path schema: type: string description: | The target file path. The parameter specifies full path to the file, for example: `folder1/folder2/file.png` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the file. This is used for conditional requests to ensure that the file is only uploaded if it matches the specified ETag. If the file does not exist, and this header is provided, the request returns 412 Precondition Failed response. If this header is not provided or the value is "*", any existing file at the specified path will be overwritten. - name: If-None-Match in: header schema: type: string description: | The entity tag (ETag) used to ensure that the file is only uploaded if it does not already exist. The only supported value is "*". requestBody: required: true content: multipart/form-data: schema: type: object properties: file: type: string format: binary description: | A part of multipart/form-data request responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string contentLength: type: integer contentType: type: string examples: Example: value: "name": "file.png" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png" "nodeType": "ITEM" "resourceType": "FILE" "contentLength": 128630 "contentType": "image/png" '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X PUT https://chat..com/v1/files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png \ -H "Api-Key: DIAL_API_KEY" \ -F "data=@file.png" get: operationId: downloadFile tags: - Files summary: /v1/files/{Bucket}/{file_path} description: | Call this endpoint to get a file content. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: file_path in: path schema: type: string description: | The target file path. The parameter specifies full path to the file, for example: `folder1/folder2/file.png` required: true responses: '200': description: Success content: application/octet-stream: schema: type: string format: binary examples: Example: value: "" '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png \ -H "Api-Key: DIAL_API_KEY" \ -o new_file.png delete: operationId: deleteFile tags: - Files summary: /v1/files/{Bucket}/{file_path} description: | Call this endpoint to delete the file. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: file_path in: path schema: type: string description: | The target file path. The parameter specifies full path to the file, for example: `folder1/folder2/file.png` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the file. This is used for conditional requests to ensure that the file is only deleted if it matches the specified ETag. responses: '200': description: Success '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png \ -H "Api-Key: DIAL_API_KEY" /v1/metadata/files/{Bucket}/{Path}: get: operationId: getFileMetadata tags: - Files summary: /v1/metadata/files/{Bucket}/{Path} description: | Call this endpoint to retrieve metadata for a file or folder at the specified path. If the path is a folder, it must end with a "/". If it is called for a folder, there can be optional `nextToken` field in the response to be used to request next items if present. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: Path in: path schema: type: string description: | The parameter specifies path to the requested directory or file, for example: `folder1/folder2/`. Note, it could be empty if you want to list the root folder. required: true - in: query name: token schema: type: string description: The token from the previous request to request next items. - in: query name: limit schema: type: integer minimum: 1 maximum: 1000 default: 100 description: Limit on the number of items in the response. - in: query name: recursive schema: type: boolean default: false description: | If true, returns items recursively without nested folder metadata. For example, request for `/a/` will contain only metadata for items `/a/b/c` and `/a/d/e/f`, but it won't contain metadata for folders: `/a/b/`, `/a/d/`, `/a/d/e`. - in: query name: permissions schema: type: boolean default: false description: If true, returns the permissions applicable to the requestor, indicating what actions they can perform on the files. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string description: This field is not available for folders. parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string etag: type: string description: This field is not available for folders. createdAt: type: integer description: The creation time is not supported by all storage providers. updatedAt: type: integer contentLength: type: integer contentType: type: string permissions: type: array items: type: string enum: - READ - WRITE - SHARE items: type: array description: This field is only available for folders. items: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer contentLength: type: integer contentType: type: string permissions: type: array items: type: string enum: - READ - WRITE - SHARE examples: Folder: value: name: folder2 parentPath: folder1 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ nodeType: FOLDER resourceType: FILE permissions: - READ - WRITE items: - name: file.png parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png nodeType: ITEM resourceType: FILE updatedAt: 1707876435000 createdAt: 1707876435000 contentLength: 128630 contentType: image/png permissions: - READ - WRITE File: value: name: file.png author: the name of the file author parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png nodeType: ITEM resourceType: FILE etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 contentLength: 128630 contentType: image/png permissions: - READ - WRITE '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/metadata/files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ \ -H "Api-Key: DIAL_API_KEY" /v1/ops/resource/move: post: operationId: moveResource tags: - Files - Conversations - Prompts - Applications summary: /v1/ops/resource/move description: | Moves the source resource to the destination. requestBody: required: true content: application/json: schema: type: object properties: sourceUrl: type: string description: Source URL. Must belong to the user. destinationUrl: type: string description: Destination URL. Must belong to the user and be of the same type as the source URL. overwrite: type: boolean description: If true, the destination URL will be overwritten if it already exists. examples: Example: value: sourceUrl: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/file.txt destinationUrl: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/file.txt overwrite: true responses: '200': description: Success '400': description: Bad request '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/move \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "sourceUrl": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/file.txt", "destinationUrl": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/file.txt", "overwrite": true }' /v1/ops/resource/copy: post: operationId: copyResource tags: - Files - Conversations - Prompts - Applications summary: /v1/ops/resource/copy description: | Copies the source resource to the destination. requestBody: required: true content: application/json: schema: type: object properties: sourceUrl: type: string description: Source URL. Must belong to the user. destinationUrl: type: string description: Destination URL. Must belong to the user and be of the same type as the source URL. overwrite: type: boolean description: If true, the destination URL will be overwritten if it already exists. examples: Example: value: sourceUrl: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/file.txt destinationUrl: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/file.txt overwrite: true responses: '200': description: Success '400': description: Bad request '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/copy \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "sourceUrl": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/file.txt", "destinationUrl": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/file.txt", "overwrite": true }' /v1/conversations/{Bucket}/{conversation_path}: put: operationId: saveConversation tags: - Conversations summary: /v1/conversations/{Bucket}/{conversation_path} description: | Call this endpoint to add a conversation to the specified bucket and path. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: conversation_path in: path schema: type: string description: | The target conversation path. The parameter specifies full path to the conversation, for example: `folder1/folder2/conversation_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the conversation. This is used for conditional requests to ensure that the conversation is only uploaded if it matches the specified ETag. If the conversation does not exist, this header is ignored. If this header is not provided or the value is "*", any existing conversation at the specified path will be overwritten. - name: If-None-Match in: header schema: type: string description: | The entity tag (ETag) used to ensure that the conversation is only uploaded if it does not already exist. The only supported value is "*". requestBody: required: true content: application/json: schema: type: string description: | An arbitrary string representing the conversation. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer examples: Example: value: "name": "conversation_name" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name" "nodeType": "ITEM" "resourceType": "CONVERSATION" "createdAt": 1707871723597 "updatedAt": 1707876304850 '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X PUT https://chat..com/v1/conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "messages": [{"role": "user", "content": "Hello!"}] }' get: operationId: getConversation tags: - Conversations summary: /v1/conversations/{Bucket}/{conversation_path} description: | Call this endpoint to get the conversation. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: conversation_path in: path schema: type: string description: | The target conversation path. The parameter specifies full path to the conversation, for example: `folder1/folder2/conversation_name` required: true responses: '200': description: Success content: application/json: schema: type: string examples: Example: value: | { "messages": [{"role": "user", "content": "Hello!"}] } '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name \ -H "Api-Key: DIAL_API_KEY" delete: operationId: deleteConversation tags: - Conversations summary: /v1/conversations/{Bucket}/{conversation_path} description: | Call this endpoint to delete the conversation. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: conversation_path in: path schema: type: string description: | The target conversation path. The parameter specifies full path to the conversation, for example: `folder1/folder2/conversation_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the conversation. This is used for conditional requests to ensure that the conversation is only deleted if it matches the specified ETag. responses: '200': description: Success '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name \ -H "Api-Key: DIAL_API_KEY" /v1/metadata/conversations/{Bucket}/{Path}: get: operationId: getConversationMetadata tags: - Conversations summary: /v1/metadata/conversations/{Bucket}/{Path} description: | Call this endpoint to get metadata for a folder or an item. If the path is a folder, it must end with a "/". If it is called for a folder, there can be optional `nextToken` field in the response to be used to request next items if present. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: Path in: path schema: type: string description: | The parameter specifies path to the requested directory or a conversation, for example: `folder1/folder2/`. Note, it could be empty if you want to list the root folder. required: true - in: query name: token schema: type: string description: The token from the previous request to request next items. - in: query name: limit schema: type: integer minimum: 1 maximum: 1000 default: 100 description: Limit on the number of items in the response. - in: query name: recursive schema: type: boolean default: false description: | If true, returns items recursively without nested folder metadata. For example, request for `/a/` will contain only metadata for items `/a/b/c` and `/a/d/e/f`, but it won't contain metadata for folders: `/a/b/`, `/a/d/`, `/a/d/e`. - in: query name: permissions schema: type: boolean default: false description: If true, returns the permissions applicable to the requestor, indicating what actions they can perform on the conversations. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string description: This field is not available for folders. parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string etag: type: string description: This field is not available for folders. createdAt: type: integer description: The creation time is not supported by all storage providers. updatedAt: type: integer permissions: type: array items: type: string enum: - READ - WRITE - SHARE items: type: array items: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer permissions: type: array items: type: string enum: - READ - WRITE - SHARE nextToken: type: string description: An optional field that can be used to request next items if present. examples: Folder: value: name: folder2 parentPath: folder1 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ nodeType: FOLDER resourceType: CONVERSATION permissions: - READ - WRITE items: - name: conversation_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name nodeType: ITEM resourceType: CONVERSATION updatedAt: 1707876435000 permissions: - READ - WRITE Conversation: value: name: conversation_name author: the name of the author of the conversation parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name nodeType: ITEM resourceType: CONVERSATION etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 permissions: - READ - WRITE '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/metadata/conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ \ -H "Api-Key: DIAL_API_KEY" /v1/prompts/{Bucket}/{prompt_path}: put: operationId: savePrompt tags: - Prompts summary: /v1/prompts/{Bucket}/{prompt_path} description: | Call this endpoint to add a prompt to the specified bucket and path. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: prompt_path in: path schema: type: string description: | The target prompt path. The parameter specifies full path to the prompt, for example: `folder1/folder2/prompt_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the prompt. This is used for conditional requests to ensure that the prompt is only uploaded if it matches the specified ETag. If the prompt does not exist, this header is ignored. If this header is not provided or the value is "*", any existing prompt at the specified path will be overwritten. - name: If-None-Match in: header schema: type: string description: | The entity tag (ETag) used to ensure that the prompt is only uploaded if it does not already exist. The only supported value is "*". requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PromptRequest' examples: Example: value: name: My prompt id: prompt_123 folderId: public/folder/ content: The content of the prompt responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string description: Resource name provided in the prompt path parentPath: type: string description: Relative path to the resource starting with the bucket identifier bucket: type: string description: User's bucket name url: type: string description: A full path to the prompt nodeType: type: string description: A node type enum: - ITEM - FOLDER resourceType: type: string description: A resource type etag: type: string description: This field is not available for folders. createdAt: type: integer description: The creation time is not supported by all storage providers. updatedAt: type: integer permissions: type: array items: type: string enum: - READ - WRITE - SHARE examples: Example: value: name: prompt_name parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name nodeType: ITEM resourceType: PROMPT etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb createdAt: 1707871723597 updatedAt: 1707876304850 permissions: - READ - WRITE '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X PUT https://chat..com/v1/prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name \ -H "Api-Key: DIAL_API_KEY" \ -d 'You are a helpful assistant' get: operationId: getPrompt tags: - Prompts summary: /v1/prompts/{Bucket}/{prompt_path} description: | Call this endpoint to get the prompt. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: prompt_path in: path schema: type: string description: | The target prompt path. The parameter specifies full path to the prompt, for example: `folder1/folder2/prompt_name` required: true responses: '200': description: Success content: application/json: schema: type: object properties: id: type: string description: Prompt unique identifier folderId: type: string description: Path to the folder where prompt located according to the user's root name: type: string description: Prompt's display name content: type: string description: Prompt content examples: Example: value: id: prompt_123 folderId: public/folder/ name: My prompt content: The content of the prompt '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name \ -H "Api-Key: DIAL_API_KEY" delete: operationId: deletePrompt tags: - Prompts summary: /v1/prompts/{Bucket}/{prompt_path} description: | Call this endpoint to delete the prompt. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: prompt_path in: path schema: type: string description: | The target prompt path. The parameter specifies full path to the prompt, for example: `folder1/folder2/prompt_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the prompt. This is used for conditional requests to ensure that the prompt is only deleted if it matches the specified ETag. responses: '200': description: Success '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name \ -H "Api-Key: DIAL_API_KEY" /v1/metadata/prompts/{Bucket}/{Path}: get: operationId: getPromptMetadata tags: - Prompts summary: /v1/metadata/prompts/{Bucket}/{Path} description: | Call this endpoint to get metadata for a folder or an item. If the path is a folder, it must end with a "/". If it is called for a folder, there can be optional `nextToken` field in the response to be used to request next items if present. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: Path in: path schema: type: string description: | The parameter specifies path to a directory or a prompt, for example: `folder1/folder2/`. required: true - in: query name: token schema: type: string description: The token from the previous request to request next items. - in: query name: limit schema: type: integer minimum: 1 maximum: 1000 default: 100 description: Limit on the number of items in the response. - in: query name: recursive schema: type: boolean default: false description: | If true, returns items recursively without nested folder metadata. For example, request for `/a/` will contain only metadata for items `/a/b/c` and `/a/d/e/f`, but it won't contain metadata for folders: `/a/b/`, `/a/d/`, `/a/d/e`. - in: query name: permissions schema: type: boolean default: false description: If true, returns the permissions applicable to the requestor, indicating what actions they can perform on the prompts. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string contentLength: type: integer updatedAt: type: integer items: type: array items: type: object properties: name: type: string author: type: string etag: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string updatedAt: type: integer nextToken: type: string description: An optional field that can be used to request next items if present. etag: type: string description: This field is not available for folders. examples: Folder: value: "name": "folder2" "parentPath": "folder1" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/" "nodeType": "FOLDER" "resourceType": "PROMPT" items: - name: "prompt_name" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name" "nodeType": "ITEM" "resourceType": "PROMPT" "updatedAt": 1707876435000 Prompt: value: "name": "prompt_name" "author": "the name of the author" "etag": "7dfb93c3c62b88e9a75ff36a6af6c7eb" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name" "nodeType": "ITEM" "resourceType": "PROMPT" "updatedAt": 1707876435000 '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/metadata/prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ \ -H "Api-Key: DIAL_API_KEY" /v1/toolsets/{Bucket}/{toolset_path}: put: operationId: saveToolSet tags: - Toolsets summary: /v1/toolsets/{Bucket}/{toolset_path} description: Call this endpoint to add a toolset to the specified bucket and path or update the existing toolset. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: toolset_path in: path schema: type: string description: | The target toolset path. The parameter specifies full path to the toolset, for example: `folder1/folder2/toolset_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the toolset. This is used for conditional requests to ensure that the toolset is only uploaded if it matches the specified ETag. If the toolset does not exist, this header is ignored. If this header is not provided or the value is "*", any existing toolset at the specified path will be overwritten. - name: If-None-Match in: header schema: type: string description: | The entity tag (ETag) used to ensure that the toolset is only uploaded if it does not already exist. The only supported value is "*". requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Toolset' examples: ToolsetWithOauthAuthStatic: value: endpoint: http://toolset/v1/mcp iconUrl: http://toolset/icon.svg description: My toolset description displayName: My Toolset displayVersion: "1.1" forward_per_request_key: true transport: HTTP allowedTools: - tool1 - tool2 auth_settings: authentication_type: OAUTH client_id: my-client-id client_secret: my-client-secret redirect_uri: https://myapp.com/toolset/sign-in authorization_endpoint: https://authserver.com/authorize token_endpoint: https://authserver.com/token code_challenge_method: S256 scopes_supported: [ scope1, scope2 ] ToolsetWithOauthAuthDynamic: value: endpoint: http://toolset/v1/mcp iconUrl: http://toolset/icon.svg description: My toolset description displayName: My Toolset displayVersion: "1.1" forward_per_request_key: true transport: HTTP allowedTools: - tool1 - tool2 auth_settings: authentication_type: OAUTH redirect_uri: https://myapp.com/toolset/sign-in ToolsetWithApiKeyAuth: value: endpoint: http://toolset/v1/mcp iconUrl: http://toolset/icon.svg description: My toolset description displayName: My Toolset displayVersion: "1.1" forward_per_request_key: true transport: HTTP allowedTools: - tool1 - tool2 auth_settings: authentication_type: API_KEY api_key_header: X-API-KEY ToolsetWithNoneAuth: value: endpoint: http://toolset/v1/mcp iconUrl: http://toolset/icon.svg description: My toolset description displayName: My Toolset displayVersion: "1.1" forward_per_request_key: true transport: HTTP allowedTools: - tool1 - tool2 auth_settings: authentication_type: NONE responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer etag: type: string examples: Example: value: name: toolset-name parentPath: folder1/folder2 bucket: encrypted-bucket url: toolsets/encrypted-bucket/folder1/folder2/toolset-name nodeType: ITEM resourceType: TOOL_SET createdAt: 1707871723597 updatedAt: 1707876304850 etag: 59b9715451eac909281701f490633b5c '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X PUT https://chat..com/v1/toolsets/ENCRYPTED_BUCKET/my-toolset \ -H "Api-Key: DIAL_API_KEY" get: operationId: getCustomToolSet tags: - Toolsets summary: /v1/toolsets/{Bucket}/{toolset_path} description: Call this endpoint to retrieve a specific toolset. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: toolset_path in: path schema: type: string description: | The target toolset path. The parameter specifies full path to the toolset, for example: `folder1/folder2/toolset_name` required: true responses: '200': description: Success content: application/json: schema: type: object $ref: '#/components/schemas/Toolset' examples: ToolsetWithOauthAuth: value: name: toolsets/encrypted-bucket/folder/toolSetName-1 endpoint: http://toolset/v1/mcp reference: bf9500f0-6977-4cf3-8a01-a29c8431cffc forward_auth_token: false defaults: { } interceptors: [ ] icon_url: http://toolset/icon.svg description: My toolset description display_name: My Toolset user_roles: - admin description_keywords: - keyword1 - keyword2 max_retry_attempts: 2 author: Author's name created_at: 1672534800 updated_at: 1672534900 forward_per_request_key: false transport: HTTP allowed_tools: - tool1 - tool2 auth_settings: authentication_type: OAUTH client_id: my-client-id redirect_uri: https://myapp.com/toolset/sign-in authorization_endpoint: https://authserver.com/authorize token_endpoint: https://authserver.com/token code_challenge_method: S256 scopes_supported: [scope1, scope2] global_auth_status: SIGNED_OUT user_level_auth_status: SIGNED_OUT ToolsetWithApiKeyAuth: value: name: toolsets/encrypted-bucket/folder/toolSetName-1 endpoint: http://toolset/v1/mcp reference: bf9500f0-6977-4cf3-8a01-a29c8431cffc forward_auth_token: false defaults: { } interceptors: [ ] icon_url: http://toolset/icon.svg description: My toolset description display_name: My Toolset user_roles: - admin description_keywords: - keyword1 - keyword2 max_retry_attempts: 2 author: Author's name created_at: 1672534800 updated_at: 1672534900 forward_per_request_key: false transport: HTTP allowed_tools: - tool1 - tool2 auth_settings: authentication_type: API_KEY api_key_header: X-API-KEY global_auth_status: SIGNED_OUT user_level_auth_status: SIGNED_OUT ToolsetWithNoneAuth: value: name: toolsets/encrypted-bucket/folder/toolSetName-1 endpoint: http://toolset/v1/mcp reference: bf9500f0-6977-4cf3-8a01-a29c8431cffc forward_auth_token: false defaults: { } interceptors: [ ] icon_url: http://toolset/icon.svg description: My toolset description display_name: My Toolset user_roles: - admin description_keywords: - keyword1 - keyword2 max_retry_attempts: 2 author: Author's name created_at: 1672534800 updated_at: 1672534900 forward_per_request_key: false transport: HTTP allowed_tools: - tool1 - tool2 auth_settings: authentication_type: NONE global_auth_status: SIGNED_OUT user_level_auth_status: SIGNED_OUT '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/toolsets/ENCRYPTED_BUCKET/my-toolset \ -H "Api-Key: DIAL_API_KEY" delete: operationId: deleteToolSet tags: - Toolsets summary: /v1/toolsets/{Bucket}/{toolset_path} description: Call this endpoint to delete a toolset from the specified path. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: toolset_path in: path schema: type: string description: | The target toolset path. The parameter specifies full path to the toolset, for example: `folder1/folder2/toolset_name` required: true - name: If-Match in: header schema: type: string description: | The entity tag (ETag) of the toolset. This is used for conditional requests to ensure that the toolset is only deleted if it matches the specified ETag. responses: '200': description: Success '401': description: Invalid Authentication '412': description: Precondition Failed - ETag mismatch x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/toolsets/ENCRYPTED_BUCKET/my-toolset \ -H "Api-Key: DIAL_API_KEY" /v1/toolset/{toolset_id}/tools: get: operationId: getAllToolSetTools tags: - Toolsets summary: /v1/toolset/{toolset_id}/tools description: Call this endpoint to retrieve all tools supported by a specific MCP server. Available to admins and toolset owners. Used during toolset configuration to select allowed tools. parameters: - name: toolset_id in: path schema: type: string description: | The target toolset ID. The parameter specifies the unique identifier of the toolset. required: true responses: '200': description: Success content: application/json: schema: type: object properties: id: type: string result: type: object properties: tools: type: array items: type: object properties: name: type: string title: type: string examples: Example: value: { "id": "1", "result": { "tools": [ { "name": "tool_name", "title": "tool_title" }, { "name": "tool_name", "title": "tool_title" } ] } } '403': description: Forbidden content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/toolset/{toolset_id}/tools -H "Api-Key: DIAL_API_KEY" /v1/toolset/{toolset_id}/allowed-tools: get: operationId: getAllToolSetAllowedTools tags: - Toolsets summary: /v1/toolset/{toolset_id}/allowed-tools description: Call this endpoint to retrieve a filtered list of all allowed tools for a specific MCP server. parameters: - name: toolset_id in: path schema: type: string description: | The target toolset ID. The parameter specifies the unique identifier of the toolset. required: true responses: '200': description: Success content: application/json: schema: type: object properties: id: type: string result: type: object properties: tools: type: array items: type: object properties: name: type: string title: type: string examples: Example: value: { "id": "1", "result": { "tools": [ { "name": "tool_name", "title": "tool_title" }, { "name": "tool_name", "title": "tool_title" } ] } } '400': description: Bad request content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/toolset/{toolset_id}/allowed-tools -H "Api-Key: DIAL_API_KEY" /v1/ops/toolset/signin: post: operationId: toolsetSignin tags: - Toolsets summary: /v1/ops/toolset/signin description: Authenticates a user with a specified Toolset using OAUTH or API_KEY. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The Toolset URL (e.g., toolsets/{bucket}/{path}). credentials_level: type: string enum: [ GLOBAL, APP, USER ] description: The scope of credentials for the Toolset. authentication_type: type: string enum: [ OAUTH, API_KEY ] description: The authentication method. code: type: string description: The authorization code (OAUTH only). api_key: type: string description: The API key value (API_KEY only). required: - url - credentials_level - authentication_type examples: ToolsetWithOauthAuth: value: url: toolsets/my-encrypted-bucket/toolSetName-1 credentials_level: USER authentication_type: OAUTH code: my-auth-code-value ToolsetWithApiKeyAuth: value: url: toolsets/encrypted-bucket/toolSetName-1 credentials_level: USER authentication_type: API_KEY api_key: my-api-key-value responses: '200': description: Success content: application/json: schema: type: object properties: status: type: string description: Signin status. '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/toolset/signout: post: operationId: toolSetSignout tags: - Toolsets summary: /v1/ops/toolset/signout description: Logs the user out from the Toolset by removing the associated credentials. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The Toolset URL (e.g., toolsets/{bucket}/{path}). credentials_level: type: string enum: [ GLOBAL, APP, USER ] description: The scope of credentials for the Toolset. authentication_type: type: string enum: [ OAUTH, API_KEY ] description: The authentication method. required: - url - credentials_level - authentication_type examples: ToolsetWithOauthAuth: value: url: toolsets/my-encrypted-bucket/toolSetName-1 credentials_level: USER authentication_type: OAUTH ToolsetWithApiKeyAuth: value: url: toolsets/encrypted-bucket/toolSetName-1 credentials_level: USER authentication_type: API_KEY responses: '200': description: Success content: application/json: schema: type: object properties: status: type: string description: Signout status. '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/metadata/toolsets/{Bucket}/{Path}: get: operationId: getToolSetMetadata tags: - Toolsets summary: /v1/metadata/toolsets/{Bucket}/{Path} description: | Call this endpoint to get metadata for a toolset folder or item.
If the path is a folder, it must end with a "/". If it is called for a folder, there can be optional `nextToken` field in the response to be used to request next items if present. parameters: - name: Bucket in: path schema: type: string description: The target bucket. required: true - name: Path in: path schema: type: string description: | The parameter specifies path to a directory or a toolset, for example: `folder1/folder2/`. required: true - in: query name: token schema: type: string description: The token from the previous request to request next items. - in: query name: limit schema: type: integer minimum: 1 maximum: 1000 default: 100 description: Limit on the number of items in the response. - in: query name: recursive schema: type: boolean default: false description: | If true, returns items recursively without nested folder metadata. For example, request for `/a/` will contain only metadata for items `/a/b/c` and `/a/d/e/f`, but it won't contain metadata for folders: `/a/b/`, `/a/d/`, `/a/d/e`. - in: query name: permissions schema: type: boolean default: false description: If true, returns the permissions applicable to the requestor, indicating what actions they can perform on the toolsets. responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string author: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string contentLength: type: integer updatedAt: type: integer items: type: array items: type: object properties: name: type: string author: type: string etag: type: string parentPath: type: string bucket: type: string url: type: string nodeType: type: string resourceType: type: string updatedAt: type: integer nextToken: type: string description: An optional field that can be used to request next items if present. etag: type: string description: This field is not available for folders. examples: Folder: value: "name": "folder2" "parentPath": "folder1" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/" "nodeType": "FOLDER" "resourceType": "TOOL_SET" items: - name: "toolset_name" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/toolset_name" "nodeType": "ITEM" "resourceType": "TOOL_SET" "updatedAt": 1707876435000 Toolset: value: "name": "toolset_name" "author": "the name of the author" "etag": "7dfb93c3c62b88e9a75ff36a6af6c7eb" "parentPath": "folder1/folder2" "bucket": "3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST" "url": "toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/toolset_name" "nodeType": "ITEM" "resourceType": "TOOL_SET" "updatedAt": 1707876435000 '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/metadata/toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/ \ -H "Api-Key: DIAL_API_KEY" /v1/ops/publication/list: post: operationId: getPublications tags: - Publications summary: /v1/ops/publication/list description: Call this endpoint to get a list of publication requests. For admins, it is a list of all publication requests that are `PENDING` for review (approve or reject). For users, it is a list of all publication requests created by a particular user. Refer to documentation to learn more about working with publications for [users](https://docs.dialx.ai/platform/collaboration-intro#publication) and [admins](https://docs.dialx.ai/platform/admin-panel/approvals-prompt-publications). requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The publication URL. For admins it is `publications/public/`. For users it is `publications/user_bucket/`. examples: ExampleUser: value: url: "publications/3CcedGxCx23EwiVbV/" ExampleAdmin: value: url: "publications/public/" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationResponse' examples: ExampleUser: value: publications: - url: publications/3CcedGxCx23EwiVbV/0123 author: the name of the publication request author displayAuthor: the name of the publication request author displayed on UI targetFolder: public/folder/ status: PENDING createdAt: 0 resourceTypes: [ "CONVERSATION" ] ExampleAdmin: value: publications: - url: publications/3CcedGxCx23EwiVbV/0123 author: the name of the publication request author displayAuthor: the name of the publication request author displayed on UI name: Publication name targetFolder: public/folder/ status: PENDING createdAt: 0 resourceTypes: [ "CONVERSATION" ] '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/get: post: operationId: getPublication tags: - Publications summary: /v1/ops/publication/get description: Call this endpoint to get a specific publication request. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The publication request. Template is `publications/bucketId/requestId`. examples: Example: value: url: "publications/3CcedGxCx23EwiVbV/0123" responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/GetPublicationResponseObject' examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 targetFolder: public/folder/ author: the name of the publication request author displayAuthor: the name of the publication request author displayed on UI status: APPROVED createdAt: 0 resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation reviewUrl: conversations/3CcedGxCx23EwiVbV/conversation rules: - function: EQUAL source: roles targets: - user resourceTypes: - CONVERSATION '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/create: post: operationId: createPublication tags: - Publications summary: /v1/ops/publication/create description: Call this endpoint to create a publish or unpublish request. requestBody: content: application/json: schema: $ref: '#/components/schemas/PublicationRequest' examples: Example: value: name: Publication name displayAuthor: The author's name displayed on UI targetFolder: public/folder/ resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation publishCredentials: true rules: - function: EQUAL source: roles targets: - user responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationResponseObject' examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 name: Publication name author: The name of the publication request author displayAuthor: The author's name displayed on UI targetFolder: public/folder/ status: PENDING createdAt: 0 resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation reviewUrl: conversations/3CcedGxCx23EwiVbV/conversation rules: - function: EQUAL source: roles targets: - user resourceTypes: - CONVERSATION '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/update: post: operationId: updatePublication tags: - Publications summary: /v1/ops/publication/update description: Call this endpoint to update a publish request. Available for admins. requestBody: content: application/json: schema: $ref: '#/components/schemas/UpdatePublicationRequest' examples: Example: value: name: Publication name displayAuthor: The author's name displayed on UI url: publications/3CcedGxCx23EwiVbV/0123 targetFolder: public/folder/ resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation publishCredentials: true rules: - function: EQUAL source: roles targets: - user responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationResponseObject' examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 name: Publication name author: The name of the publication request author displayAuthor: The author's name displayed on UI targetFolder: public/folder/ status: PENDING createdAt: 0 resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation reviewUrl: conversations/3CcedGxCx23EwiVbV/conversation rules: - function: EQUAL source: roles targets: - user resourceTypes: - CONVERSATION '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/delete: post: operationId: deletePublication tags: - Publications summary: /v1/ops/publication/delete description: Call this endpoint to delete the publication request. Only requests that are in the `PENDING` status can be deleted. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The publication URL. Template is `publications/bucketId/requestId`. examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 responses: '200': description: Success '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/reject: post: operationId: rejectPublication tags: - Publications summary: /v1/ops/publication/reject description: Admins only!
Call this endpoint to reject the publication request. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The publication URL. Template is `publications/bucketId/requestId`. comment: type: string description: Rejection comment. examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 comment: The rejection reason. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationResponseObject' examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 name: Publication name targetFolder: public/folder/ status: REJECTED createdAt: 0 resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation reviewUrl: conversations/3CcedGxCx23EwiVbV/conversation rules: - function: EQUAL source: roles targets: - user resourceTypes: - CONVERSATION '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/approve: post: operationId: approvePublication tags: - Publications summary: /v1/ops/publication/approve description: Admins only!
Call this endpoint to approve the publication request. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: The publication URL. Template is `publications/bucketId/requestId`. examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationResponseObject' examples: Example: value: url: publications/3CcedGxCx23EwiVbV/0123 name: Publication name targetFolder: public/folder/ status: APPROVED createdAt: 0 resources: - action: ADD sourceUrl: conversations/3CcedGxCx23EwiVbV/my/folder/conversation targetUrl: conversations/public/folder/conversation reviewUrl: conversations/3CcedGxCx23EwiVbV/conversation rules: - function: EQUAL source: roles targets: - user resourceTypes: - CONVERSATION '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/publication/rule/list: post: operationId: getPublicationRules tags: - Publications summary: /v1/ops/publication/rule/list description: Call this endpoint to get a list of rules for publications. requestBody: required: true content: application/json: schema: type: object properties: url: type: string description: Publication public folder URL. Template is `public/folderName` examples: Example: value: url: publications/3CcedGxCx23EwiVbV/ responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/PublicationRules' examples: Example: value: rules: public/folder: - source: roles function: EQUAL targets: - user '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/resource/per-request-permissions/grant: post: operationId: grantPerRequestPermissions tags: - Sharing summary: /v1/ops/resource/per-request-permissions/grant description: | Call this endpoint to share resources between deployments (toolsets and applications). **Important**: This request can be authorized only with a [per-request API](https://docs.dialx.ai/platform/core/per-request-keys) key issued by DIAL Core for the deployment sending the request. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/sharing) for more details on how to share resources between deployments. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to share. items: type: object properties: url: type: string description: | A relative url of the resource to share. permissions: type: array description: Lists the permissions you grant for the resource. items: type: string enum: - READ - WRITE receiver: type: string description: The ID of the receiving DIAL deployment (application or toolset). examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ - url: files/3CcedGxCx23EwiVbVms6KypuBQ65miviST/folder1/image.png permissions: - WRITE receiver: deploymentID responses: '200': description: Success '403': description: Unauthorized - Operation is only permitted by per request API key x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/per-request-permissions/grant \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name", "permissions": ["READ"] }, { "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png", "permissions": ["WRITE"] } ], "receiver": "132465798" }' /v1/ops/resource/per-request-permissions/revoke: post: operationId: revokePerRequestPermissions tags: - Sharing summary: /v1/ops/resource/per-request-permissions/revoke description: | Call this endpoint to revoke access to a shared resources between deployments (toolsets and applications). **Important**: This request can be authorized only with a [per-request API](https://docs.dialx.ai/platform/core/per-request-keys) key issued by DIAL Core for the deployment sending the request. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/sharing) for more details on how to share resources between deployments. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to share. items: type: object properties: url: type: string description: | A relative url of the resource to share. permissions: type: array description: Lists the permissions you grant for the resource. items: type: string enum: - READ - WRITE receiver: type: string description: The ID of the receiving DIAL deployment (application or toolset). examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ - url: files/3CcedGxCx23EwiVbVms6KypuBQ65miviST/folder1/image.png permissions: - WRITE receiver: deploymentID responses: '200': description: Success '403': description: Unauthorized - Operation is only permitted by per request API key x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/per-request-permissions/revoke \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name", "permissions": ["READ"] }, { "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png", "permissions": ["WRITE"] } ], "receiver": "132465798" }' /v1/ops/resource/per-request-permissions/list: post: operationId: getPerRequestPermissions tags: - Sharing summary: /v1/ops/resource/per-request-permissions/list description: | Call this endpoint to get a list of shared resources by or with a specific deployment (toolset and application). **Important**: This request can be authorized only with a [per-request API](https://docs.dialx.ai/platform/core/per-request-keys) key issued by DIAL Core for the deployment sending the request. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/sharing) for more details on how to share resources between deployments. requestBody: required: true content: application/json: schema: type: object properties: with: type: string enum: - me - others description: | Currently, supported the next options: - `me`: returns shared resources with you. - `others`: returns resources that you have shared with others examples: Example: value: with: me responses: '200': description: Success content: application/json: schema: type: object properties: resources: type: array items: type: object properties: url: type: string permissions: description: | Lists the permissions you have on the resource if `with` is set to "me". Lists the permissions you have granted to others if `with` is set to "others". type: array items: type: string enum: - READ - WRITE receivers: type: array items: type: object properties: receiver: type: string resources: type: array items: type: object properties: url: type: string permissions: type: array items: type: string enum: - READ - WRITE examples: me: value: resources: - url: prompts/3CcedGxCx23EwiVbVmyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ others: value: receivers: - receiver: "112345678" resources: - url: prompts/3CcedGxCx23EwiVbVmyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ '403': description: Unauthorized - Operation is only permitted by per request API key x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/per-request-permissions/list \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "with": "me", }' /v1/ops/resource/share/create: post: operationId: shareResource tags: - Sharing summary: /v1/ops/resource/share/create description: | Call this endpoint to share and re-share resources. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/sharing) for more details on how to share resources. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to share. items: type: object properties: url: type: string description: | A relative url of the resource to share. permissions: type: array description: Lists the permissions you have on the resource. items: type: string enum: - READ - WRITE - SHARE shareCredentials: type: boolean description: Indicates whether global resource credentials should be shared with user. default: false invitationType: type: string description: The invitation type. Only `link` is currently supported. maxAcceptedUsers: type: integer description: The number of users that can accept the invitation link. Defaults to unlimited. examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ - url: files/3CcedGxCx23EwiVbVms6KypuBQ65miviST/folder1/image.png permissions: - WRITE - url: files/3CcedGxCx23EwiVbVmscVkKypuBQ65miviST/folder1/document.pdf permissions: - SHARE shareCredentials: false - url: toolsets/3CcedGxCx23EwiVbVmscVkKypuBQ65miviST/folder1/my-toolset permissions: - READ shareCredentials: true invitationType: link maxAcceptedUsers: 10 responses: '200': description: Success content: application/json: schema: type: object properties: invitationLink: type: string examples: Example: value: invitationLink: v1/invitations/2818T2YRgFaMt8YW176ix7f3adFjxBx5TMQbzmnxgRGNPbDtctJ1wwGkigG78YU6juKnUKRWPNAt1f8Cna5Do7X48FnXwHs5MutEpefm6jTuMQ '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/share/create \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name" }, { "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png" } ], "invitationType": "link" }' /v1/ops/resource/share/list: post: operationId: getSharedResources tags: - Sharing summary: /v1/ops/resource/share/list description: | Call this endpoint to get the list of shared resources. Returns only resources that were accepted. requestBody: required: true content: application/json: schema: type: object properties: resourceTypes: type: array items: type: string enum: - FILE - PROMPT - CONVERSATION - APPLICATION - TOOL_SET with: type: string enum: - me - others description: | Currently, supported the next options: - `me`: returns shared resources with you. - `others`: returns resources that you have shared with others includeUserInfo: type: boolean description: | If true, includes additional user information such as resource owner display name, users who have shared the resource with you, and users with whom you have shared the resource. default: false examples: Example: value: resourceTypes: - FILE - PROMPT - CONVERSATION - APPLICATION - TOOL_SET with: me responses: '200': description: Success content: application/json: schema: type: object properties: resources: type: array items: type: object properties: nodeType: type: string resourceType: type: string bucket: type: string parentPath: type: string name: type: string url: type: string permissions: description: | Lists the permissions you have on the resource if `with` is set to "me". Lists the permissions you have granted to others if `with` is set to "others". type: array items: type: string enum: - READ - WRITE - SHARE author: description: | Resource owner display name (a configurable claim from JWT or a project name for API keys). The field is populated if `with` is set to "me" and `includeUserInfo` is true. type: string sharedBy: description: | A list of users who have shared the resource with you. The field is populated if `with` is set to "me" and `includeUserInfo` is true. type: array items: type: object properties: user: description: User display name (a configurable claim from JWT or a project name for API keys). type: string acceptedAt: description: The timestamp when the shared resource has been accepted. type: integer permissions: description: A list of permissions granted by the user. type: array items: type: string enum: - READ - WRITE - SHARE sharedWith: description: | A list of users with whom you have shared the resource. The field is populated if `with` is set to "others" and `includeUserInfo` is true. type: array items: type: object properties: user: description: User display name (a configurable claim from JWT or a project name for API keys). type: string permissions: description: A list of permissions granted to the user. type: array items: type: string enum: - READ - WRITE - SHARE shareCredentials: type: boolean description: Indicates whether global resource credentials were shared with user. default: false examples: Example: value: resources: - nodeType: ITEM resourceType: PROMPT bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST parentPath: folder1/folder2 name: prompt_name url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - WRITE - nodeType: ITEM resourceType: FILE bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST parentPath: folder1 name: image.png url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png permissions: - READ author: user_2 sharedBy: - user: user_1 acceptedAt: 1707874031765 permissions: - READ - user: user_2 acceptedAt: 1707875031765 permissions: - WRITE - nodeType: ITEM resourceType: TOOL_SET bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST parentPath: folder1 name: my-toolset url: toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/my-toolset shareCredentials: true permissions: - READ '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/share/list \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resourceTypes": ["FILE", "PROMPT", "CONVERSATION"], "with": "me", "includeUserInfo": true }' /v1/ops/resource/share/revoke: post: operationId: revokeSharedResources tags: - Sharing summary: /v1/ops/resource/share/revoke description: | Call this endpoint to revoke shared access from all users. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to revoke. items: type: object properties: url: type: string description: | A relative url of the resource to revoke. examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png responses: '200': description: Success '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/share/revoke \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name" }, { "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png" } ] }' /v1/ops/resource/share/discard: post: operationId: discardSharedResources tags: - Sharing summary: /v1/ops/resource/share/discard description: | Call this endpoint to discard the resource shared with you. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to discard. items: type: object properties: url: type: string description: | A relative url of the resource to discard. examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png responses: '200': description: Success '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/share/discard \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name" }, { "url": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png" } ] }' /v1/ops/resource/share/copy: post: operationId: copySharedResources tags: - Sharing summary: /v1/ops/resource/share/copy description: | Call this endpoint to share the *destination* resource with users who have access to the *source* resource. Note, user's permissions will be copied from a source to a destination. requestBody: required: true content: application/json: schema: type: object properties: sourceUrl: type: string description: The relative URL of the original resource where user's permissions will be copied from. destinationUrl: type: string description: The relative URL of the original resource where user's permissions will be copied to. examples: Example: value: sourceUrl: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name destinationUrl: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name responses: '200': description: Success '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/share/copy \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "sourceUrl": "conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/conversation_name", "destinationUrl": "files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file_name", }' /v1/invitations: get: operationId: getInvitations tags: - Sharing summary: /v1/invitations description: | Call this endpoint to get the list of your active invitations. responses: '200': description: Success content: application/json: schema: type: object properties: invitations: type: array items: type: object properties: id: type: string author: type: string resources: type: array items: type: object properties: url: type: string description: A relative url of the resource. author: description: Resource owner display name (a configurable claim from JWT or a project name for API keys). type: string permissions: description: Lists of permissions to be granted. type: array items: type: string enum: - READ - WRITE - SHARE shareCredentials: type: boolean description: Indicates whether global resource credentials was shared with user. default: false createdAt: type: integer expireAt: type: integer examples: Example: value: invitations: - id: 2818T2YRgFaMt8YW176ix7f3adFjxBx5TMQbzmnxgRGNPbDtctJ1wwGkigG78YU6juKnUKRWPNAt1f8Cna5Do7X48FnXwHs5MutEpefm6jTuMQ resources: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name author: user_1 permissions: - READ shareCredentials: false - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png author: user_1 permissions: - READ - WRITE shareCredentials: false - url: toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/my-toolset author: user_1 permissions: - READ shareCredentials: true - url: credentials/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/my-toolset author: user_1 permissions: - READ shareCredentials: false createdAt: 1707874031765 expireAt: 1708133231765 author: the name of the author of the invitation request '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/invitations \ -H "Api-Key: DIAL_API_KEY" /v1/invitations/{invitation_id}: get: operationId: getInvitation tags: - Sharing summary: /v1/invitations/{invitation_id} description: | Call this endpoint to get the invitation details or accept the invitation. parameters: - in: path name: invitation_id schema: type: string required: true - in: query name: accept schema: type: boolean description: Requests with `accept=true` accept an invitation. responses: '200': description: Success content: application/json: schema: type: object properties: id: type: string author: type: string resources: type: array description: An array of shared resources. items: type: object properties: url: type: string description: A relative url of the shared resource. permissions: type: array description: Lists the permissions you have on the resource. items: type: string enum: - READ - WRITE - SHARE shareCredentials: type: boolean description: Indicates whether global resource credentials was shared with user. default: false createdAt: type: integer expireAt: type: integer examples: Example: value: id: 2818T2YRgFaMt8YW176ix7f3adFjxBx5TMQbzmnxgRGNPbDtctJ1wwGkigG78YU6juKnUKRWPNAt1f8Cna5Do7X48FnXwHs5MutEpefm6jTuMQ resources: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name permissions: - READ shareCredentials: false - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/image.png permissions: - READ shareCredentials: false - url: toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/my-toolset permissions: - READ shareCredentials: true - url: credentials/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/toolsets/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/my-toolset permissions: - READ shareCredentials: false createdAt: 1707874031765 expireAt: 1708133231765 author: the name of the author of the invitation request '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/invitations/2818T2Y...pefm6jTuMQ \ -H "Api-Key: DIAL_API_KEY" - lang: 'cURL' label: 'CURL (Accept)' source: | curl -X GET https://chat..com/v1/invitations/2818T2Y...pefm6jTuMQ?accept=true \ -H "Api-Key: DIAL_API_KEY" delete: operationId: deleteInvitation tags: - Sharing summary: /v1/invitations/{invitation_id} description: | Call this endpoint to revoke the invitation. parameters: - in: path name: invitation_id schema: type: string required: true responses: '200': description: Success '401': description: Invalid Authentication x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X DELETE https://chat..com/v1/invitations/2818T2Y...pefm6jTuMQ \ -H "Api-Key: DIAL_API_KEY" /v1/ops/notification/list: post: operationId: getNotifications tags: - Notifications summary: /v1/ops/notification/list description: Call this endpoint to get a list of notifications. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/notifications#notification-api) for more details on how to work with notifications. responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/NotificationsResponse' examples: Example: value: notifications: - id: 5a0bc26f-787a-4dae-8d7b-617e11a2fe31 url: publications/3CcedGxCx23EwiV/0123 type: PUBLICATION message: Your request has been approved by admin timestamp: 1723218135157 '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/notification/delete: post: operationId: deleteNotifications tags: - Notifications summary: /v1/ops/notification/delete description: Call this endpoint to delete one or more than one notification. requestBody: required: true content: application/json: schema: type: object properties: ids: type: array description: Notification identifiers. items: type: string examples: Example: value: ids: - 5a0bc26f-787a-4dae-8d7b-617e11a2fe32 - 5a0bc26f-787a-4dae-8d7b-617e11a2fe31 responses: '200': description: Success '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/resource/subscribe: post: operationId: subscribeToResources tags: - Notifications summary: /v1/ops/resource/subscribe description: | Use this endpoint to subscribe to resource updates. Refer to [Documentation](https://docs.dialx.ai/tutorials/developers/work-with-resources/notifications#subscribe-api) for more details on how to work with subscriptions. requestBody: required: true content: application/json: schema: type: object properties: resources: type: array description: An array of resources to subscribe to. items: type: object properties: url: type: string description: | A relative url of the resource to subscribe to. examples: Example: value: resources: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name - url: conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/conversation - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/image.png responses: '200': description: Success content: text/event-stream: schema: type: array items: type: object properties: url: type: string action: type: string enum: - CREATE - UPDATE - DELETE timestamp: type: integer examples: Event Streaming: value: - url: prompts/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/prompt_name action: CREATE timestamp: 1722463025552 - url: conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/conversation action: UPDATE timestamp: 1722463025552 - url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/image.png action: DELETE timestamp: 1722463025552 '400': description: Bad request '401': description: Unauthorized '500': description: The server had an error while processing your request. x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/resource/subscribe \ -H "Content-Type: application/json" \ -H "Api-Key: DIAL_API_KEY" \ -d '{ "resources": [ { "url": "conversations/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder/conversation" } ] }' /v1/ops/code_interpreter/open_session: post: operationId: openSession tags: - Code interpreter summary: /v1/ops/code_interpreter/open_session description: Call this endpoint to open session for code interpreter application requestBody: required: true content: application/json: schema: type: object properties: sessionId: type: string description: session id. examples: ExampleUser: value: sessionId: "3CcedGxCx23EwiVbV" responses: '200': description: Success content: application/json: schema: type: object properties: sessionId: type: string examples: Session: value: sessionId: 3CcedGxCx23EwiVbV '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/close_session: post: operationId: closeSession tags: - Code interpreter summary: /v1/ops/code_interpreter/close_session description: Call this endpoint to close session for code interpreter application requestBody: required: true content: application/json: schema: type: object properties: sessionId: type: string description: session id. examples: ExampleUser: value: sessionId: "3CcedGxCx23EwiVbV" responses: '200': description: Success content: application/json: schema: type: object properties: sessionId: type: string examples: Session: value: sessionId: 3CcedGxCx23EwiVbV '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/execute_code: post: operationId: executeCode tags: - Code interpreter summary: /v1/ops/code_interpreter/execute_code description: Call this endpoint to execute code by code interpreter application requestBody: required: true content: application/json: schema: type: object properties: sessionId: type: string description: session id. code: description: code to be executed type: string inputFiles: $ref: '#/components/schemas/CodeInterpreterRequestFile' outputFiles: $ref: '#/components/schemas/CodeInterpreterRequestFile' examples: ExecuteCode: value: sessionId: "3CcedGxCx23EwiVbV" code: |- some Python code could be inserted here responses: '200': description: Success content: application/json: schema: type: object properties: status: type: string stdout: type: string stderr: type: string result: type: object display: type: object examples: CodeExecuteResponse: value: status: completed stdout: Application is completed result: success: true '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/upload_file: post: operationId: uploadFileToCodeInterpreter tags: - Code interpreter summary: /v1/ops/code_interpreter/upload_file description: Call this endpoint to upload file to code interpreter container requestBody: required: true content: multipart/form-data: schema: type: object properties: file: type: string format: binary description: | A part of multipart/form-data request responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/CodeInterpreterFile' examples: UploadFile: value: sessionId: 2e2e329dided path: files/21jen1j12e/myfile.txt size: 512 '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/download_file: post: operationId: downloadFileFromCodeInterpreter tags: - Code interpreter summary: /v1/ops/code_interpreter/download_file description: Call this endpoint to download file from code interpreter container requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CodeInterpreterFile' responses: '200': description: Success content: application/octet-stream: schema: type: string format: binary examples: Example: value: "" '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/list_files: post: operationId: listFilesFromCodeInterpreter tags: - Code interpreter summary: /v1/ops/code_interpreter/list_files description: Call this endpoint to list files from code interpreter container requestBody: required: true content: application/json: schema: properties: sessionId: type: string responses: '200': description: Success content: application/json: schema: properties: files: type: array items: $ref: '#/components/schemas/CodeInterpreterFile' examples: UploadFile: value: files: - sessionId: 2e2e329dided path: files/21jen1j12e/myfile.txt size: 512 '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/transfer_input_file: post: operationId: transferInputFile tags: - Code interpreter summary: /v1/ops/code_interpreter/transfer_input_file description: Call this endpoint to transfer file from Core storage to code interpreter container requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CodeInterpreterRequestFile' responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/CodeInterpreterFile' examples: UploadFile: value: sessionId: 2e2e329dided path: files/21jen1j12e/myfile.txt size: 512 '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/transfer_output_file: post: operationId: transferOutputFile tags: - Code interpreter summary: /v1/ops/code_interpreter/transfer_output_file description: Call this endpoint to transfer file from code interpreter container to Core storage requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CodeInterpreterRequestFile' responses: '200': description: Success content: application/json: schema: type: object properties: name: type: string parentPath: type: string bucket: type: string url: type: string etag: type: string nodeType: type: string resourceType: type: string createdAt: type: integer updatedAt: type: integer contentLength: type: integer contentType: type: string permissions: type: array items: type: string enum: - READ - WRITE examples: File: value: name: file.png parentPath: folder1/folder2 bucket: 3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST url: files/3CcedGxCx23EwiVbVmscVktScRyf46KypuBQ65miviST/folder1/folder2/file.png nodeType: ITEM resourceType: FILE etag: 7dfb93c3c62b88e9a75ff36a6af6c7eb updatedAt: 1707876435000 createdAt: 1707876435000 contentLength: 128630 contentType: image/png permissions: - READ - WRITE '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '500': description: The server had an error while processing your request /v1/ops/code_interpreter/get_session: post: operationId: getSession tags: - Code interpreter summary: /v1/ops/code_interpreter/get_session description: Call this endpoint to get a session description. Note, this API does not reset TTL for a session. requestBody: required: true content: application/json: schema: type: object properties: sessionId: type: string description: session id. examples: Example: value: sessionId: "123456" responses: '200': description: Session is alive content: application/json: schema: $ref: '#/components/schemas/GetSession' examples: GetSession: value: sessionId: "123456" '400': description: Bad request '401': description: Invalid Authentication '403': description: Forbidden '404': description: Session is not found '500': description: The server had an error while processing your request /v1/deployments: get: operationId: getDeploymentsByInterfaceType tags: - Deployment listing summary: /v1/deployments description: | Call this endpoint to get basic details about the available deployments of all types (AI models, applications, toolsets) filtered by the interface type. parameters: - name: interface_type in: query schema: type: array items: type: string enum: - chat - embeddings - mcp - custom_ui - all description: Filter deployments by the interface types they support. Can accept multiple values as comma-separated list or array.
`chat` - Deployments that expose chat-based interfaces. This includes the OpenAI-compatible chat completion interface and Responses API. Matches models with `chat` type and applications with `dial:applicationTypeCompletionEndpoint`. Never includes toolsets.
`embedding` - Deployments that expose embedding endpoints. Matches only models with `embedding` type. Never includes applications and toolsets.
`mcp` - Deployments that expose MCP (Model Context Protocol) interface (toolsets and applications with `dial:applicationTypeMcp`). Never includes models.
`custom_ui` - Deployments that expose custom UI interfaces (applications with `dial:applicationTypeViewerUrl`). Never includes models and toolsets.
`all` - Include all deployments regardless of interface type (default behavior if parameter is omitted). required: false responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/Deployments' examples: DeploymentsSample: value: { "deployments": [ { "id": "text-embedding-ada-002", "model": "text-embedding-ada-002", "interfaces":[ "embedding" ], "display_name": "Embedding Ada", "icon_url": "https://chat..com/ada.svg", "description": "Symmetrical embedding model.", "owner": "organization-owner", "object": "model", "status": "succeeded", "created_at": 1672534800, "updated_at": 1672534800, "lifecycle_status": "generally-available", "capabilities": { "scale_types": [ "standard" ], "completion": false, "chat_completion": false, "embeddings": true, "fine_tune": false, "inference": false }, }, { "id": "gpt-world", "application": "gpt-world", "interfaces":[ "chat", "custom_ui" ], "display_name": "GPT World", "icon_url": "https://chat..com/gpt_world.svg", "description": "This application producing answer based on the curated set of LLM related publications.\\n\\nThe source of publications is [arxiv.org](https://arxiv.org/). GPT World is classic example of conversational semantic search application.\\nOn every new user question, it performs summarization using GPT-4, calculates embedding using text-embedding-ada-002 model and then it uses chunks of text from curated set.\\n\\nThis is DIAL version of the [original demo](https://deltix.io/interactive-gpt-world-map.html) with [TSNE map](https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding).", "owner": "organization-owner", "object": "application", "status": "succeeded", "created_at": 1672534800, "updated_at": 1672534800 }, { "id": "toolsets/encrypted-bucket/folder/toolset-name", "toolset": "toolsets/encrypted-bucket/folder/toolset-name", "interfaces":[ "mcp" ], "display_name": "Toolset display name", "display_version": "0.0.1", "description": "My toolset description", "icon_url": "http://toolset/icon.svg", "owner": "Owner's name", "object": "toolset", "status": "succeeded", "description_keywords": [ "keyword1", "keyword2" ], "reference": "ff5584b7-a82b-4f4f-bf42-5bf74a3893d6", "max_retry_attempts": 2, "created_at": 1672534800, "updated_at": 1672534900, "transport": "HTTP", "allowed_tools": [ "tool1", "tool2" ], "auth_settings": { "authentication_type": "OAUTH", "client_id": "my-client-id", "redirect_uri": "https://myapp.com/toolset/sign-in", "authorization_endpoint": "https://authserver.com/authorize", "token_endpoint": "https://authserver.com/token", "code_challenge_method": "S256", "scopes_supported": [ "scope1", "scope2" ], "global_auth_status": "SIGNED_OUT", "user_level_auth_status": "SIGNED_OUT" } } ] } '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/deployments?interface_type={interface_type} \ -H "Api-Key: DIAL_API_KEY" /openai/deployments: get: operationId: getDeployments tags: - Deployment listing summary: /openai/deployments description: | Call this endpoint to get basic details about the available deployments. The response contains model objects (same as `/openai/models`). responses: '200': description: Success content: application/json: schema: type: object properties: data: type: array description: An array of models. items: $ref: '#/components/schemas/ModelOpenAi' examples: DeploymentsSample: value: data: - id: text-embedding-ada-002 model: text-embedding-ada-002 display_name: Embedding Ada icon_url: https://chat..com/ada.svg description: Symmetrical embedding model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: false embeddings: true fine_tune: false inference: false features: rate: false mcp: true tokenize: false truncate_prompt: false configuration: false system_prompt: false tools: false seed: false url_attachments: false folder_attachments: false - id: gpt-4 model: gpt-4 display_name: GPT 4 icon_url: https://chat..com/openai.svg description: Chat completion model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: true embeddings: false fine_tune: false inference: false features: rate: true mcp: true tokenize: true truncate_prompt: true configuration: false system_prompt: true tools: true seed: true url_attachments: true folder_attachments: false defaults: max_tokens: 1024 '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/deployments \ -H "Api-Key: DIAL_API_KEY" /openai/deployments/{deployment_name}: get: operationId: getDeployment tags: - Deployment listing summary: /openai/deployments/{deployment_name} description: | Call this endpoint to get information about a model by its deployment name. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ModelOpenAi' examples: DeploymentsSample: value: id: gpt-4 model: gpt-4 display_name: GPT 4 icon_url: https://chat..com/openai.svg description: Chat completion model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: true embeddings: false fine_tune: false inference: false features: rate: true mcp: true tokenize: true truncate_prompt: true configuration: false system_prompt: true tools: true seed: true url_attachments: true folder_attachments: false defaults: max_tokens: 1024 '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/deployments/gpt-4 \ -H "Api-Key: DIAL_API_KEY" /openai/models: get: operationId: getModels tags: - Deployment listing summary: /openai/models description: | Call this endpoint to get extended details about the available models. responses: '200': description: Success content: application/json: schema: type: object properties: data: type: array description: An array of models. items: $ref: '#/components/schemas/ModelOpenAi' examples: ModelsSample: value: data: - id: text-embedding-ada-002 model: text-embedding-ada-002 display_name: Embedding Ada icon_url: https://chat..com/ada.svg description: Symmetrical embedding model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: false embeddings: true fine_tune: false inference: false - id: gpt-4 model: gpt-4 display_name: GPT 4 icon_url: https://chat..com/openai.svg description: Chat completion model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: true embeddings: false fine_tune: false inference: false '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/models \ -H "Api-Key: DIAL_API_KEY" /openai/models/{model_name}: get: operationId: getModel tags: - Deployment listing summary: /openai/models/{model_name} description: | Call this endpoint to get an extended information about a model by its name. parameters: - name: model_name in: path schema: type: string description: The name of the model. required: true responses: '200': description: Success content: application/json: schema: type: object $ref: '#/components/schemas/ModelOpenAi' examples: ModelsSample: value: id: gpt-4 model: gpt-4 display_name: GPT 4 icon_url: https://chat..com/openai.svg description: Chat completion model. owner: organization-owner object: model status: succeeded created_at: 1672534800 updated_at: 1672534800 lifecycle_status: generally-available capabilities: scale_types: - standard completion: false chat_completion: true embeddings: false fine_tune: false inference: false '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/models/gpt-4 \ -H "Api-Key: DIAL_API_KEY" /openai/applications: get: operationId: getApplications tags: - Deployment listing summary: /openai/applications description: Call this endpoint to get extended details about the available Applications. responses: '200': description: Success content: application/json: schema: type: object properties: data: type: array description: An array of Applications. items: $ref: '#/components/schemas/ApplicationOpenAi' examples: ApplicationsSample: value: data: - id: gpt-world application: gpt-world display_name: GPT World icon_url: https://chat..com/gpt_world.svg description: This application producing answer based on the curated set of LLM related publications.\n\nThe source of publications is [arxiv.org](https://arxiv.org/). GPT World is classic example of conversational semantic search application.\nOn every new user question, it performs summarization using GPT-4, calculates embedding using text-embedding-ada-002 model and then it uses chunks of text from curated set.\n\nThis is DIAL version of the [original demo](https://deltix.io/interactive-gpt-world-map.html) with [TSNE map](https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding). owner: organization-owner object: application status: succeeded created_at: 1672534800 updated_at: 1672534800 '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/applications \ -H "Api-Key: DIAL_API_KEY" /openai/applications/{application_name}: get: operationId: getApplication tags: - Deployment listing summary: /openai/applications/{application_name} description: | Call this endpoint to get extended information about an Application by its name. parameters: - name: application_name in: path schema: type: string description: The name of the Application. required: true responses: '200': description: Success content: application/json: schema: type: object $ref: '#/components/schemas/ApplicationOpenAi' examples: ApplicationsSample: value: id: gpt-world application: gpt-world display_name: GPT World icon_url: https://chat..com/gpt_world.svg description: This application producing answer based on the curated set of LLM related publications.\n\nThe source of publications is [arxiv.org](https://arxiv.org/). GPT World is classic example of conversational semantic search application.\nOn every new user question, it performs summarization using GPT-4, calculates embedding using text-embedding-ada-002 model and then it uses chunks of text from curated set.\n\nThis is DIAL version of the [original demo](https://deltix.io/interactive-gpt-world-map.html) with [TSNE map](https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding). owner: organization-owner object: application status: succeeded created_at: 1672534800 updated_at: 1672534800 '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/applications/gpt-world \ -H "Api-Key: DIAL_API_KEY" /openai/toolsets: get: operationId: getToolSets tags: - Deployment listing summary: /openai/toolsets description: Call this endpoint to get extended details about the available toolsets. responses: '200': description: Success content: application/json: schema: type: object properties: data: type: array description: An array of toolsets. items: $ref: '#/components/schemas/ToolsetOpenAi' examples: ToolsetsSamples: value: data: - id: toolsets/encrypted-bucket/folder/toolset-name toolset: toolsets/encrypted-bucket/folder/toolset-name display_name: Toolset display name display_version: 0.0.1 description: My toolset description icon_url: http://toolset/icon.svg owner: Owner's name object: toolset status: succeeded description_keywords: - keyword1 - keyword2 reference: ff5584b7-a82b-4f4f-bf42-5bf74a3893d6 max_retry_attempts: 2 created_at: 1672534800 updated_at: 1672534900 transport: HTTP allowed_tools: - tool1 - tool2 auth_settings: authentication_type: OAUTH client_id: my-client-id redirect_uri: https://myapp.com/toolset/sign-in authorization_endpoint: https://authserver.com/authorize token_endpoint: https://authserver.com/token code_challenge_method: S256 scopes_supported: [ scope1, scope2 ] global_auth_status: SIGNED_OUT user_level_auth_status: SIGNED_OUT '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/toolsets \ -H "Api-Key: DIAL_API_KEY" /openai/toolsets/{toolset_name}: get: operationId: getToolset tags: - Deployment listing summary: /openai/toolsets/{toolset_name} description: Call this endpoint to get an extended information about a specific toolset by name parameters: - name: toolset_name in: path schema: type: string description: The name of the toolset. required: true responses: '200': description: Success content: application/json: schema: type: object $ref: '#/components/schemas/ToolsetOpenAi' examples: ToolsetSamples: value: id: toolsets/encrypted-bucket/folder/toolset-name toolset: toolsets/encrypted-bucket/folder/toolset-name display_name: Toolset display name display_version: 0.0.1 description: My toolset description icon_url: http://toolset/icon.svg owner: Owner's name object: toolset status: succeeded description_keywords: - keyword1 - keyword2 reference: ff5584b7-a82b-4f4f-bf42-5bf74a3893d6 max_retry_attempts: 2 created_at: 1672534800 updated_at: 1672534900 transport: HTTP allowed_tools: - tool1 - tool2 auth_settings: authentication_type: OAUTH client_id: my-client-id redirect_uri: https://myapp.com/toolset/sign-in authorization_endpoint: https://authserver.com/authorize token_endpoint: https://authserver.com/token code_challenge_method: S256 scopes_supported: [ scope1, scope2 ] global_auth_status: SIGNED_OUT user_level_auth_status: SIGNED_OUT '401': description: Invalid Authentication content: application/json: schema: type: object properties: error: $ref: '#/components/schemas/Error' x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl https://chat..com/openai/toolsets/my-toolset \ -H "Api-Key: DIAL_API_KEY" /v1/deployments/{deployment_name}/limits: get: operationId: getDeploymentLimits tags: - Limits summary: /v1/deployments/{deployment_name}/limits description: | Call this endpoint to get information about spent limits for a given deployment. parameters: - name: deployment_name in: path schema: type: string description: The name of the deployment. required: true responses: '200': description: Success content: application/json: schema: type: object properties: hourRequestStats: type: object description: Statistics for requests per hour. properties: total: description: Total number of requests allowed per hour. type: integer used: description: Number of requests used in the current hour. type: integer dayRequestStats: type: object description: Statistics for requests per day. properties: total: description: Total number of requests allowed per day. type: integer used: description: Number of requests used in the current day. type: integer minuteTokenStats: type: object description: Statistics for tokens per minute. properties: total: description: Total number of tokens allowed per minute. type: integer used: description: Number of tokens used in the current minute. type: integer dayTokenStats: type: object description: Statistics for tokens per day. properties: total: description: Total number of tokens allowed per day. type: integer used: description: Number of tokens used in the current day. type: integer weekTokenStats: type: object description: Statistics for tokens per week. properties: total: description: Total number of tokens allowed per week. type: integer used: description: Number of tokens used in the current week. type: integer monthTokenStats: type: object description: Statistics for tokens per month. properties: total: description: Total number of tokens allowed per month. type: integer used: description: Number of tokens used in the current month. type: integer minuteCostStats: type: object description: Statistics for cost per minute. properties: total: description: Total cost allowed per minute. type: number used: description: Cost used in the current minute. type: number dayCostStats: type: object description: Statistics for cost per day. properties: total: description: Total cost allowed per day. type: number used: description: Cost used in the current day. type: number weekCostStats: type: object description: Statistics for cost per week. properties: total: description: Total cost allowed per week. type: number used: description: Cost used in the current week. type: number monthCostStats: type: object description: Statistics for cost per month. properties: total: description: Total cost allowed per month. type: number used: description: Cost used in the current month. type: number examples: Example: value: "hourRequestStats": "total": 10 "used": 5 "dayRequestStats": "total": 100 "used": 10 "minuteTokenStats": "total": 1000 "used": 100 "dayTokenStats": "total": 10000 "used": 4000 "weekTokenStats": "total": 50000 "used": 20000 "monthTokenStats": "total": 200000 "used": 80000 "minuteCostStats": "total": 0.069 "used": 0.001 "dayCostStats": "total": 100.00 "used": 10.00 "weekCostStats": "total": 500.00 "used": 100.00 "monthCostStats": "total": 20000.00 "used": 1000.00 '401': description: Invalid Authentication '404': description: Limit not found x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/deployments/gpt-4/limits \ -H "Api-Key: DIAL_API_KEY" /v1/ops/config/reload: post: operationId: reloadConfig tags: - Config summary: /v1/ops/config/reload description: | Call this endpoint to reload [DIAL Core configuration](https://github.com/epam/ai-dial-core). Allowed for admin users only! responses: '200': description: Success content: application/json: schema: type: string examples: Example: value: | { "roles": {"default": {"limits": {"chat-gpt-35-turbo": {"minute":"100000", "day":"10000000"}}}} } '403': description: Forbidden x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/config/reload \ -H "Api-Key: DIAL_API_KEY" /v1/consent/{deployment_id}: get: operationId: requestUserConsent tags: - User Consent summary: /v1/consent/{deployment_id} description: | Call this endpoint to get a user's consent for the deployment id. Refer to [DIAL documentation](https://docs.dialx.ai/tutorials/developers/apps-development/auth-matrix#dial-api) to learn more about consent forms and Auth Matrix. parameters: - name: deployment_id in: path schema: type: string description: The unique identifier of the deployment. required: true responses: '200': description: Success content: application/json: schema: $ref: '#/components/schemas/ReviewConsentResponse' '403': description: Forbidden x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X GET https://chat..com/v1/consent/{deployment_id} \ -H "Api-Key: DIAL_API_KEY" post: operationId: acceptUserConsent tags: - User Consent summary: /v1/consent/{deployment_id} description: | Call this endpoint to accept user's consent for the deployment id. parameters: - name: deployment_id in: path schema: type: string description: The unique identifier of the deployment. required: true requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AcceptConsentRequest' responses: '200': description: Success '403': description: Forbidden x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/consent/{deployment_id} \ -H "Api-Key: DIAL_API_KEY" /v1/ops/client-channel/subscribe: post: operationId: subscribeOnClientChannel tags: - Client channel summary: /v1/ops/client-channel/subscribe description: | **Note**: This endpoint is in PREVIEW - it can be removed or modified in nearest future. Call this endpoint to get subscription on events from client channel. parameters: - name: X-DIAL-CLIENT-CHANNEL-ID in: header required: false schema: type: string description: Client channel ID. The client should provide the header in case of reconnect. responses: '200': description: Success headers: X-DIAL-CLIENT-CHANNEL-ID: description: | Client channel ID. **Note**: The header is optional and is passed in the response only if provided in the request. schema: type: string content: text/event-stream: schema: type: string description: | Server-Sent Events stream. Data is sent as a sequence of heartbeat comments / "data:" lines separated by blank lines. examples: rpcRequestStream: summary: Example of SSE stream value: | : heartbeat : heartbeat : heartbeat data: {"jsonrpc": "2.0", "method": "toolset/signin", "params": {"toolsetId": "toolsets/public/toolset2"}, "id": "1"} : heartbeat : heartbeat data: {"jsonrpc": "2.0", "method": "toolset/signin", "params": {"toolsetId": "toolsets/public/my-toolset"}, "id": "2"} '401': description: Unauthorized '400': description: Bad request x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/client-channel/subscribe \ -H "Api-Key: DIAL_API_KEY" /v1/ops/client-channel/unsubscribe: post: operationId: unsubscribeOnClientChannel tags: - Client channel summary: /v1/ops/client-channel/unsubscribe description: | **Note**: This endpoint is in PREVIEW - it can be removed or modified in nearest future. Call this endpoint to remove subscription on events from client channel. parameters: - name: X-DIAL-CLIENT-CHANNEL-ID in: header required: true schema: type: string description: Client channel ID responses: '200': description: Success '401': description: Unauthorized '404': description: Client channel is not found x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/client-channel/unsubscribe \ -H "Api-Key: DIAL_API_KEY" \ -H "X-DIAL-CLIENT-CHANNEL-ID: 12345" /v1/ops/client-channel/report: post: operationId: reportResponseToClientChannel tags: - Client channel summary: /v1/ops/client-channel/report description: | **Note**: This endpoint is in PREVIEW - it can be removed or modified in nearest future. Call this endpoint to report RPC response to client channel. parameters: - name: X-DIAL-CLIENT-CHANNEL-ID in: header required: true schema: type: string description: Client channel ID requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/JsonRpcResponse' responses: '200': description: Success '401': description: Unauthorized '400': description: Bad request x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/client-channel/report \ -H "Api-Key: DIAL_API_KEY" \ -H "X-DIAL-CLIENT-CHANNEL-ID: 12345" -d '{"jsonrpc":"2.0","result":"success","id":"1"}' /v1/ops/client-channel/interact: post: operationId: interactWithClientChannel tags: - Client channel summary: /v1/ops/client-channel/interact description: | **Note**: This endpoint is in PREVIEW - it can be removed or modified in nearest future. Call this endpoint to send RPC request to client channel and wait for RPC response. parameters: - name: X-DIAL-CLIENT-CHANNEL-ID in: header required: true schema: type: string description: Client channel ID requestBody: required: true content: application/json: schema: # Single JSON-RPC request or batch oneOf: - $ref: '#/components/schemas/JsonRpcRequest' - type: array items: $ref: '#/components/schemas/JsonRpcRequest' responses: '200': description: Success content: text/event-stream: schema: type: string description: | Server-Sent Events stream. Data is sent as a sequence of heartbeat comments / "data:" lines separated by blank lines. examples: rpcResponseStream: summary: Example of SSE stream value: | : heartbeat : heartbeat : heartbeat data: [{"jsonrpc":"2.0","result":"success","id":"1"},{"jsonrpc":"2.0","result":"denied","id":"2"}] '401': description: Unauthorized '400': description: Bad request x-codeSamples: - lang: 'cURL' label: 'CURL' source: | curl -X POST https://chat..com/v1/ops/client-channel/interact \ -H "Api-Key: DIAL_API_KEY" \ -H "X-DIAL-CLIENT-CHANNEL-ID: 12345" -d '[{"jsonrpc": "2.0", "method": "toolset/signin", "params": {"toolsetId": "toolsets/public/toolset2"}, "id": "1"},{"jsonrpc": "2.0", "method": "toolset/signin", "params": {"toolsetId": "toolsets/public/my-toolset"}, "id": "2"}]' components: securitySchemes: ApiKeyAuth: type: apiKey in: header name: Api-Key description: |- All API requests must include the API key in the `Api-Key` HTTP header as follows: ```bash Api-Key: DIAL_API_KEY ``` BearerAuth: type: http scheme: bearer bearerFormat: JWT description: |- Some API requests require additional information about the user's JWT token. In this case, it must be included in the `Authorization` HTTP header as follows:
```bash Authorization: Bearer ``` schemas: ReviewConsentResponse: type: object description: Response for reviewing user consent status. properties: consent: $ref: '#/components/schemas/Consent' accepted: type: boolean description: Whether the user has already accepted the consent. AcceptConsentRequest: type: object description: Request body for accepting user consent. properties: consent: $ref: '#/components/schemas/Consent' Consent: type: object description: User consent for deployments. Keys are deployment IDs. properties: deployments: type: object additionalProperties: type: object properties: consentRequired: type: boolean description: Whether the consent is required for the deployment. ChatCompletionTool: type: object properties: type: type: string enum: ["function"] description: The type of the tool. Currently, only `function` is supported. function: $ref: "#/components/schemas/FunctionObject" custom_fields: $ref: "#/components/schemas/ToolCustomFields" required: - type - function ToolCustomFields: type: object properties: cache_breakpoint: $ref: "#/components/schemas/CacheBreakpoint" CacheBreakpoint: type: object description: A manual cache breakpoint. The part of the chat completion request up to this breakpoint will be cached by the deployment. Follow-up requests sharing the same prefix have a chance of hitting the cache and reusing the input tokens associated with this prefix. The field only makes sense for the deployments that support [prompt caching](https://docs.dialx.ai/tutorials/developers/prompt-caching). properties: expire_at: type: string description: "An optional expiration time for the given cache breakpoint, e.g. '2025-10-02T15:01:23Z'" example: '2025-10-02T15:01:23Z' FunctionObject: type: object properties: description: type: string description: A description of what the `function` does, used by the model to choose when and how to call the `function`. name: type: string description: The name of the `function` to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: "#/components/schemas/FunctionParameters" strict: type: boolean nullable: true default: false description: Whether to enable strict schema adherence when generating the `function` call. If set to `true`, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](docs/guides/function-calling). required: - name FunctionParameters: type: object description: "The parameters the `function` accepts, described as a JSON Schema object. See the [guide](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. \n\nOmitting `parameters` defines a `function` with an empty parameter list." ChatCompletionToolChoiceOption: description: | Controls which (if any) tool is called by the model. `none` means the model will not call any `tool` and instead generates a `message`. `auto` means the model can pick between generating a `message` or calling one or more `tools`. `required` means the model must call one or more `tools`. Specifying a particular `tool` via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that `tool`. `none` is the default when no `tools` are present. `auto` is the default if `tools` are present. oneOf: - type: string description: > `none` means the model will not call any `tool` and instead generates a `message`. `auto` means the model can pick between generating a `message` or calling one or more `tools`. `required` means the model must call one or more `tools`. enum: - none - auto - required - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" ChatCompletionNamedToolChoice: type: object description: Specifies a `tool` the model should use. Use to force the model to call a specific `function`. properties: type: type: string enum: - "function" description: The type of the `tool`. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the `function` to call. required: - name required: - type - function ParallelToolCalls: description: Whether to enable parallel `function` calling during the `tool` use. type: boolean default: true ChatCompletionMessageToolCalls: type: array description: The `tool` calls generated by the model, such as `function` calls. items: $ref: "#/components/schemas/ChatCompletionMessageToolCall" ChatCompletionFunctionCall: type: object description: Deprecated and replaced by `tool_calls`. The name and arguments of a `function` that should be called, as generated by the model. properties: name: type: string description: The name of the `function` to call. arguments: type: string description: The arguments to call the `function` with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your `function` schema. Validate the arguments in your code before calling your `function`. required: - name - arguments ChatCompletionMessageToolCall: type: object properties: id: type: string description: The ID of the `tool` call. type: $ref: "#/components/schemas/ToolCallType" function: type: object description: The `function` that the model called. properties: name: type: string description: The name of the `function` to call. arguments: type: string description: The arguments to call the `function` with, as generated by the model in JSON format. Note that the model does not always generate a valid JSON, and may hallucinate parameters not defined by your `function` schema. Validate the arguments in your code before calling your `function`. required: - name - arguments required: - id - type - function ToolCallType: type: string enum: - function description: The type of the `tool` call, in this case `function`. DeploymentFeatures: type: object description: The features supported by a deployment. properties: rate: type: boolean description: | Does the deployment support endpoint for rating a request: `POST /v1/{deployment_name}/rate`? mcp: type: boolean description: | Does the deployment support endpoint for MCP (Multi-Channel Processing) requests: `GET /v1/deployments/{deployment_name}/mcp`? tokenize: type: boolean description: | Does the deployment support endpoint for tokenization: `POST /v1/{deployment_name}/tokenize`? truncate_prompt: type: boolean description: | Does the deployment support endpoint for prompt truncation: `POST /v1/{deployment_name}/truncate_prompt`? configuration: type: boolean description: | Does the deployment support endpoint that provides JSON schema for deployment configuration: `GET /v1/deployments/{deployment_name}/configuration`? system_prompt: type: boolean description: | Does the deployment support system prompt in a chat completion request? tools: type: boolean description: | Does the deployment support `tools` and `functions` in chat completion request? seed: type: boolean description: | Does the deployment support seed parameter in chat completion request? url_attachments: type: boolean description: | Does the deployment support URL attachments in messages of a chat completion request?

An example of message with URL attachment: ```json { "messages": [ { "content": "Message content", "attachments": [ { "title": "Title of the URL attachment", "url": "https://en.wikipedia.org/wiki/URL" } ] } ] } ``` folder_attachments: type: boolean description: | Does the deployment support folder attachments in messages of a chat completion request? A folder attachment must point to a metadata of a directory in DIAL file storage.

An example of a message with folder attachment: ```json { "messages": [ { "content": "Message content", "attachments": [ { "title": "Title of the folder attachment", "type": "application/vnd.dial.metadata+json", "url": "metadata/BUCKET/PATH/TO/FOLDER/" } ] } ] } ``` allow_resume: type: boolean description: Whether the deployment supports resuming conversations. Defaults to `true`. default: true accessible_by_per_request_key: type: boolean description: Whether the deployment is accessible by per-request API key. Defaults to `true`. default: true content_parts: type: boolean description: Whether the deployment supports content parts in messages. Defaults to `false`. default: false temperature: type: boolean description: Whether the deployment supports the temperature parameter. Defaults to `true`. default: true cache: type: boolean description: Whether the deployment supports LLM prompt caching (manual or automatic). Defaults to `false`. default: false auto_caching: type: boolean description: Whether the deployment supports automatic prompt caching. Defaults to `false`. default: false parallel_tool_calls: type: boolean description: Whether the deployment supports parallel tool calls. Defaults to `true`. default: true assistant_attachments_in_request: type: boolean description: Whether the deployment supports assistant attachments in the request. Defaults to `false`. default: false required: - rate - mcp - tokenize - truncate_prompt - configuration - system_prompt - tools - seed - url_attachments - folder_attachments DeploymentInputAttachmentTypes: type: array description: | A list of [content types](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/MIME_types/Common_types) that the deployment supports for input attachments.

The deployment does not support input attachments if the list is empty or the listing parameter is missing. items: type: string DeploymentMaxInputAttachments: type: integer description: | The maximum number of input attachments that the deployment supports.

When the listing parameter is missing and application does not support input attachments, the value is defaulted to `0`.

When the listing parameter is missing and application supports input attachments, there is no restriction on the number of attachments. DeploymentDefaultParameters: type: object description: | A dictionary providing default values for chat completion request parameters in case the parameters are missing in the request.

This is useful when a deployment requires specific parameters to be set, when those parameters are optional in the request schema.

For example the following default parameter sets the `max_tokens` parameter to `1024` when it's missing in the chat completion request: ```json { "max_tokens": 1024 } ``` example: max_tokens: 1024 DeploymentBase: type: object properties: id: type: string description: The unique identifier of the deployment. display_name: type: string description: The display name of the deployment. Returned only with the response from `/v1/deployments` endpoint. display_version: type: string description: The display version of the deployment. icon_url: type: string description: The icon of the deployment. description: type: string description: The description of the deployment in the Markdown format. reference: type: string description: The reference identifier of the deployment. owner: type: string description: The name of the owner for the deployment. status: type: string description: The status of the deployment. Always is `succeeded`. created_at: type: integer description: The value, in seconds since the epoch, that represents the time at which the object was created. updated_at: type: integer description: The value, in seconds since the epoch, that represents the time at which the object was modified. description_keywords: type: array items: type: string description: A list of keywords describing the deployment. max_retry_attempts: type: integer description: The maximum number of retry attempts to route a single user's request to the deployment's endpoint. interfaces: type: array items: type: string description: Interface types supported by the deployment. Returned only with the response from `/v1/deployments` endpoint. DeploymentWithFeatures: type: object properties: features: $ref: '#/components/schemas/DeploymentFeatures' input_attachment_types: $ref: '#/components/schemas/DeploymentInputAttachmentTypes' max_input_attachments: $ref: '#/components/schemas/DeploymentMaxInputAttachments' defaults: $ref: '#/components/schemas/DeploymentDefaultParameters' Deployment: allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: model: type: string description: The deployment name. object: type: string description: The object type. Always is `deployment`. scale_settings: type: object description: The scale settings of the deployment. properties: scale_type: type: string description: The scale type. Only the `standard` type is currently supported. - $ref: '#/components/schemas/DeploymentWithFeatures' ModelOpenAi: allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: model: type: string description: The model name. Same as the `id` field. object: type: string description: The object type. Always is `model`. lifecycle_status: type: string description: Lifecycle status. Always is `generally-available`. capabilities: $ref: '#/components/schemas/ModelCapabilities' tokenizer_model: type: string description: | This parameter specifies the exact model whose tokenization algorithm matches the one used by the given model. Typically, this is the name of the first model released in a series that shares the same tokenization algorithm _(e.g., `gpt-3.5-turbo-0301`, `gpt-4-0314`, `gpt-4-1106-vision-preview`)_.

This parameter is useful for DIAL clients that implement tokenization algorithms on their side, rather than using the `/tokenize` endpoint provided by the model. limits: $ref: '#/components/schemas/ModelLimits' pricing: $ref: '#/components/schemas/ModelPricing' - $ref: '#/components/schemas/DeploymentWithFeatures' ApplicationOpenAi: allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: application: type: string description: The application name. viewer_url: type: string description: The URL of the custom app UI. editor_url: type: string description: The URL of the custom app builder UI. object: type: string description: The object type. Always is `application`. application_properties: type: object description: Custom application properties. application_type_schema_id: type: string format: uri description: The URI of the application type schema. function: $ref: '#/components/schemas/ApplicationFunction' routes: type: object description: Custom routes for the application. additionalProperties: type: object invalid: type: boolean description: Indicates whether the application is invalid (e.g., missing required properties or schema violations). Only applicable for schema-rich applications. Null when the application is valid. readOnly: true - $ref: '#/components/schemas/DeploymentWithFeatures' Assistant: deprecated: true description: "Deprecated: Assistant type has been removed from the codebase." allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: assistant: type: string description: The assistant name. object: type: string description: The object type. Always is `assistant`. addons: type: array description: The array of addons enabled by default in the assistant. items: type: string - $ref: '#/components/schemas/DeploymentWithFeatures' Addon: deprecated: true description: "Deprecated: Addon type has been removed from the codebase." allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: addon: type: string description: The addon name. object: type: string description: The object type. Always is `addon`. ApplicationFunction: type: object description: Function deployment configuration for the application. properties: id: type: string description: The function identifier. runtime: type: string description: The runtime environment for the function. author_bucket: type: string description: The author's bucket. source_folder: type: string description: The source folder for the function code. target_folder: type: string description: The target folder for the deployed function. status: type: string enum: [DEPLOYING, UNDEPLOYING, DEPLOYED, UNDEPLOYED, FAILED] description: The current deployment status of the function. error: type: string description: Error message if the function deployment failed. mapping: type: object description: The mapping configuration for the function. env: type: object description: Environment variables for the function. additionalProperties: type: string ResourceAuthSettings: type: object description: Authentication settings for a resource. properties: authentication_type: type: string enum: [OAUTH, API_KEY, NONE] description: Type of authentication. client_id: type: string description: (OAUTH only) Client ID for OAuth flows. client_secret: type: string description: (OAUTH only) Client secret for OAuth flows. writeOnly: true redirect_uri: type: string description: (OAUTH only) Redirect URI for OAuth flows. authorization_endpoint: type: string description: (OAUTH only) Authorization endpoint for OAuth. token_endpoint: type: string description: (OAUTH only) Token endpoint for OAuth. code_challenge: type: string description: (OAUTH only) Code challenge for PKCE. readOnly: true code_challenge_method: type: string description: (OAUTH only) Code challenge method for PKCE. scopes_supported: type: array items: type: string description: (OAUTH only) Supported OAuth scopes. global_auth_status: type: string enum: [SIGNED_IN, SIGNED_OUT] description: Global credentials status. readOnly: true app_level_auth_status: type: string enum: [SIGNED_IN, SIGNED_OUT] description: Application-level credentials status. readOnly: true user_level_auth_status: type: string enum: [SIGNED_IN, SIGNED_OUT] description: User-level credentials status. readOnly: true api_key_header: type: string description: (API_KEY only) Header name for API key. required: - authentication_type ToolsetOpenAi: allOf: - type: object properties: id: type: string description: DIAL toolset id ('name' by default). toolset: type: string description: DIAL toolset name. interfaces: type: string description: Interfaces supported by the toolset. Default value `mcp`. Returned only with the response from `/v1/deployments` endpoint. icon_url: type: string description: The path for the location of the icon applied to the toolset on UI. description: type: string description: A brief description of the toolset. display_name: type: string description: A display name of the toolset on the UI. display_version: type: string description: A display version of the toolset on the UI. reference: type: string description: A reference id of the toolset ('name' or server-generated identifier). description_keywords: type: array description: A list of keywords describing the toolset, e.g. code-gen, text2image. max_retry_attempts: type: integer description: The maximum number of retry attempts to route a single user's request to the toolset's endpoint. object: type: string description: The object type. Always is `toolset`. status: type: string description: The status of the toolset. Always is `succeeded`. owner: type: string description: A toolset's owner. created_at: type: integer description: The date of the toolset creation. updated_at: type: integer description: The date of the toolset last update. transport: type: string description: The transport supported by a specific MCP server. Available options are `HTTP` or `SSE`. allowed_tools: type: array description: A list of available tools in the MCP server. auth_settings: $ref: '#/components/schemas/ResourceAuthSettings' - $ref: '#/components/schemas/DeploymentWithFeatures' ToolSet: allOf: - $ref: '#/components/schemas/DeploymentBase' - type: object properties: toolset: type: string description: The toolset name. transport: type: string description: The transport supported by the MCP server. Available options are `HTTP` or `SSE`. allowed_tools: type: array description: A list of available tools in the MCP server. items: type: string object: type: string description: The object type. Always is `toolset`. - $ref: '#/components/schemas/DeploymentWithFeatures' Toolset: allOf: - type: object properties: name: type: string description: DIAL Toolset's name. endpoint: type: string description: DIAL Toolset API for MCP calls. icon_url: type: string description: The path for the location of the icon that applies for the DIAL toolset on UI. description: type: string description: A brief description of the toolset. display_name: type: string description: A display name of the toolset on the UI. display_version: type: string description: A display version of the toolset on the UI. description_keywords: type: array description: A list of keywords describing the toolset, e.g. code-gen, text2image. reference: type: string description: A reference id of the toolset ('name' or server-generated identifier). forward_per_request_key: type: boolean description: Indicates if a per-request API key should be forwarded to an upstream call. max_retry_attempts: type: integer description: The maximum number of retry attempts to route a single user's request to the toolset's endpoint. author: type: string description: The toolset's developer. created_at: type: integer description: The date of the toolset creation. readOnly: true updated_at: type: integer description: The date of the toolset last update. readOnly: true forward_auth_token: type: boolean description: Indicates if the authorization token should be forwarded to an upstream request. readOnly: true transport: type: string description: The transport supported by a specific MCP server. The available options are `HTTP` or `SSE`. allowed_tools: type: array description: A list of allowed tools supported by the MCP server. auth_settings: $ref: '#/components/schemas/ResourceAuthSettings' - $ref: '#/components/schemas/DeploymentWithFeatures' ModelCapabilities: type: object description: The capabilities of the model. properties: scale_types: type: array description: The scale types of the model. Defaults to `["standard"]`. items: type: string completion: type: boolean description: True if the model is a completion. chat_completion: type: boolean description: True if the model is a chat completion. embeddings: type: boolean description: True if the model is an embedding. fine_tune: type: boolean description: True if it is a fine-tuned model. inference: type: boolean description: True if the model can be deployed. ModelLimits: description: | Defines the token limits for the model.

Either `max_total_tokens` is specified by itself, or `max_prompt_tokens` and `max_completion_tokens` are specified together. type: object oneOf: - type: object properties: max_total_tokens: type: integer description: The maximum number of tokens allowed in a completion request and response combined. required: - max_total_tokens - type: object properties: max_prompt_tokens: type: integer description: The maximum number of tokens allowed in a completion request. max_completion_tokens: type: integer description: The maximum number of tokens allowed in a completion response. required: - max_prompt_tokens - max_completion_tokens ModelPricing: description: Defines the pricing for the model in an unspecified currency. type: object properties: unit: type: string enum: - token - char_without_whitespace description: The pricing units. prompt: type: string description: The per-unit price for the completion request. completion: type: string description: | The per-unit price for the completion response.

This field is typically missing for embedding models. required: - unit - prompt EmbeddingRequest: type: object properties: input: description: |- The input text to generate embeddings for. It can be either: - a string, - an array of strings, - an array of token ids (representing a single tokenized string) and - an array of arrays of token ids (representing an array of tokenized strings). **Note:** representation of strings as an array of token ids may not be supported by certain models. anyOf: - type: string description: The string that will be turned into an embedding. - type: array items: type: string description: The array of strings that will be turned into embeddings. - type: array items: type: integer description: The array of token ids that will be turned into an embedding. - type: array items: type: array items: type: integer description: The array of arrays of token ids that will be turned into embeddings. custom_input: $ref: '#/components/schemas/EmbeddingsCustomInput' user: type: string description: A unique identifier representing the end-user. encoding_format: description: The format in which the embeddings are returned. type: string enum: - float - base64 default: float example: base64 dimensions: description: |- The number of dimensions the resulting output embeddings should have. **Note:** instruction may not be supported by some models. type: integer example: 512 custom_fields: $ref: '#/components/schemas/EmbeddingsCustomFields' required: - input EmbeddingResponse: type: object properties: object: type: string description: Object type. Always is `list`. model: type: string description: The name of the model that generated the response. data: type: array description: A list of generated vectors. items: type: object description: The representation of an embedding vector corresponding to `index`-th input. properties: index: type: integer description: The index of the embedding from `0` to `number of regular and custom inputs in the request - 1`. object: type: string description: Object type. Always is `embedding`. embedding: description: Embedding output corresponding to the `index`-th embedding input. It's either an array of floats or base64-encoded vector depending on the value of `encoding_format` request parameter. oneOf: - type: array items: type: number - type: string required: - index - object - embedding usage: type: object description: This field contains information about the tokens from the model that were used to generate the response. properties: prompt_tokens: type: integer description: The number of tokens in the request to the model. total_tokens: type: integer description: The number of tokens in the request to the model. required: - prompt_tokens - total_tokens required: - object - model - data - usage ChatCompletionFunction: type: object deprecated: true properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: "#/components/schemas/FunctionParameters" required: - name ChatCompletionFunctionCallOption: type: object description: > Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. properties: name: type: string description: The name of the function to call. required: - name ChatCompletionAddon: oneOf: - type: object properties: name: type: string description: The name of an addon defined in the DIAL Core config. - type: object properties: url: type: string description: | The URL pointing to an OpenAI Plugin Schema.

See for example the [to-do plugin](https://github.com/openai/plugins-quickstart/blob/main/.well-known/ai-plugin.json). ChatCompletionRequestMessage: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestDeveloperMessage" - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" ChatCompletionRequestDeveloperMessage: type: object title: Developer message description: > Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, `developer` messages replace the previous `system` messages. properties: content: description: The contents of the developer message. oneOf: - type: string description: The contents of the developer message. title: Text content - type: array description: An array of content parts with a defined type. For developer messages, only type `text` is supported. title: Array of content parts items: $ref: "#/components/schemas/ChatCompletionRequestDeveloperMessageContentPart" minItems: 1 custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" role: type: string enum: - developer description: The role of the messages author, in this case `developer`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionRequestSystemMessage: type: object title: System message properties: content: description: The contents of the system message. oneOf: - type: string description: The contents of the system message. title: Text content - type: array description: An array of content parts with a defined type. For system messages, only type `text` is supported. title: Array of content parts items: $ref: "#/components/schemas/ChatCompletionRequestSystemMessageContentPart" minItems: 1 custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" role: type: string enum: ["system"] description: The role of the messages author, in this case `system`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionRequestUserMessage: type: object title: User message properties: content: description: | The contents of the user message. oneOf: - type: string description: The text contents of the message. title: Text content - type: array description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4o` model. title: Array of content parts items: $ref: "#/components/schemas/ChatCompletionRequestUserMessageContentPart" minItems: 1 custom_content: $ref: "#/components/schemas/ChatCompletionRequestUserMessageCustomContent" custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" role: type: string enum: ["user"] description: The role of the messages author, in this case `user`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionRequestAssistantMessage: type: object title: Assistant message properties: content: nullable: true type: string oneOf: - type: string description: The contents of the assistant message. title: Text content - type: array description: An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. title: Array of content parts items: $ref: "#/components/schemas/ChatCompletionRequestAssistantMessageContentPart" minItems: 1 description: | The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. custom_content: $ref: "#/components/schemas/ChatCompletionRequestAssistantMessageCustomContent" custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" refusal: nullable: true type: string description: The refusal message by the assistant. role: type: string enum: ["assistant"] description: The role of the messages author, in this case `assistant`. name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. tool_calls: $ref: "#/components/schemas/ChatCompletionMessageToolCalls" function_call: type: object deprecated: true description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." nullable: true properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. required: - arguments - name required: - role ChatCompletionRequestToolMessage: type: object title: Tool message properties: role: type: string enum: ["tool"] description: The role of the messages author, in this case `tool`. content: oneOf: - type: string description: The contents of the tool message. title: Text content - type: array description: An array of content parts with a defined type. For tool messages, only type `text` is supported. title: Array of content parts items: $ref: "#/components/schemas/ChatCompletionRequestToolMessageContentPart" minItems: 1 description: The contents of the tool message. custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" tool_call_id: type: string description: Tool call that this message is responding to. required: - role - content - tool_call_id ChatCompletionRequestFunctionMessage: type: object title: Function message deprecated: true properties: role: type: string enum: ["function"] description: The role of the messages author, in this case `function`. content: nullable: true type: string description: The contents of the function message. custom_fields: $ref: "#/components/schemas/ChatCompletionRequestCustomFields" name: type: string description: The name of the function to call. required: - role - content - name ChatCompletionRequestDeveloperMessageContentPart: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" ChatCompletionRequestSystemMessageContentPart: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" ChatCompletionRequestUserMessageContentPart: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" ChatCompletionRequestAssistantMessageContentPart: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartRefusal" ChatCompletionRequestToolMessageContentPart: oneOf: - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" ChatCompletionRequestMessageContentPartText: type: object title: Text content part properties: type: type: string enum: ["text"] description: The type of the content part. text: type: string description: The text content. required: - type - text ChatCompletionRequestMessageContentPartImage: type: object title: Image content part properties: type: type: string enum: ["image_url"] description: The type of the content part. image_url: type: object properties: url: type: string description: Either a URL of the image or the base64 encoded image data. format: uri detail: type: string description: Specifies the detail level of the image. Learn more in the [Vision guide](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision?tabs=rest%2Csystem-assigned%2Cresource#detail-parameter-settings-in-image-processing-low-high-auto). enum: ["auto", "low", "high"] default: "auto" required: - url required: - type - image_url ChatCompletionRequestMessageContentPartRefusal: type: object title: Refusal content part properties: type: type: string enum: ["refusal"] description: The type of the content part. refusal: type: string description: The refusal message generated by the model. required: - type - refusal ChatCompletionResponseMessage: type: object description: The Assistant message. properties: role: type: string enum: - assistant description: The role of the author of the response message. refusal: type: string description: The refusal message generated by the model. nullable: true content: type: string description: The contents of the message. `content` is set for all messages except messages with tool calls, function calls and refusals. nullable: true custom_content: $ref: "#/components/schemas/ChatCompletionResponseCustomContent" tool_calls: type: array description: The tool calls generated by the model, such as function calls. items: $ref: "#/components/schemas/ChatCompletionMessageToolCall" function_call: $ref: "#/components/schemas/ChatCompletionFunctionCall" required: - role - content - refusal ChatCompletionStreamResponseDelta: type: object description: A chat completion delta generated by streamed model responses. properties: role: type: string enum: ["assistant"] description: The role of the author of this message. refusal: type: string description: The refusal message generated by the model. nullable: true content: type: string description: The contents of the chunk message. nullable: true custom_content: $ref: "#/components/schemas/ChatCompletionResponseCustomContent" function_call: deprecated: true type: object description: "Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model." properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. tool_calls: type: array items: $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" ChatCompletionMessageToolCallChunk: type: object properties: index: type: integer id: type: string description: The ID of the tool call. type: type: string enum: ["function"] description: The type of the tool. Currently, only `function` is supported. function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - index ChatCompletionRequestAssistantMessageCustomContent: type: object description: The custom content of the assistant message. properties: state: type: object description: |- The internal state of the Assistant. This field can have an arbitrary set of fields with an arbitrary structure. attachments: type: array items: $ref: "#/components/schemas/RequestAttachment" description: List of attachments used to supply an additional output from the model. form_schema: type: object description: |- The JSON schema describing a form that the assistant prompts the user to fill in. Given this schema, the user is expected to provide a JSON value in the next message in the `custom_content.form_value` field. ChatCompletionRequestUserMessageCustomContent: type: object description: The custom content of the user message. properties: attachments: type: array items: $ref: "#/components/schemas/RequestAttachment" description: List of attachments used to supply an additional input for the model. form_value: type: object description: |- The JSON value corresponding to the JSON schema sent by the assistant in the previous message in the `custom_content.form_schema` field. ChatCompletionRequestCustomFields: type: object description: DIAL-specific extensions of the Chat Completions message. properties: cache_breakpoint: $ref: "#/components/schemas/CacheBreakpoint" EmbeddingsCustomInput: type: array description: |- The custom embedding inputs that represent multi-modal inputs (e.g. images and video) along with compound inputs (e.g. a title for an image and the image itself). items: $ref: '#/components/schemas/EmbeddingsCustomInputElement' EmbeddingsCustomInputElement: description: A particular embedding input which embeddings model translates to an embedding vector. oneOf: - type: string description: Input text to get embeddings for, encoded as a string. - $ref: "#/components/schemas/RequestAttachment" - $ref: "#/components/schemas/EmbeddingsCustomInputCompoundElement" EmbeddingsCustomInputCompoundElement: description: An embedding input composed of multiple strings and attachments. type: array items: oneOf: - type: string - $ref: "#/components/schemas/RequestAttachment" EmbeddingsCustomFields: type: object description: |- Additional parameters for an embedding model. properties: type: type: string description: |- Type of embedding to embed an input with. The particular values of this parameter are specific for particular models. **Note:** embedding types may not be supported by some models. instruction: type: string description: |- Allows to specify an instruction prompt for an instructor-like embedding model. **Note:** instruction may not be supported by some models. ResponseFormatText: type: object properties: type: type: string description: "The type of response format being defined: `text`" enum: ["text"] required: - type ResponseFormatJsonObject: type: object properties: type: type: string description: "The type of response format being defined: `json_object`" enum: ["json_object"] required: - type ResponseFormatJsonSchemaSchema: type: object description: "The schema for the response format, described as a JSON Schema object." ResponseFormatJsonSchema: type: object properties: type: type: string description: "The type of response format being defined: `json_schema`" enum: ["json_schema"] json_schema: type: object properties: description: type: string description: A description of what the response format is for, used by the model to determine how to respond in the format. name: type: string description: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. schema: $ref: "#/components/schemas/ResponseFormatJsonSchemaSchema" strict: type: boolean nullable: true default: false description: Whether to enable strict schema adherence when generating the output. If set to `true`, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. required: - schema - name required: - type - json_schema ChatCompletionsCustomFields: type: object description: |- Additional DIAL-specific parameters for a chat completion request. properties: configuration: type: object description: |- The object that represents configuration of the deployment. The schema of the object is specific for each deployment and provided by the endpoint `GET /v1/deployments/{deployment_name}/configuration`.

A deployment supports configuration if its listing, retrieved by `GET /openai/deployments/{deployment_name}`, has a field `features.configuration` set to **true**.

Certain models connected via DIAL adapters are configurable. For detailed configuration information, refer to the documentation of each adapter: - [OpenAI Adapter](https://github.com/epam/ai-dial-adapter-openai/?tab=readme-ov-file#configurable-models) - [Google VertexAI Adapter](https://github.com/epam/ai-dial-adapter-vertexai/?tab=readme-ov-file#configurable-models) - [AWS Bedrock Adapter](https://github.com/epam/ai-dial-adapter-bedrock/?tab=readme-ov-file#configurable-models) example: $ref: ./examples/configuration_value.json ChatCompletionResponseCustomContent: type: object description: The custom content of a message. properties: attachments: type: array items: $ref: "#/components/schemas/ChatCompletionResponseAttachment" description: List of attachments. stages: type: array readOnly: true items: $ref: "#/components/schemas/ChatCompletionResponseStage" description: The intermediate stages that the Assistant went through to generate the response. state: type: object description: The internal state of the Assistant. This field can have an arbitrary set of fields with an arbitrary structure. In case of a streaming, the state is published fully in one chunk. RequestAttachment: type: object properties: type: type: string default: text/markdown description: The content type of the attachment. Should be one of the MIME types. title: type: string description: The title of the attachment. data: type: string description: |- Should follow the format described in the MIME standard for `type`. It is mandatory for the attachment to have exactly one of the following fields (never both): `data` or `url`. url: type: string description: |- The content of `url` should follow the format described in the MIME standard for `type`. It is mandatory for the attachment to have exactly one of the following fields (never both): `data` or `url`. reference_type: type: string description: The content type of `reference_url`. Should be one of the MIME types. reference_url: type: string description: If `reference_type` is specified, the content of `reference_url` should follow the format described in the MIME standard for `reference_type`. ChatCompletionResponseAttachment: type: object properties: index: type: integer description: |- In *streaming* chat completion responses, each attachment includes an `index` field indicating its position in the final ordered list. This field is required because attachments may arrive out of order, and the client must reconstruct the correct sequence using `index`.

In *non-streaming* responses, the `index` field is omitted because an attachment's position is already determined by its place in the returned list. type: type: string default: text/markdown description: The content type of the attachment. Should be one of the MIME types. title: type: string description: The title of the attachment. data: type: string description: |- Should follow the format described in the MIME standard for `type`. It is mandatory for the attachment to have one of the following fields (never both): `data` or `url`. url: type: string description: |- The content of `url` should follow the format described in the MIME standard for `type`. It is mandatory for the attachment to have one of the following fields (never both): `data` or `url`. reference_type: type: string description: The content type of `reference_url`. Should be one of the MIME types. reference_url: type: string description: If `reference_type` is specified, the content of `reference_url` should follow the format described in the MIME standard for `reference_type`. required: - index ChatCompletionResponseStage: type: object properties: index: type: integer description: |- In *streaming* chat completion responses, each stage includes an `index` field indicating its position in the final ordered list. This field is required because stages may arrive out of order, and the client must reconstruct the correct sequence using `index`.

In *non-streaming* responses, the `index` field is omitted because a stage's position is already determined by its place in the returned list. name: type: string description: The name of the stage. content: type: string description: The contents of the stage. attachments: type: array items: $ref: "#/components/schemas/ChatCompletionResponseAttachment" description: List of attachments to the stage. status: type: string nullable: true description: |- The execution status of the stage. Available status values: * `null`: The stage is in progress. * `completed`: The stage is completed. * `failed`: The stage is failed. required: - index - name - status CreateChatCompletionResponse: type: object properties: id: type: string description: The ID of the response. object: type: string description: Object type. Always is `chat.completion` for non-streaming. created: type: integer description: The response timestamp. The time in seconds since the epoch. model: type: string description: The name of the model that generated the response. May not be the same as the deployment name. choices: type: array description: List of generated messages. Contains _n_ items. items: type: object properties: index: type: integer description: The index of the choice from `0` to `n - 1`. message: type: object $ref: "#/components/schemas/ChatCompletionResponseMessage" finish_reason: type: string nullable: true description: |- The reason indicating the completion of the choice generation process. The possible reasons: * `stop`: Successful generation. * `length`: The generation was stopped because it surpassed the available number of tokens. * `function_call`: The Assistant decided to call a function. * `tool_calls`: The Assistant decided to call a tool. * `content_filter`: Omitted content due to a flag from content filters. required: - index - message - finish_reason usage: type: object description: This field contains information about the tokens from the model that were used to generate the response. properties: prompt_tokens: type: integer description: The number of tokens in the request to the model. completion_tokens: type: integer description: The number of tokens in the response from the model. total_tokens: type: integer description: The sum of prompt and completion tokens. statistics: type: object $ref: "#/components/schemas/ChatCompletionResponseStatistics" system_fingerprint: type: string description: Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. PublicationRequest: type: object properties: name: type: string description: A publication request name. displayAuthor: type: string description: The name that will be displayed on UI instead of the name of the author of the publication request. targetFolder: type: string description: The name of the target folder for the publication. resources: type: array description: List of resources to be published. **Required** either `rules` or `resources` or both. items: type: object properties: action: type: string description: The type of action to performed. Use `ADD` to create a publish request. Use `DELETE` to create an unpublish request. enum: - ADD - DELETE - ADD_IF_ABSENT sourceUrl: type: string description: The path to the source of the publication. targetUrl: type: string description: The path to the destination of the publication. publishCredentials: type: boolean description: A flag enabling resource publication with credentials. Set `true` for publishing with credentials. rules: type: array description: List of rules to restrict access to the published resource. Applies to `targetFolder`. The request is invalid if `rules` is specified together with `public` as value for `targetFolder`. **Required** either `rules` or `resources` or both. Skip `resources` and include `rules` to update only rules. You can pass an empty `rules` object to delete all rules. items: type: object properties: source: type: string description: Claim for authorization using JWT. For authorization with API keys the source is `roles`. function: type: string description: The function. enum: - EQUAL - CONTAIN - REGEX targets: type: array description: Claim value(s) for authorization using JWT. For authorization with API keys - the roles assigned to API key. items: type: string required: - name - targetFolder UpdatePublicationRequest: type: object properties: name: type: string description: A publication request name. displayAuthor: type: string description: The name that will be displayed on UI instead of the name of the author of the publication request. url: type: string description: The publication request URL. targetFolder: type: string description: The name of the target folder for the publication. resources: type: array description: A list of resources to be published. **Required** either `rules` or `resources` or both. items: type: object properties: action: type: string description: A type of action to performed. Use `ADD` to create a publish request. Use `DELETE` to create an unpublish request. enum: - ADD - DELETE - ADD_IF_ABSENT sourceUrl: type: string description: The path to the source of the publication. targetUrl: type: string description: The path to the destination of the publication. publishCredentials: type: boolean description: A flag enabling resource publication with credentials. Set `true` for publishing with credentials. rules: type: array description: A list of rules to restrict access to the published resource. **Required** either `rules` or `resources` or both. Skip `resources` and include `rules` to update only rules. You can pass an empty `rules` object to delete all rules. items: type: object properties: source: type: string description: Claim for authorization using JWT. For authorization with API keys the source is `roles`. function: type: string description: The function. enum: - EQUAL - CONTAIN - REGEX targets: type: array description: Claim value(s) for authorization using JWT. For authorization with API keys - the roles assigned to API key. items: type: string required: - name - url - targetFolder PublicationResponse: type: object description: Publications properties: publications: type: array description: List of publications. items: type: object properties: url: type: string description: The URL that represents the publication request. name: type: string description: The publication name. author: type: string description: The author of the publication request. displayAuthor: type: string description: The name displayed on UI instead of the author of the publication request. createdAt: type: integer description: The creation time of the publication request in milliseconds. targetFolder: type: string description: The name of the target folder for the publication. status: type: string description: Publication status. enum: - PENDING - APPROVED - REJECTED resourceTypes: type: array description: The type of resource. items: type: string enum: - FILE - PROMPT - CONVERSATION - APPLICATION NotificationsResponse: type: object description: Notifications properties: notifications: type: array description: List of notifications. items: type: object properties: id: type: string description: The identifier of the notification. url: type: string description: The URL of the resource the notification applies to. For example, a publication request URL if the notification is created for publication requests. type: type: string description: The notification type. message: type: string description: The notification text. timestamp: type: number description: The notification timestamp. GetPublicationResponseObject: type: object description: Publications properties: url: type: string description: The URL with the publication bucket id, and the publication request id. createdAt: type: integer description: The creation time of the publication request in milliseconds. name: type: string description: The publication name. author: type: string description: The author of the publication request. displayAuthor: type: string description: The name displayed on UI instead of the author of the publication request. targetFolder: type: string description: The name of the target folder for the publication. status: type: string description: Publication status. enum: - PENDING - APPROVED - REJECTED resources: type: array description: List of resources to be published. items: type: object properties: action: type: string description: The type of action to be performed. enum: - ADD - DELETE - ADD_IF_ABSENT sourceUrl: type: string description: The location of the source for the publication resource. targetUrl: type: string description: The path to the destination for the publication. reviewUrl: type: string description: The URL of the source. resourceTypes: type: array description: The type of resource. items: type: string enum: - FILE - PROMPT - CONVERSATION - APPLICATION rules: type: array description: List of rules to restrict access to the published resource. items: type: object properties: source: type: string description: Claim for authorization using JWT. For authorization with API keys the source is `roles`. targets: type: array description: Claim value(s) for authorization using JWT. For authorization with API keys - the roles assigned to API key. items: type: string function: type: string description: The function for the rule. enum: - EQUAL - CONTAIN - REGEX PublicationResponseObject: type: object description: Publications properties: url: type: string description: The URL with the publication bucket id, and the publication request id. createdAt: type: integer description: The creation time of the publication request in milliseconds. name: type: string description: The publication name. author: type: string description: The author of the publication request. displayAuthor: type: string description: The name displayed on UI instead of the author of the publication request. targetFolder: type: string description: The name of the target folder for the publication. status: type: string description: Publication status. enum: - PENDING - APPROVED - REJECTED resources: type: array description: List of resources to be published. items: type: object properties: action: type: string description: The type of action to be performed. enum: - ADD - DELETE - ADD_IF_ABSENT sourceUrl: type: string description: The location of the source for the publication resource. targetUrl: type: string description: The path to the destination for the publication. reviewUrl: type: string description: The URL of the source. resourceTypes: type: array description: The type of resource. items: type: string enum: - FILE - PROMPT - CONVERSATION - APPLICATION rules: type: array description: List of rules to restrict access to the published resource. items: type: object properties: source: type: string description: Claim for authorization using JWT. For authorization with API keys the source is `roles`. targets: type: array description: Claim value(s) for authorization using JWT. For authorization with API keys - the roles assigned to API key. items: type: string function: type: string description: The function for the rule. enum: - EQUAL - CONTAIN - REGEX PublicationRules: type: object description: Publication rules properties: rules: type: object description: Map of rules to restrict access to the published resource, where a key is a path to target folder and a value is a list of rules additionalProperties: true properties: key: type: string description: target folder value: type: array description: rules' list items: type: object properties: source: type: string description: Claim for authorization using JWT. For authorization with API keys the source is `roles`. targets: type: array description: Claim value(s) for authorization using JWT. For authorization with API keys - the roles assigned to API key. items: type: string function: type: string description: The function. enum: - EQUAL - CONTAIN - REGEX ChatCompletionResponseStatistics: type: object description: The Assistant work statistics. properties: usage_per_model: type: array description: Statistics of tokens used in models by the Assistant. In case of streaming, the statistics is published fully in one chunk. items: type: object properties: index: type: integer description: |- In *streaming* chat completion responses, each model usage includes an `index` field indicating its position in the final ordered list. This field is required because model usages may arrive out of order, and the client must reconstruct the correct sequence using `index`.

In *non-streaming* responses, the `index` field is omitted because the position of a model usage is already determined by its place in the returned list. model: type: string description: The model name. prompt_tokens: type: integer description: The number of tokens in the request to the model. completion_tokens: type: integer description: The number of tokens in the response from the model. total_tokens: type: integer description: The sum of prompt and completion tokens. discarded_messages: type: array items: type: integer description: | The list of indices of messages that were discarded by the Assistant. Returned only when `max_prompt_tokens` was set in the request. CreateChatCompletionStreamResponse: type: object description: Represents a streamed chunk of a chat completion response returned by model, based on the provided input. properties: id: type: string description: A unique identifier for the chat completion. Each chunk has the same ID. object: type: string description: The object type, which is always `chat.completion.chunk`. enum: [chat.completion.chunk] created: type: integer description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. model: type: string description: The model name that generated the response. May not be the same as the deployment name. system_fingerprint: type: string description: | This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. choices: type: array description: A list of generated chunks. items: type: object properties: index: type: integer description: The index of the choice from 0 to _n - 1_ delta: type: object $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" finish_reason: type: string nullable: true description: |- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. required: - index - delta - finish_reason usage: type: object description: This field contains information about used models tokens for generation of the response. In case of streaming, the usage is published fully in one chunk. properties: prompt_tokens: type: integer description: The number of tokens in the request to the model. completion_tokens: type: integer description: The number of tokens in the response from the model. total_tokens: type: integer description: The sum of prompt and completion tokens. required: - prompt_tokens - completion_tokens - total_tokens statistics: type: object $ref: "#/components/schemas/ChatCompletionResponseStatistics" required: - choices - created - id - model - object Error: type: object properties: type: type: string nullable: true message: type: string nullable: true param: type: string nullable: true code: type: string nullable: true display_message: type: string nullable: true description: | The user-friendly error message for non-technical users. userinfo: type: object description: User info properties: project: type: string description: The project name. roles: type: array description: List of user or API key roles. items: type: string userClaims: type: object description: Claims extracted from the access token. properties: email: type: array description: The email of the user. items: type: string sub: type: array description: Identifies the principal or subject of the token. items: type: string ApplicationLogs: type: object description: Application logs properties: logs: type: array description: log records items: $ref: '#/components/schemas/ApplicationLog' ApplicationLog: type: object properties: instance: description: machine instance ID type: string content: description: log content type: string CodeInterpreterRequestFile: type: object properties: sessionId: type: string description: session ID sourceUrl: type: string description: URL to source file targetPath: type: string description: Path to target file CodeInterpreterFile: type: object properties: sessionId: type: string description: session ID path: type: string description: path to file size: type: integer description: file size GetSession: type: object properties: sessionId: type: string description: Session ID PromptRequest: type: object properties: id: type: string description: Prompt unique identifier name: type: string description: Display name folderId: type: string description: Path to the folder where prompt located according to the user's root content: type: string description: Prompt body required: - id - name - folderId - content JsonRpcRequest: type: object required: [ jsonrpc, method ] properties: jsonrpc: type: string enum: [ "2.0" ] description: JSON-RPC protocol version method: type: string description: Name of the method to be invoked. params: description: | Parameter values for the RPC call. Can be: `array` (by-position parameters) OR `object` (by-name parameters). oneOf: - type: array items: { } - type: object id: description: | Identifier established by the client. Must be included in the response if present. If omitted, it's a notification. oneOf: - type: string - type: integer JsonRpcResponse: type: object required: [ jsonrpc ] properties: jsonrpc: type: string enum: [ "2.0" ] description: JSON-RPC protocol version result: description: | The successful result of the RPC call. Must not be included if `error` is present. error: description: | Error object in case of failure. Must not be included if `result` is present. type: object required: [ code, message ] properties: code: type: integer description: Error code. message: type: string description: Error message. data: description: Additional error information id: description: | Same `id` as in the request. `Null` for certain errors where the request `id` cannot be determined. oneOf: - type: string - type: integer Deployments: type: object properties: deployments: type: array items: anyOf: - $ref: '#/components/schemas/ModelOpenAi' - $ref: '#/components/schemas/ApplicationOpenAi' - $ref: '#/components/schemas/ToolsetOpenAi'