openapi: 3.1.0 info: title: Hugging Face Dataset Viewer Audio Chat Completions API description: Query and visualize datasets stored on the Hugging Face Hub through a lightweight REST API. Get dataset splits, preview rows, search and filter data, access Parquet files, retrieve size statistics, and obtain Croissant metadata - all without downloading the entire dataset. version: 1.0.0 termsOfService: https://huggingface.co/terms-of-service contact: name: Hugging Face Support url: https://huggingface.co/support license: name: Apache 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 servers: - url: https://datasets-server.huggingface.co description: Hugging Face Dataset Viewer production server security: - {} - bearerAuth: [] tags: - name: Chat Completions description: OpenAI-compatible chat completion endpoints paths: /v1/chat/completions: post: summary: Create Chat Completion description: Create a chat completion using an OpenAI-compatible API. Supports conversational LLMs and Vision-Language Models (VLMs). Requests are routed to the optimal inference provider automatically. operationId: createChatCompletion tags: - Chat Completions requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: CreatechatcompletionRequestExample: summary: Default createChatCompletion request x-microcks-default: true value: model: example_value messages: - role: system content: example_value name: Example Title tool_calls: - {} tool_call_id: '500123' frequency_penalty: 42.5 logprobs: true max_tokens: 10 presence_penalty: 42.5 reasoning_effort: example_value response_format: example_value seed: 10 stop: - example_value stream: true stream_options: include_usage: true temperature: 42.5 tool_choice: example_value tool_prompt: example_value tools: - type: example_value function: name: Example Title description: A sample description. parameters: example_value top_logprobs: 10 top_p: 42.5 responses: '200': description: Chat completion response content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' examples: Createchatcompletion200Example: summary: Default createChatCompletion 200 response x-microcks-default: true value: id: abc123 object: example_value created: 10 model: example_value system_fingerprint: example_value choices: - index: 10 message: role: example_value content: example_value tool_calls: {} finish_reason: stop logprobs: content: {} usage: prompt_tokens: 10 completion_tokens: 10 total_tokens: 10 text/event-stream: schema: $ref: '#/components/schemas/ChatCompletionStreamResponse' examples: Createchatcompletion200Example: summary: Default createChatCompletion 200 response x-microcks-default: true value: id: abc123 object: example_value created: 10 model: example_value system_fingerprint: example_value choices: - index: 10 delta: role: example_value content: example_value tool_calls: {} finish_reason: example_value logprobs: content: {} usage: prompt_tokens: 10 completion_tokens: 10 total_tokens: 10 '400': description: Bad request - invalid parameters content: application/json: schema: $ref: '#/components/schemas/Error' examples: Createchatcompletion400Example: summary: Default createChatCompletion 400 response x-microcks-default: true value: error: message: example_value type: example_value code: example_value '401': description: Unauthorized - invalid or missing API token content: application/json: schema: $ref: '#/components/schemas/Error' examples: Createchatcompletion401Example: summary: Default createChatCompletion 401 response x-microcks-default: true value: error: message: example_value type: example_value code: example_value '404': description: Model not found or not available through any provider content: application/json: schema: $ref: '#/components/schemas/Error' examples: Createchatcompletion404Example: summary: Default createChatCompletion 404 response x-microcks-default: true value: error: message: example_value type: example_value code: example_value '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' examples: Createchatcompletion429Example: summary: Default createChatCompletion 429 response x-microcks-default: true value: error: message: example_value type: example_value code: example_value '502': description: Provider error content: application/json: schema: $ref: '#/components/schemas/Error' examples: Createchatcompletion502Example: summary: Default createChatCompletion 502 response x-microcks-default: true value: error: message: example_value type: example_value code: example_value x-microcks-operation: delay: 0 dispatcher: FALLBACK components: schemas: Usage: type: object properties: prompt_tokens: type: integer description: Number of tokens in the prompt example: 10 completion_tokens: type: integer description: Number of tokens in the completion example: 10 total_tokens: type: integer description: Total tokens used example: 10 ChatCompletionStreamResponse: type: object properties: id: type: string example: abc123 object: type: string const: chat.completion.chunk example: example_value created: type: integer example: 10 model: type: string example: example_value system_fingerprint: type: string example: example_value choices: type: array items: type: object properties: index: type: integer delta: type: object properties: role: type: string content: type: string tool_calls: type: array items: type: object properties: id: type: string index: type: integer type: type: string function: type: object properties: name: type: string arguments: type: string finish_reason: type: string logprobs: type: object properties: content: type: array items: type: object properties: token: type: string logprob: type: number top_logprobs: type: array items: type: object properties: token: type: string logprob: type: number example: [] usage: $ref: '#/components/schemas/Usage' ChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: Model ID to use. Can be a Hugging Face model ID (e.g., meta-llama/Llama-3-70b-chat-hf) or a provider-specific identifier. example: meta-llama/Llama-3-70b-chat-hf messages: type: array description: List of messages comprising the conversation items: type: object required: - role properties: role: type: string enum: - system - user - assistant - tool description: The role of the message author content: oneOf: - type: string - type: array items: oneOf: - type: object required: - type - text properties: type: type: string const: text text: type: string - type: object required: - type - image_url properties: type: type: string const: image_url image_url: type: object required: - url properties: url: type: string description: Message content (string or array for multimodal) name: type: string description: Optional name for the participant tool_calls: type: array items: type: object required: - id - type - function properties: id: type: string type: type: string function: type: object required: - name properties: name: type: string arguments: type: string description: type: string tool_call_id: type: string description: Tool call ID for tool responses example: [] frequency_penalty: type: number minimum: -2.0 maximum: 2.0 default: 0 description: Penalize tokens based on frequency in text so far example: 42.5 logprobs: type: boolean default: false description: Whether to return log probabilities example: true max_tokens: type: integer description: Maximum number of tokens to generate example: 10 presence_penalty: type: number minimum: -2.0 maximum: 2.0 default: 0 description: Penalize tokens based on presence in text so far example: 42.5 reasoning_effort: type: string description: Constrains effort on reasoning for models that support it. Common values are none, minimal, low, medium, high, xhigh. example: example_value response_format: oneOf: - type: object properties: type: type: string const: text - type: object required: - type - json_schema properties: type: type: string const: json_schema json_schema: type: object required: - name properties: name: type: string description: type: string schema: type: object strict: type: boolean - type: object properties: type: type: string const: json_object example: example_value seed: type: integer description: Random seed for reproducibility example: 10 stop: type: array items: type: string maxItems: 4 description: Up to 4 sequences where generation will stop example: [] stream: type: boolean default: false description: Whether to stream partial responses using SSE example: true stream_options: type: object properties: include_usage: type: boolean description: Include usage statistics in stream example: example_value temperature: type: number minimum: 0 maximum: 2 default: 1.0 description: Sampling temperature example: 42.5 tool_choice: oneOf: - type: string enum: - auto - none - required - type: object required: - function properties: function: type: object required: - name properties: name: type: string description: Controls tool usage example: example_value tool_prompt: type: string description: Prompt prepended before tools example: example_value tools: type: array items: type: object required: - type - function properties: type: type: string function: type: object required: - name properties: name: type: string description: type: string parameters: type: object description: List of tools the model may call example: [] top_logprobs: type: integer minimum: 0 maximum: 5 description: Number of most likely tokens to return per position example: 10 top_p: type: number minimum: 0 maximum: 1 default: 1.0 description: Nucleus sampling parameter example: 42.5 ChatCompletionResponse: type: object properties: id: type: string description: Unique completion identifier example: abc123 object: type: string const: chat.completion example: example_value created: type: integer description: Unix timestamp example: 10 model: type: string description: Model used example: example_value system_fingerprint: type: string example: example_value choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string content: type: string tool_calls: type: array items: type: object properties: id: type: string type: type: string function: type: object properties: name: type: string arguments: type: string finish_reason: type: string enum: - stop - length - tool_calls - content_filter logprobs: type: object properties: content: type: array items: type: object properties: token: type: string logprob: type: number top_logprobs: type: array items: type: object properties: token: type: string logprob: type: number example: [] usage: $ref: '#/components/schemas/Usage' Error: type: object properties: error: type: object properties: message: type: string description: Error message type: type: string description: Error type code: type: string description: Error code example: example_value securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: HF Token description: Optional Hugging Face API token. Required for private and gated datasets.