> ## Documentation Index > Fetch the complete documentation index at: https://docs.cloudglue.dev/llms.txt > Use this file to discover all available pages before exploring further. # Chat Completions > Generate a model response to a conversation that can include references to video content ## OpenAPI ````yaml POST /chat/completions openapi: 3.0.0 info: title: Cloudglue API description: API for Cloudglue license: name: Apache License 2.0 url: https://www.apache.org/licenses/LICENSE-2.0 version: 0.7.8 servers: - url: https://api.cloudglue.dev/v1 security: - bearerAuth: [] paths: /chat/completions: post: tags: - Chat summary: >- Generate a model response to a conversation that can include references to video content description: >- Generate a model response to a conversation that can include references to video content operationId: createCompletion requestBody: description: Chat completion parameters content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' required: true responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/ChatCompletionResponse' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/Error' '404': description: Collections not found content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Chat completion limits reached (monthly or daily) content: application/json: schema: $ref: '#/components/schemas/Error' '500': description: An unexpected error occurred on the server content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ChatCompletionRequest: type: object properties: model: type: string description: Name of the video understanding model to use. enum: - nimbus-001 messages: type: array description: A list of messages comprising the conversation so far items: $ref: '#/components/schemas/ChatMessage' collections: type: array description: >- List of collection IDs to use as context for the chat. Note that 'nimbus-001' only supports collections with collection_type 'media-descriptions' or 'rich-transcripts' items: type: string minItems: 1 maxItems: 1 filter: type: object description: Filter criteria to constrain search results used in chat properties: metadata: type: array description: Filter by file metadata using JSON path expressions items: type: object properties: path: type: string description: >- JSON path on metadata object (e.g. 'my_custom_field', 'category.subcategory') operator: type: string enum: - NotEqual - Equal - LessThan - GreaterThan - In - ContainsAny - ContainsAll description: Comparison operator to apply valueText: type: string description: >- Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In) valueTextArray: type: array items: type: string description: >- Array of values for array comparisons (used with ContainsAny, ContainsAll) required: - path - operator video_info: type: array description: >- Filter by video information. Use scope 'file' for source video properties or 'segment' for segment properties (e.g. segment duration). items: type: object properties: path: type: string enum: - duration_seconds - has_audio description: >- JSON path on video_info object (e.g. 'has_audio', 'duration_seconds') scope: type: string enum: - file - segment description: >- Scope of the filter. 'file' filters by source video properties, 'segment' filters by segment properties. Only duration_seconds is supported with segment scope. operator: type: string enum: - NotEqual - Equal - LessThan - GreaterThan - In - ContainsAny - ContainsAll description: Comparison operator to apply valueText: type: string description: >- Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In) valueTextArray: type: array items: type: string description: >- Array of values for array comparisons (used with ContainsAny, ContainsAll) required: - path - operator file: type: array description: Filter by file properties using JSON path expressions items: type: object properties: path: type: string description: >- JSON path on file object (e.g. 'uri', 'id', 'filename', 'created_at', 'bytes') operator: type: string enum: - NotEqual - Equal - LessThan - GreaterThan - In - ContainsAny - ContainsAll description: Comparison operator to apply valueText: type: string description: >- Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In) valueTextArray: type: array items: type: string description: >- Array of values for array comparisons (used with ContainsAny, ContainsAll) required: - path - operator temperature: type: number description: Sampling temperature to use, between 0 and 2 minimum: 0 maximum: 2 required: - model - messages - collections ChatCompletionResponse: type: object properties: id: type: string description: Unique identifier for this chat completion object: type: string description: Object type, always "chat.completion" created_at: type: integer description: Unix timestamp in milliseconds when the chat completion was created model: type: string description: The model used for the chat completion choices: type: array description: The generated responses items: type: object properties: index: type: integer description: The index of this choice message: $ref: '#/components/schemas/ChatMessage' description: The chat message generated by the model citations: type: array description: >- Citations to specific video segments that informed the response items: allOf: - type: object properties: collection_id: type: string description: ID of the collection containing the cited video file_id: type: string description: ID of the file being cited segment_id: type: string description: ID of the segment being cited start_time: oneOf: - type: string description: Start time of the cited segment in seconds - type: number description: Start time of the cited segment in seconds description: Start time of the cited segment in seconds end_time: oneOf: - type: string description: End time of the cited segment in seconds - type: number description: End time of the cited segment in seconds description: End time of the cited segment in seconds text: type: string description: >- (Deprecated) Relevant text from the segment; use context and relevant_sources instead context: type: string description: >- Short explanation of the relevance of the segment to the query provided as context relevant_sources: type: array description: >- List of source modalities in segment that are relevant for this citation items: type: object properties: text: type: string description: >- Source modality, one of visual_scene_description, scene_text, speech - $ref: '#/components/schemas/DescribeOutput' payload: $ref: '#/components/schemas/ChatCompletionPayload' usage: type: object description: Usage statistics for the completion request properties: prompt_tokens: type: integer description: Number of tokens in the prompt completion_tokens: type: integer description: Number of tokens in the generated completion total_tokens: type: integer description: Total number of tokens used in the request Error: required: - error type: object properties: error: type: string ChatMessage: type: object properties: role: type: string description: The role of the message author enum: - system - user - assistant content: type: string description: The content of the message name: type: string description: The name of the author of this message required: - role - content DescribeOutput: type: object properties: visual_scene_description: type: array description: Array of visual descriptions items: $ref: '#/components/schemas/DescribeOutputPart' scene_text: type: array description: Array of scene text extractions items: $ref: '#/components/schemas/DescribeOutputPart' speech: type: array description: Array of speech transcriptions items: $ref: '#/components/schemas/SpeechOutputPart' audio_description: type: array description: Array of audio descriptions items: $ref: '#/components/schemas/DescribeOutputPart' ChatCompletionPayload: type: object properties: messages: type: array items: $ref: '#/components/schemas/ChatMessage' temperature: type: number description: The temperature of the chat completion filter: $ref: '#/components/schemas/SearchFilter' collections: type: array items: type: string format: uuid DescribeOutputPart: type: object properties: text: type: string description: Text content start_time: type: number description: Start time in seconds end_time: type: number description: End time in seconds SpeechOutputPart: type: object properties: speaker: type: string description: Identified speaker text: type: string description: Transcribed speech text start_time: type: number description: Start time of speech in seconds end_time: type: number description: End time of speech in seconds words: type: array description: >- Word-level timestamps. Only present when include_word_timestamps=true. Not available for YouTube sources. items: $ref: '#/components/schemas/WordTimestamp' SearchFilter: type: object properties: metadata: type: array description: Filter by file metadata using JSON path expressions items: allOf: - $ref: '#/components/schemas/SearchFilterCriteria' - type: object properties: scope: type: string enum: - file - segment description: >- Specifies scope of eligible search items (file/segment) to check metadata filtering conditions video_info: type: array description: >- Filter by video information. Use scope 'file' to filter by source video properties, or 'segment' to filter by individual segment properties (e.g. segment duration). items: allOf: - $ref: '#/components/schemas/SearchFilterCriteria' - type: object properties: path: type: string enum: - duration_seconds - has_audio scope: type: string enum: - file - segment description: >- Scope of the filter. 'file' filters by source video properties, 'segment' filters by segment properties. Only duration_seconds is supported with segment scope. file: type: array description: Filter by file properties items: allOf: - $ref: '#/components/schemas/SearchFilterCriteria' - type: object properties: path: type: string enum: - bytes - filename - uri - created_at - id WordTimestamp: type: object description: A single word with its timing information properties: word: type: string description: The word text start_time: type: number description: Start time of the word in seconds end_time: type: number description: End time of the word in seconds required: - word - start_time - end_time SearchFilterCriteria: type: object required: - path - operator properties: path: type: string description: JSON path for the field to filter on operator: type: string enum: - NotEqual - Equal - LessThan - GreaterThan - ContainsAny - ContainsAll - In - Like description: Comparison operator to apply valueText: type: string description: >- Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, Like) valueTextArray: type: array items: type: string description: >- Array of values for array comparisons (used with ContainsAny, ContainsAll, In) securitySchemes: bearerAuth: type: http scheme: bearer ````