openapi: 3.0.3 info: title: Llama Platform Agent Data LlamaExtract API version: 0.1.0 tags: - name: LlamaExtract paths: /api/v1/extraction/jobs: get: tags: - LlamaExtract summary: List Jobs operationId: list_jobs_api_v1_extraction_jobs_get security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: query required: true schema: type: string format: uuid title: Extraction Agent Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/ExtractJob' title: Response List Jobs Api V1 Extraction Jobs Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' post: tags: - LlamaExtract summary: Run Job operationId: run_job_api_v1_extraction_jobs_post security: - HTTPBearer: [] parameters: - name: from_ui in: query required: false schema: type: boolean default: false title: From Ui - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractJobCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/jobs/{job_id}: get: tags: - LlamaExtract summary: Get Job operationId: get_job_api_v1_extraction_jobs__job_id__get security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string format: uuid title: Job Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/jobs/file: post: tags: - LlamaExtract summary: Run Job On File operationId: run_job_on_file_api_v1_extraction_jobs_file_post security: - HTTPBearer: [] parameters: - name: from_ui in: query required: false schema: type: boolean default: false title: From Ui - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/Body_run_job_on_file_api_v1_extraction_jobs_file_post' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/jobs/batch: post: tags: - LlamaExtract summary: Run Batch Jobs operationId: run_batch_jobs_api_v1_extraction_jobs_batch_post security: - HTTPBearer: [] parameters: - name: from_ui in: query required: false schema: type: boolean default: false title: From Ui - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractJobCreateBatch' responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/ExtractJob' title: Response Run Batch Jobs Api V1 Extraction Jobs Batch Post '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/jobs/{job_id}/result: get: tags: - LlamaExtract summary: Get Job Result operationId: get_job_result_api_v1_extraction_jobs__job_id__result_get security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string format: uuid title: Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractResultset' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/runs: get: tags: - LlamaExtract summary: List Extract Runs operationId: list_extract_runs_api_v1_extraction_runs_get security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: query required: true schema: type: string format: uuid title: Extraction Agent Id - name: skip in: query required: false schema: type: integer default: 0 title: Skip - name: limit in: query required: false schema: type: integer default: 25 title: Limit - name: status in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by status title: Status description: Filter by status - name: run_id in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by run ID title: Run Id description: Filter by run ID - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedExtractRunsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/runs/latest-from-ui: get: tags: - LlamaExtract summary: Get Latest Run From Ui operationId: get_latest_run_from_ui_api_v1_extraction_runs_latest_from_ui_get security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: query required: true schema: type: string format: uuid title: Extraction Agent Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: anyOf: - $ref: '#/components/schemas/ExtractRun' - type: 'null' title: Response Get Latest Run From Ui Api V1 Extraction Runs Latest From Ui Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/runs/by-job/{job_id}: get: tags: - LlamaExtract summary: Get Run By Job Id operationId: get_run_by_job_id_api_v1_extraction_runs_by_job__job_id__get security: - HTTPBearer: [] parameters: - name: job_id in: path required: true schema: type: string format: uuid title: Job Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractRun' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/runs/{run_id}: get: tags: - LlamaExtract summary: Get Run operationId: get_run_api_v1_extraction_runs__run_id__get security: - HTTPBearer: [] parameters: - name: run_id in: path required: true schema: type: string format: uuid title: Run Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractRun' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - LlamaExtract summary: Delete Extraction Run operationId: delete_extraction_run_api_v1_extraction_runs__run_id__delete security: - HTTPBearer: [] parameters: - name: run_id in: path required: true schema: type: string format: uuid title: Run Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/run: post: tags: - LlamaExtract summary: Extract Stateless description: Stateless extraction using a default agent in the user's default project; requires `data_schema`, `config`, and one of `file_id` / `text` / base64 file data. operationId: extract_stateless_api_v1_extraction_run_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractStatelessRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractJob' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents: post: tags: - LlamaExtract summary: Create Extraction Agent operationId: create_extraction_agent_api_v1_extraction_extraction_agents_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractAgentCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractAgent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - LlamaExtract summary: List Extraction Agents operationId: list_extraction_agents_api_v1_extraction_extraction_agents_get security: - HTTPBearer: [] parameters: - name: include_default in: query required: false schema: type: boolean description: Whether to include default agents in the results default: false title: Include Default description: Whether to include default agents in the results - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/ExtractAgent' title: Response List Extraction Agents Api V1 Extraction Extraction Agents Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents/schema/validation: post: tags: - LlamaExtract summary: Validate Extraction Schema description: Validate an extraction agent schema; returns the normalized schema or raises 400. operationId: validate_extraction_schema_api_v1_extraction_extraction_agents_schema_validation_post security: - HTTPBearer: [] parameters: - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractSchemaValidateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractSchemaValidateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents/schema/generate: post: tags: - LlamaExtract summary: Generate Extraction Schema description: Generate or refine an extraction agent schema from a file, natural-language prompt, or existing schema. operationId: generate_extraction_schema_api_v1_extraction_extraction_agents_schema_generate_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractSchemaGenerateRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractSchemaGenerateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents/by-name/{name}: get: tags: - LlamaExtract summary: Get Extraction Agent By Name operationId: get_extraction_agent_by_name_api_v1_extraction_extraction_agents_by_name__name__get deprecated: true security: - HTTPBearer: [] parameters: - name: name in: path required: true schema: type: string title: Name - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractAgent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents/default: get: tags: - LlamaExtract summary: Get Or Create Default Extraction Agent description: Get or create the default extraction agent for the current project (empty schema, default config). operationId: get_or_create_default_extraction_agent_api_v1_extraction_extraction_agents_default_get security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractAgent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/extraction/extraction-agents/{extraction_agent_id}: get: tags: - LlamaExtract summary: Get Extraction Agent operationId: get_extraction_agent_api_v1_extraction_extraction_agents__extraction_agent_id__get security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: path required: true schema: type: string format: uuid title: Extraction Agent Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractAgent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - LlamaExtract summary: Delete Extraction Agent operationId: delete_extraction_agent_api_v1_extraction_extraction_agents__extraction_agent_id__delete security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: path required: true schema: type: string format: uuid title: Extraction Agent Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - LlamaExtract summary: Update Extraction Agent operationId: update_extraction_agent_api_v1_extraction_extraction_agents__extraction_agent_id__put security: - HTTPBearer: [] parameters: - name: extraction_agent_id in: path required: true schema: type: string format: uuid title: Extraction Agent Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ExtractAgentUpdate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ExtractAgent' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ExtractModels: type: string enum: - openai-gpt-4-1 - openai-gpt-4-1-mini - openai-gpt-4-1-nano - openai-gpt-5 - openai-gpt-5-mini - gemini-2.0-flash - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.5-pro - openai-gpt-4o - openai-gpt-4o-mini title: ExtractModels description: Extract model options. ExtractAgentUpdate: properties: data_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string title: Data Schema description: The schema of the data config: $ref: '#/components/schemas/ExtractConfig' description: The configuration parameters for the extraction agent. type: object required: - data_schema - config title: ExtractAgentUpdate description: Settings for updating an extraction schema. File: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime name: type: string maxLength: 3000 minLength: 1 title: Name external_file_id: anyOf: - type: string - type: 'null' title: External File Id description: The ID of the file in the external system file_size: anyOf: - type: integer minimum: 0.0 - type: 'null' title: File Size description: Size of the file in bytes file_type: anyOf: - type: string maxLength: 3000 minLength: 1 - type: 'null' title: File Type description: File type (e.g. pdf, docx, etc.) project_id: type: string format: uuid title: Project Id description: The ID of the project that the file belongs to last_modified_at: anyOf: - type: string format: date-time - type: 'null' title: Last Modified At description: The last modified time of the file resource_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Resource Info description: Resource information for the file permission_info: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Permission Info description: Permission information for the file data_source_id: anyOf: - type: string format: uuid - type: 'null' title: Data Source Id description: The ID of the data source that the file belongs to expires_at: anyOf: - type: string format: date-time - type: 'null' title: Expires At description: The expiration date for the file. Files past this date can be deleted. purpose: anyOf: - type: string - type: 'null' title: Purpose description: The intended purpose of the file (e.g., 'user_data', 'parse', 'extract', 'split', 'classify') type: object required: - id - name - project_id title: File description: Schema for a file. PaginatedExtractRunsResponse: properties: items: items: $ref: '#/components/schemas/ExtractRun' type: array title: Items description: The list of extraction runs total: type: integer title: Total description: The total number of extraction runs skip: type: integer title: Skip description: The number of extraction runs skipped limit: type: integer title: Limit description: The maximum number of extraction runs returned type: object required: - items - total - skip - limit title: PaginatedExtractRunsResponse description: Schema for paginated extraction runs response. ExtractSchemaValidateRequest: properties: data_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string title: Data Schema type: object required: - data_schema title: ExtractSchemaValidateRequest description: Request schema for validating an extraction schema. PublicModelName: type: string enum: - openai-gpt-4o - openai-gpt-4o-mini - openai-gpt-4-1 - openai-gpt-4-1-mini - openai-gpt-4-1-nano - openai-gpt-5 - openai-gpt-5-mini - openai-gpt-5-nano - openai-text-embedding-3-large - openai-text-embedding-3-small - openai-whisper-1 - anthropic-sonnet-3.5 - anthropic-sonnet-3.5-v2 - anthropic-sonnet-3.7 - anthropic-sonnet-4.0 - anthropic-sonnet-4.5 - anthropic-haiku-3.5 - anthropic-haiku-4.5 - gemini-2.5-flash - gemini-3.0-pro - gemini-3.1-pro - gemini-2.5-pro - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.5-flash-lite title: PublicModelName description: Public model names. ExtractAgentCreate: properties: name: type: string maxLength: 3000 minLength: 1 title: Name description: The name of the extraction schema data_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string title: Data Schema description: The schema of the data. config: $ref: '#/components/schemas/ExtractConfig' description: The configuration parameters for the extraction agent. type: object required: - name - data_schema - config title: ExtractAgentCreate description: Settings for creating an extraction agent. ExtractTarget: type: string enum: - PER_DOC - PER_PAGE - PER_TABLE_ROW title: ExtractTarget description: Defines the extraction target scope. ExtractJobCreateBatch: properties: webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes extraction_agent_id: type: string format: uuid title: Extraction Agent Id description: The id of the extraction agent file_ids: items: type: string format: uuid type: array minItems: 1 title: File Ids description: The ids of the files data_schema_override: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string - type: 'null' title: Data Schema Override description: The data schema to override the extraction agent's data schema with config_override: anyOf: - $ref: '#/components/schemas/ExtractConfig' - type: 'null' description: The config to override the extraction agent's config with type: object required: - extraction_agent_id - file_ids title: ExtractJobCreateBatch description: Schema for creating extraction jobs in batch. ExtractConfig: properties: priority: anyOf: - type: string enum: - low - medium - high - critical - type: 'null' title: Priority description: The priority for the request. This field may be ignored or overwritten depending on the organization tier. extraction_target: $ref: '#/components/schemas/ExtractTarget' description: The extraction target specified. default: PER_DOC extraction_mode: $ref: '#/components/schemas/ExtractMode' description: The extraction mode specified (FAST, BALANCED, MULTIMODAL, PREMIUM). default: PREMIUM parse_model: anyOf: - $ref: '#/components/schemas/PublicModelName' - type: 'null' description: The parse model to use for document parsing. If not provided, uses the default for the extraction mode. extract_model: anyOf: - $ref: '#/components/schemas/ExtractModels' - type: string - type: 'null' title: Extract Model description: The extract model to use for data extraction. If not provided, uses the default for the extraction mode. multimodal_fast_mode: type: boolean title: Multimodal Fast Mode description: 'DEPRECATED: Whether to use fast mode for multimodal extraction.' default: false system_prompt: anyOf: - type: string - type: 'null' title: System Prompt description: The system prompt to use for the extraction. use_reasoning: type: boolean title: Use Reasoning description: Whether to use reasoning for the extraction. default: false cite_sources: type: boolean title: Cite Sources description: Whether to cite sources for the extraction. default: false citation_bbox: type: boolean title: Citation Bbox description: 'Whether to fetch citation bounding boxes for the extraction. Only available in PREMIUM mode. Deprecated: this is now synonymous with cite_sources.' default: false deprecated: true confidence_scores: type: boolean title: Confidence Scores description: Whether to fetch confidence scores for the extraction. default: false chunk_mode: $ref: '#/components/schemas/DocumentChunkMode' description: The mode to use for chunking the document. default: PAGE high_resolution_mode: type: boolean title: High Resolution Mode description: Whether to use high resolution mode for the extraction. default: false invalidate_cache: type: boolean title: Invalidate Cache description: Whether to invalidate the cache for the extraction. default: false num_pages_context: anyOf: - type: integer minimum: 1.0 - type: 'null' title: Num Pages Context description: Number of pages to pass as context on long document extraction. page_range: anyOf: - type: string - type: 'null' title: Page Range description: Comma-separated list of page numbers or ranges to extract from (1-based, e.g., '1,3,5-7,9' or '1-3,8-10'). type: object title: ExtractConfig description: Configuration parameters for the extraction agent. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ExtractSchemaGenerateResponse: properties: data_schema: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Data Schema description: The generated JSON schema type: object required: - data_schema title: ExtractSchemaGenerateResponse description: Response schema for schema generation. ExtractMode: type: string enum: - FAST - BALANCED - PREMIUM - MULTIMODAL title: ExtractMode description: Extraction mode options. ExtractSchemaValidateResponse: properties: data_schema: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Data Schema type: object required: - data_schema title: ExtractSchemaValidateResponse description: Response schema for schema validation. ExtractState: type: string enum: - CREATED - PENDING - SUCCESS - ERROR title: ExtractState ExtractJobCreate: properties: priority: anyOf: - type: string enum: - low - medium - high - critical - type: 'null' title: Priority description: The priority for the request. This field may be ignored or overwritten depending on the organization tier. webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes extraction_agent_id: type: string format: uuid title: Extraction Agent Id description: The id of the extraction agent file_id: type: string format: uuid title: File Id description: The id of the file data_schema_override: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string - type: 'null' title: Data Schema Override description: The data schema to override the extraction agent's data schema with config_override: anyOf: - $ref: '#/components/schemas/ExtractConfig' - type: 'null' description: The config to override the extraction agent's config with type: object required: - extraction_agent_id - file_id title: ExtractJobCreate description: Schema for creating an extraction job. FileData: properties: data: type: string title: Data description: The file content as base64-encoded string mime_type: type: string title: Mime Type description: The MIME type of the file (e.g., 'application/pdf', 'text/plain') type: object required: - data - mime_type title: FileData description: Schema for file data with base64 content and MIME type. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError ExtractAgent: properties: id: type: string format: uuid title: Id description: The id of the extraction agent. name: type: string title: Name description: The name of the extraction agent. project_id: type: string format: uuid title: Project Id description: The ID of the project that the extraction agent belongs to. data_schema: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Data Schema description: The schema of the data. config: $ref: '#/components/schemas/ExtractConfig' description: The configuration parameters for the extraction agent. custom_configuration: anyOf: - type: string const: default - type: 'null' title: Custom Configuration description: Custom configuration type for the extraction agent. Currently supports 'default'. created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: The creation time of the extraction agent. updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: The last update time of the extraction agent. type: object required: - id - name - project_id - data_schema - config title: ExtractAgent description: Schema and configuration for an extraction agent. ExtractStatelessRequest: properties: webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes data_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string title: Data Schema description: The schema of the data to extract config: $ref: '#/components/schemas/ExtractConfig' description: The configuration parameters for the extraction file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The ID of the file to extract from text: anyOf: - type: string - type: 'null' title: Text description: The text content to extract from file: anyOf: - $ref: '#/components/schemas/FileData' - type: 'null' description: The file data with base64 content and MIME type type: object required: - data_schema - config title: ExtractStatelessRequest description: Schema for stateless extraction requests. ExtractJob: properties: id: type: string format: uuid title: Id description: The id of the extraction job extraction_agent: $ref: '#/components/schemas/ExtractAgent' description: The agent that the job was run on. status: type: string enum: - PENDING - SUCCESS - ERROR - PARTIAL_SUCCESS - CANCELLED title: Status description: The status of the extraction job error: anyOf: - type: string - type: 'null' title: Error description: The error that occurred during extraction file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The id of the file that the extract was extracted from file: anyOf: - $ref: '#/components/schemas/File' - type: 'null' description: '[DEPRECATED] The file that the extract was extracted from' deprecated: true type: object required: - id - extraction_agent - status title: ExtractJob description: Schema for an extraction job. ExtractSchemaGenerateRequest: properties: prompt: anyOf: - type: string - type: 'null' title: Prompt description: Natural language description of the data structure to extract file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: Optional file ID to analyze for schema generation data_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: string - type: 'null' title: Data Schema description: Optional schema to validate, refine, or extend during generation type: object title: ExtractSchemaGenerateRequest description: Request schema for generating an extraction schema. DocumentChunkMode: type: string enum: - PAGE - SECTION title: DocumentChunkMode description: How to chunk documents. ExtractResultset: properties: run_id: type: string format: uuid title: Run Id description: The id of the extraction run extraction_agent_id: type: string format: uuid title: Extraction Agent Id description: The id of the extraction agent data: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - items: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object type: array - type: 'null' title: Data description: The data extracted from the file extraction_metadata: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Extraction Metadata description: The metadata extracted from the file type: object required: - run_id - extraction_agent_id - data - extraction_metadata title: ExtractResultset description: Schema for an extraction resultset. WebhookConfiguration: properties: webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url description: URL to receive webhook POST notifications examples: - https://example.com/webhooks/llamacloud webhook_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Webhook Headers description: Custom HTTP headers sent with each webhook request (e.g. auth tokens) examples: - Authorization: Bearer sk-... webhook_events: anyOf: - items: type: string enum: - extract.pending - extract.success - extract.error - extract.partial_success - extract.cancelled - parse.pending - parse.running - parse.success - parse.error - parse.partial_success - parse.cancelled - classify.pending - classify.running - classify.success - classify.error - classify.partial_success - classify.cancelled - sheets.pending - sheets.success - sheets.error - sheets.partial_success - sheets.cancelled - unmapped_event type: array - type: 'null' title: Webhook Events description: Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. examples: - - parse.success - parse.error webhook_output_format: anyOf: - type: string - type: 'null' title: Webhook Output Format description: 'Response format sent to the webhook: ''string'' (default) or ''json''' examples: - json type: object title: WebhookConfiguration description: Configuration for a single outbound webhook endpoint. ExtractRun: properties: id: type: string format: uuid title: Id description: The id of the extraction run created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime project_id: type: string format: uuid title: Project Id description: The id of the project that the extraction run belongs to extraction_agent_id: type: string format: uuid title: Extraction Agent Id description: The id of the extraction agent data_schema: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object title: Data Schema description: The schema used for extraction config: $ref: '#/components/schemas/ExtractConfig' description: The config used for extraction file_id: anyOf: - type: string format: uuid - type: 'null' title: File Id description: The id of the file that the extract was extracted from file: anyOf: - $ref: '#/components/schemas/File' - type: 'null' description: '[DEPRECATED] The file that the extract was extracted from' deprecated: true status: $ref: '#/components/schemas/ExtractState' description: The status of the extraction run error: anyOf: - type: string - type: 'null' title: Error description: The error that occurred during extraction job_id: anyOf: - type: string format: uuid - type: 'null' title: Job Id description: The id of the job that the extraction run belongs to data: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - items: additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object type: array - type: 'null' title: Data description: The data extracted from the file extraction_metadata: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Extraction Metadata description: The metadata extracted from the file from_ui: type: boolean title: From Ui description: Whether this extraction run was triggered from the UI type: object required: - id - project_id - extraction_agent_id - data_schema - config - status - from_ui title: ExtractRun description: Schema for an extraction run. Body_run_job_on_file_api_v1_extraction_jobs_file_post: properties: extraction_agent_id: type: string format: uuid title: Extraction Agent Id description: The id of the extraction agent file: type: string format: binary title: File description: The file to run the job on data_schema_override: anyOf: - type: string - type: 'null' title: Data Schema Override description: The data schema to override the extraction agent's data schema with as a JSON string config_override: anyOf: - type: string - type: 'null' title: Config Override description: The config to override the extraction agent's config with as a JSON string type: object required: - extraction_agent_id - file title: Body_run_job_on_file_api_v1_extraction_jobs_file_post securitySchemes: HTTPBearer: type: http scheme: bearer