> ## Documentation Index > Fetch the complete documentation index at: https://docs.samplehc.com/llms.txt > Use this file to discover all available pages before exploring further. # Document extraction (async) > Initiates a modern, flexible asynchronous data extraction process using a JSON schema for the desired output and a prompt. Returns an ID for tracking. ## OpenAPI ````yaml https://app.stainless.com/api/spec/documented/samplehc/openapi.documented.yml post /api/v2/documents/extract openapi: 3.0.3 info: title: Sample Healthcare API description: API for Sample Healthcare version: 1.0.0 servers: [] security: [] paths: /api/v2/documents/extract: post: tags: - Document summary: Document extraction (async) description: >- Initiates a modern, flexible asynchronous data extraction process using a JSON schema for the desired output and a prompt. Returns an ID for tracking. requestBody: content: application/json: schema: type: object properties: documents: type: array items: type: object properties: id: type: string fileName: type: string required: - id - fileName additionalProperties: false description: An array of documents to extract data from. responseJsonSchema: type: object additionalProperties: {} description: >- A JSON schema defining the structure of the desired extraction output. prompt: type: string description: A prompt guiding the extraction process. reasoningEffort: type: string enum: - minimal - low - medium - high - xhigh description: >- Optional control over the reasoning effort for extraction. `minimal` and `xhigh` are only supported by newer OpenAI models (e.g. GPT-5 family supports `minimal`; GPT-5.5 supports `xhigh`). model: type: string enum: - reasoning-3-mini - reasoning-3 - base-5 - base-5-mini - base-5-nano - base-4.1 - base-4.1-mini - base-4.1-nano - base-5.2 - base-5.2-chat-latest - base-5.4 - base-5.4-mini - base-5.5 - qwen3-next-80b-thinking - qwen3-next-80b-instruct - glm-4.7 - deepseek-v3.2 - kimi-k2-thinking - gemini-3-pro - gemini-3-flash - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite default: reasoning-3-mini description: The model to use for extraction. rerankerModelId: type: string enum: - cohere.rerank-v3-5:0 - amazon.rerank-v1:0 description: Optional reranker model ID override for relevance filtering. forceReranker: type: boolean default: false description: >- Force using the reranker for relevance filtering even with smaller document sets. useNativeStructuredOutput: type: boolean description: >- Deprecated. Accepted for backwards compatibility and ignored. useTypeScriptExtraction: type: boolean description: >- Deprecated. Accepted for backwards compatibility and ignored. priority: type: string enum: - interactive - non-interactive - background default: interactive description: >- The priority of the extraction task. Non-interactive is lower priority. Background are tasks that can be run in the background while the user is doing other things. ocrEnhance: type: object properties: summarizeFigures: type: boolean description: Whether to summarize figures during OCR. agentic: type: array items: anyOf: - type: object properties: scope: type: string enum: - figure prompt: type: string description: Prompt for figure analysis. required: - scope - prompt additionalProperties: false - type: object properties: scope: type: string enum: - text prompt: type: string description: Optional prompt for text analysis. required: - scope additionalProperties: false - type: object properties: scope: type: string enum: - table prompt: type: string description: >- Optional prompt to guide table reconstruction (merged cells, multi-level headers, faint borders). required: - scope additionalProperties: false description: Agentic enhancement configuration. required: - summarizeFigures - agentic additionalProperties: false description: >- OCR enhancement configuration for figure, text, and table analysis. ocrQuality: type: string enum: - high - low description: OCR quality setting filterFailedPdfs: type: boolean default: false description: Filter out failed pdfs required: - documents - responseJsonSchema - prompt additionalProperties: false required: true responses: '202': description: Accepted. Advanced extraction process initiated. content: application/json: schema: type: object properties: asyncResultId: type: string description: The ID to track the asynchronous extraction task. required: - asyncResultId additionalProperties: false '400': description: Default Response content: application/json: schema: type: object properties: error: type: string description: The error message. message: type: string description: The message. statusCode: type: number description: The status code. details: type: object additionalProperties: {} description: The details of the error additionalProperties: true '404': description: Default Response content: application/json: schema: type: object properties: error: type: string description: Not Found, one or more specified documents do not exist. required: - error additionalProperties: false '500': description: Default Response content: application/json: schema: type: object properties: error: type: string description: >- Internal server error while initiating advanced extraction. required: - error additionalProperties: false x-codeSamples: - lang: Python source: |- import os from samplehc import SampleHealthcare client = SampleHealthcare( api_key=os.environ.get("SAMPLEHC_API_KEY"), # This is the default and can be omitted ) response = client.v2.documents.extract( documents=[{ "id": "id", "file_name": "fileName", }], prompt="prompt", response_json_schema={ "foo": "bar" }, ) print(response.async_result_id) ````