{ "openapi": "3.0.1", "info": { "title": "LangExtract - Structured Data Extractor", "description": "Extract structured data from unstructured text using Google's LangExtract library & LLMs. Get entities, relationships & attributes in clean JSON with source grounding. Supports Gemini, OpenAI, Anthropic, Groq & custom endpoints. Perfect for parsing resumes, contracts, reports & documents.", "version": "0.0", "x-build-id": "8WLJmteTENh4czgoi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vivianferreira~langextract-structured-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vivianferreira-langextract-structured-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vivianferreira~langextract-structured-data-extractor/runs": { "post": { "operationId": "runs-sync-vivianferreira-langextract-structured-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vivianferreira~langextract-structured-data-extractor/run-sync": { "post": { "operationId": "run-sync-vivianferreira-langextract-structured-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "provider", "apiKey", "schema" ], "properties": { "provider": { "title": "Model Provider", "enum": [ "Gemini", "OpenAI", "Anthropic", "Groq", "OpenAI-Compatible" ], "type": "string", "description": "Select your LLM provider.", "default": "Gemini" }, "apiKey": { "title": "API Key", "type": "string", "description": "Your API key for the selected provider." }, "baseUrl": { "title": "Base URL (Custom)", "type": "string", "description": "Custom endpoint for OpenAI-compatible APIs (e.g., http://localhost:11434/v1)." }, "model": { "title": "Model Name", "type": "string", "description": "Specific model version (e.g., gemini-2.5-flash, gpt-4o, claude-3-5-sonnet).", "default": "gemini-2.5-flash" }, "schema": { "title": "Extraction Schema (JSON)", "type": "string", "description": "Define what to extract. Simple format: {\"Person\": {\"name\": \"string\"}}. Or full format with prompt_description and examples for better results." }, "text": { "title": "Raw Text", "type": "string", "description": "Direct unstructured text to process (Single or Batch)." }, "urls": { "title": "URLs", "type": "array", "description": "List of URLs to webpages to extract content from.", "items": { "type": "string" } }, "systemPrompt": { "title": "System Prompt / Persona", "type": "string", "description": "Custom instructions to steer the extraction (e.g., 'Act as a legal expert')." }, "batchMode": { "title": "Enable Batch Mode", "type": "boolean", "description": "Optimize for processing multiple documents in parallel.", "default": true }, "debug": { "title": "Debug Mode", "type": "boolean", "description": "Save raw prompts and responses to the Key-Value Store.", "default": false }, "trackTokens": { "title": "Track Token Usage", "type": "boolean", "description": "Report estimated costs and token usage in logs.", "default": true }, "enableOcr": { "title": "Enable OCR for Images", "type": "boolean", "description": "Use Docling OCR to extract text from images (PNG, JPG) and scanned PDFs. Slower but enables extraction from visual documents.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }