{ "openapi": "3.0.1", "info": { "title": "AI Document Summarizer and Field Extractor", "description": "Summarize web pages and text and extract typed fields like prices, dates and skills as JSON, using your own OpenAI-compatible API key.", "version": "0.2", "x-build-id": "MoI8Tt9tae4S6xZdN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sorrel_flint~ai-doc-extract/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sorrel_flint-ai-doc-extract", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sorrel_flint~ai-doc-extract/runs": { "post": { "operationId": "runs-sync-sorrel_flint-ai-doc-extract", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sorrel_flint~ai-doc-extract/run-sync": { "post": { "operationId": "run-sync-sorrel_flint-ai-doc-extract", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "Page URLs", "type": "array", "description": "Web pages to summarize, one document per URL (no crawling). robots.txt is respected and only public addresses are fetched; skipped URLs are listed in the ISSUES record and never charged.", "items": { "type": "string" } }, "documents": { "title": "Inline documents", "type": "array", "description": "Documents supplied as text instead of URLs. Each item is an object with a 'name' and a 'text' field." }, "fields": { "title": "Fields to extract", "maxItems": 30, "type": "array", "description": "Structured fields to pull out of every document, at most 30. Each item is an object: {\"name\": \"price\", \"type\": \"number\", \"description\": \"asking price in EUR\"} (description at most 120 characters). Types: string, number, boolean, string[]. Leave empty to get only a summary." }, "instructions": { "title": "Instructions", "maxLength": 500, "type": "string", "description": "What the summary should focus on (at most 500 characters). Leave empty for a neutral summary of the whole document.", "default": "" }, "summaryLength": { "title": "Summary length", "enum": [ "short", "medium", "long", "none" ], "type": "string", "description": "How long the summary should be.", "default": "medium" }, "outputLanguage": { "title": "Output language", "maxLength": 40, "type": "string", "description": "Language of the summary, for example 'English' or 'Danish'. Leave empty to keep the language of the document.", "default": "" }, "openaiApiKey": { "title": "Your OpenAI-compatible API key", "type": "string", "description": "Your OpenAI key, or a key for any OpenAI-compatible service (set its URL below). Your provider bills you for the model directly; this Actor charges 0.01 USD per processed document. Without a key the run is a preview of the first 3 documents with placeholder values, which costs only the 0.005 USD start fee. Stored encrypted, never written to the output or log." }, "model": { "title": "Model", "type": "string", "description": "A model your key can use and that can answer in JSON. OpenAI: gpt-4o-mini (fast, cheap) or gpt-4o. OpenRouter: its ids, for example openai/gpt-4o-mini.", "default": "gpt-4o-mini" }, "openaiBaseUrl": { "title": "OpenAI-compatible base URL (optional)", "type": "string", "description": "Leave empty for OpenAI. For another OpenAI-compatible service, its Chat Completions base URL, for example https://openrouter.ai/api/v1.", "default": "" }, "maxCharsPerDocument": { "title": "Max characters per document", "minimum": 1000, "maximum": 400000, "type": "integer", "description": "Text beyond this many characters is cut off (the row says truncated: true). Long documents are processed in parts and the part results are merged; longer documents mean more model calls on your provider's bill.", "default": 40000 }, "testMode": { "title": "Test mode (free, no model call)", "type": "boolean", "description": "Run the whole pipeline on up to 10 documents with placeholder values instead of a model call; no document is charged. Use it to check your field definitions first. Runs without a key are a preview like this automatically (first 3 documents).", "default": false } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }