Evidence-First PDF Table Extractor
Pricing
from $10.00 / 1,000 document processeds
Extract PDF tables to CSV and JSON with page and bounding-box provenance, OCR fallback, and explicit quality flags.
Pricing
from $10.00 / 1,000 document processeds
Rating
0.0
(0)
Developer
Defenestrator
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Share
You can access the Evidence-First PDF Table Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "pCVl1eGQvyE8yVMPL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/defenestrator~evidence-first-pdf-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-defenestrator-evidence-first-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/defenestrator~evidence-first-pdf-table-extractor/runs": { "post": { "operationId": "runs-sync-defenestrator-evidence-first-pdf-table-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/defenestrator~evidence-first-pdf-table-extractor/run-sync": { "post": { "operationId": "run-sync-defenestrator-evidence-first-pdf-table-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": [ "pdfSources" ], "properties": { "pdfSources": { "title": "PDF files or URLs", "minItems": 1, "maxItems": 10, "type": "array", "description": "Upload PDF files or provide public HTTP/HTTPS PDF URLs. Private, loopback, link-local, and cloud-metadata destinations are blocked.", "items": { "type": "string", "minLength": 8, "maxLength": 4096 } }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto OCRs bitmap regions while retaining embedded PDF text. Always forces full-page OCR. Never disables OCR. OCR table extraction is beta and every OCR-derived table is flagged for review. Effective OCR is limited to three selected pages per document; split longer scans or set the page limit to 3 or less.", "default": "auto" }, "tableMode": { "title": "Table quality mode", "enum": [ "fast", "accurate" ], "type": "string", "description": "Fast is the cost-controlled default. Accurate can improve complex/grouped headers but takes materially longer.", "default": "fast" }, "maxDocuments": { "title": "Maximum documents", "minimum": 1, "maximum": 10, "type": "integer", "description": "Hard run cap. Extra supplied documents are not processed.", "default": 10 }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 200, "type": "integer", "description": "Processing stops at this page limit for each PDF. If OCR is effective, this value must be 3 or less; digital PDFs with OCR skipped can use the full range.", "default": 50 }, "maxFileSizeMb": { "title": "Maximum PDF size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Download and conversion safety limit per PDF.", "default": 25 }, "downloadTimeoutSeconds": { "title": "PDF download deadline", "minimum": 15, "maximum": 120, "type": "integer", "description": "Absolute DNS, connection, redirect, and body download deadline per PDF.", "default": 60 }, "documentTimeoutSeconds": { "title": "Per-document conversion deadline", "minimum": 30, "maximum": 600, "type": "integer", "description": "Hard wall-clock deadline for the isolated Docling process. PDF preflight is separately isolated and capped at the lesser of 30 seconds or this value.", "default": 180 }, "conversionMemoryLimitMb": { "title": "Supervised process-tree RSS ceiling (MB)", "minimum": 1024, "maximum": 6144, "type": "integer", "description": "PDF preflight and Docling process-tree RSS are sampled every 250 ms and the process group is killed on an observed breach. This is not a kernel/cgroup hard cap. The value must fit within allocated Actor memory while leaving a 768 MB parent-process reserve.", "default": 3072 }, "saveDocumentMarkdown": { "title": "Save document Markdown", "type": "boolean", "description": "Save a bounded full-document Markdown export in the default key-value store.", "default": true }, "failRunOnDocumentError": { "title": "Fail run when any document fails", "type": "boolean", "description": "Normally each failed PDF produces an explicit error row and the remaining PDFs continue.", "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 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Evidence-First PDF Table Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: