document-extraction

Name: document-extraction
Author: landing-ai

58stars14forks

How to install document-extraction?

landing-ai/ade-document-processing-skills/document-extraction

$npx -y skills add landing-ai/ade-document-processing-skills --skill document-extraction

Installs into the current project.

Summary

Parses, extracts, and classifies documents using LandingAI's Agentic Document Extraction (ADE). Supports PDFs, images, spreadsheets, and presentations; outputs structured Markdown with hierarchical JSON. Covers schema-based field extraction (JSON Schema or Pydantic), document cla

Files · 1

View on GitHub

SKILL.md

1	# Document Extraction (ADE)
2
3	## Overview
4
5	LandingAI's Agentic Document Extraction (ADE) is a document processing SaaS that parses, extracts, and classifies documents without requiring templates or training. The `landingai-ade` Python library is the recommended approach for most use cases. It wraps the REST API and handles authentication and response parsing for you.
6
7	ADE provides these core API functions:
8
9	\| API \| Python Method \| What It Does \|
10	\|-----\|--------------\|--------------\|
11	\| Parse \| `client.parse()` \| Converts documents into structured Markdown, chunks, and metadata. Always the first step. \|
12	\| Extract \| `client.extract()` \| Pulls specific fields from Markdown using a JSON schema. \|
13	\| Build Extract Schema \| `client.extract_build_schema()` \| Generates or refines a JSON extraction schema from Markdown using AI. \|
14	\| Split \| `client.split()` \| Classifies and separates multi-document batches by document type. \|
15	\| Classify \| `client.classify()` \| Classifies each page in a document by type. Use to route pages before parsing. (Preview) \|
16	\| Section \| `client.section()` \| Generates a hierarchical table of contents from parsed Markdown. (Preview) \|
17	\| Parse Jobs (Create) \| `client.parse_jobs.create()` \| Creates an async parse job for large files (up to 6,000 pages). \|
18	\| Parse Jobs (Get) \| `client.parse_jobs.get()` \| Retrieves the status and results of an async parse job. \|
19	\| Parse Jobs (List) \| `client.parse_jobs.list()` \| Lists all async parse jobs with optional status filtering. \|
20	\| Extract Jobs (Create) \| REST API (no SDK method) \| Creates an async extract job for long documents or large, complex schemas. \|
21	\| Extract Jobs (Get) \| REST API (no SDK method) \| Retrieves the status and results of an async extract job. \|
22	\| Extract Jobs (List) \| REST API (no SDK method) \| Lists all async extract jobs with optional status filtering. \|
23
24	Key Benefits:
25	- No ML training or templates required
26	- Layout-agnostic parsing (works with any document structure)
27	- Supports 20+ file formats (PDF, images, spreadsheets, presentations)
28	- Precise visual grounding (bounding boxes, page numbers)
29	- Multiple models optimized for different document types
30
31	## Quick Start
32
33	### 1. Installation
34
35	Never install packages globally without user approval. Always check for a local Python environment first.
36
37	```
38	1. .venv/bin/python : uv-managed (this project)
39	2. venv/bin/python : standard Python venv
40	3. uv run python : if pyproject.toml exists
41	4. poetry run python : if poetry.lock exists
42	5. python3 : system fallback; warn the user
43	```
44	Use the local environment to install: `landingai-ade`, `python-dotenv`
45
46	### 2. API Key Setup
47
48	The user may have already setup a `.env` file in the same directory as the `document-extraction` skill with the API key. You MUST check this path first (ls -la .*/skills/document-extraction/.env). Also try checking on the same directory as this SKILL.md file.
49
50	If not, provide instructions to create one. The script below will search for `.env` in common locations and load it.
51
52	```bash
53	.venv/bin/python - << 'EOF'
54	import os
55	from pathlib import Path
56	from dotenv import load_dotenv
57
58	# Load API key: prefer existing env var, then .env file lookup
59	if os.environ.get("VISION_AGENT_API_KEY"):
60	print("API key found in existing environment variable")
61	else:
62	def _find_env():
63	for d in [Path.cwd().resolve(), *Path.cwd().resolve().parents]:
64	for candidate in [
65	# ADD the directory where the document-extraction skill is located
66	d / '.env',
67	d / 'document-extraction/.env',
68	d / 'skills/document-extraction/.env',
69	]:
70	if candidate.is_file():
71	return candidate
72	return None
73	env = _find_env()
74	if env:
75	load_dotenv(env)
76	print(f"API key loaded from: {env}")
77	else:

People who liked this also viewed

6 picks

Type

document-extraction

58stars14forks

View on GitHub

How to install document-extraction?

landing-ai/ade-document-processing-skills/document-extraction

$npx -y skills add landing-ai/ade-document-processing-skills --skill document-extraction

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Document Extraction (ADE)
2
3	## Overview
4
5	LandingAI's Agentic Document Extraction (ADE) is a document processing SaaS that parses, extracts, and classifies documents without requiring templates or training. The `landingai-ade` Python library is the recommended approach for most use cases. It wraps the REST API and handles authentication and response parsing for you.
6
7	ADE provides these core API functions:
8
9	\| API \| Python Method \| What It Does \|
10	\|-----\|--------------\|--------------\|
11	\| Parse \| `client.parse()` \| Converts documents into structured Markdown, chunks, and metadata. Always the first step. \|
12	\| Extract \| `client.extract()` \| Pulls specific fields from Markdown using a JSON schema. \|
13	\| Build Extract Schema \| `client.extract_build_schema()` \| Generates or refines a JSON extraction schema from Markdown using AI. \|
14	\| Split \| `client.split()` \| Classifies and separates multi-document batches by document type. \|
15	\| Classify \| `client.classify()` \| Classifies each page in a document by type. Use to route pages before parsing. (Preview) \|
16	\| Section \| `client.section()` \| Generates a hierarchical table of contents from parsed Markdown. (Preview) \|
17	\| Parse Jobs (Create) \| `client.parse_jobs.create()` \| Creates an async parse job for large files (up to 6,000 pages). \|
18	\| Parse Jobs (Get) \| `client.parse_jobs.get()` \| Retrieves the status and results of an async parse job. \|
19	\| Parse Jobs (List) \| `client.parse_jobs.list()` \| Lists all async parse jobs with optional status filtering. \|
20	\| Extract Jobs (Create) \| REST API (no SDK method) \| Creates an async extract job for long documents or large, complex schemas. \|
21	\| Extract Jobs (Get) \| REST API (no SDK method) \| Retrieves the status and results of an async extract job. \|
22	\| Extract Jobs (List) \| REST API (no SDK method) \| Lists all async extract jobs with optional status filtering. \|
23
24	Key Benefits:
25	- No ML training or templates required
26	- Layout-agnostic parsing (works with any document structure)
27	- Supports 20+ file formats (PDF, images, spreadsheets, presentations)
28	- Precise visual grounding (bounding boxes, page numbers)
29	- Multiple models optimized for different document types
30
31	## Quick Start
32
33	### 1. Installation
34
35	Never install packages globally without user approval. Always check for a local Python environment first.
36
37	```
38	1. .venv/bin/python : uv-managed (this project)
39	2. venv/bin/python : standard Python venv
40	3. uv run python : if pyproject.toml exists
41	4. poetry run python : if poetry.lock exists
42	5. python3 : system fallback; warn the user
43	```
44	Use the local environment to install: `landingai-ade`, `python-dotenv`
45
46	### 2. API Key Setup
47
48	The user may have already setup a `.env` file in the same directory as the `document-extraction` skill with the API key. You MUST check this path first (ls -la .*/skills/document-extraction/.env). Also try checking on the same directory as this SKILL.md file.
49
50	If not, provide instructions to create one. The script below will search for `.env` in common locations and load it.
51
52	```bash
53	.venv/bin/python - << 'EOF'
54	import os
55	from pathlib import Path
56	from dotenv import load_dotenv
57
58	# Load API key: prefer existing env var, then .env file lookup
59	if os.environ.get("VISION_AGENT_API_KEY"):
60	print("API key found in existing environment variable")
61	else:
62	def _find_env():
63	for d in [Path.cwd().resolve(), *Path.cwd().resolve().parents]:
64	for candidate in [
65	# ADD the directory where the document-extraction skill is located
66	d / '.env',
67	d / 'document-extraction/.env',
68	d / 'skills/document-extraction/.env',
69	]:
70	if candidate.is_file():
71	return candidate
72	return None
73	env = _find_env()
74	if env:
75	load_dotenv(env)
76	print(f"API key loaded from: {env}")
77	else:

People who liked this also viewed

6 picks

Type