doc-intelligence 0.1.4

Document AI - Intelligent document processing and extraction

Document AI

Documentation: https://zeel-04.github.io/doc-intelligence/

A library for parsing, formatting, and processing documents that can be used to build AI-powered document processing pipelines with structured data extraction and citation support.

Features

• Extract structured data from PDF documents using LLMs
• Automatic citation tracking with page numbers, line numbers, and bounding boxes
• Support for digital PDFs (local files and URLs)
• Type-safe data models using Pydantic
• Multi-provider LLM support: OpenAI, Anthropic, Gemini, Ollama

Installation

Requirements

• Python >= 3.10
• An API key for your chosen LLM provider (OpenAI, Anthropic, or Gemini) — or a local Ollama server

Install with uv

uv pip install doc-intelligence

Or with pip:

pip install doc-intelligence

Quick Start

Set up your API key (example with OpenAI):

echo "OPENAI_API_KEY=your-api-key-here" > .env

Here's a simple example to extract structured data from a PDF:

from dotenv import load_dotenv
from pydantic import BaseModel

from doc_intelligence import PDFProcessor

# Load environment variables
load_dotenv()

# Define your data model
class License(BaseModel):
    license_name: str

# Create a processor and extract in two lines
processor = PDFProcessor(provider="openai")
result = processor.extract(
    uri="https://example-files.online-convert.com/document/pdf/example.pdf",
    response_format=License,
    include_citations=True,
    extraction_mode="single_pass",
    model="gpt-4o-mini",
)

# Access the extracted data and citations
print(f"Extracted data: {result.data}")
print(f"Metadata: {result.metadata}")

Sample Output

The extract method returns an ExtractionResult with .data and .metadata attributes:

result.data
# License(license_name='Attribution-ShareAlike 3.0 Unported')

result.metadata
# {
#     'license_name': {
#         'value': 'Attribution-ShareAlike 3.0 Unported',
#         'citations': [{
#             'page': 0,
#             'bboxes': [{
#                 'x0': 0.201,
#                 'top': 0.859,
#                 'x1': 0.565,
#                 'bottom': 0.872
#             }]
#         }]
#     }
# }

Documentation

For more detailed documentation, see the docs directory or visit the documentation site.

Development Setup

Prerequisites:

• Python 3.10+
• uv

git clone https://github.com/zeel-04/doc-intelligence.git
cd doc_intelligence
uv venv
uv sync