OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Py Idp

Py Idp is a Python library for building intelligent document-processing workflows that parse, classify, extract, assess and validate document data, with an optional human-review stage. It uses Pydantic schemas to shape extracted fields and supports configurable LLM backends.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Py Idp — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Py Idp when building a Python application that needs a staged document pipeline and structured, validated extraction rather than a standalone document-reading tool.

Who it is for

  • Python developers building invoice, form or other document-extraction workflows.
  • Teams that need schema-shaped extraction with validation and human-review routing.
  • Developers assembling document-processing services from configurable OCR, PDF and LLM components.

Documented uses

  • Classify incoming documents and extract fields into Pydantic-defined structures.
  • Assess confidence and validate extraction results against schemas and business rules.
  • Route results for human review when needed.
  • Add OCR or PDF-processing components and expose a workflow through the optional FastAPI server.
Before you choose

Requirements & limits

The repository specifies Python 3.10 or later. Its README identifies AGPL-3.0-or-later and a commercial licensing option.

  • The core package includes a mock backend; provider integrations and several processing features are optional extras.
  • The README lists OpenAI, Anthropic, Ollama, China-provider integrations and self-hosted Nanonets-OCR2-3B OCR.
  • Optional components include Docling for PDF table extraction, Tesseract fallback for noisy scans, PDF rendering, an evaluation harness and a FastAPI server.
  • The pipeline exposes per-field confidence and validation results, with a human-review stage.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Py Idp and run the documented mock extraction

Prepare the core library and run its example extraction flow using the in-tree mock backend.

Before you start

  • Python 3.10 or later
  • A PDF or text document such as invoice.pdf or invoice.txt

Steps

  1. Install the core package with pip install py-idp.

  2. Place invoice.pdf or invoice.txt in the current directory.

  3. Run python examples/00_zero_to_extraction.py.

Expected outcome

The example prints extracted fields and provides a hint for switching to a local LLM.

Guide limitations

  • The core install uses the mock backend by default; this flow does not configure a real LLM.
  • Optional extras are needed for additional providers and features such as the FastAPI server or OCR fallback.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
rollroyces/py-idp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction