Data, search & knowledge

Document processing & OCR

1,074 agents · most starred first

Document processing & OCR, page 9 of 11

llm_etl_pipeline

LLM extraction from documents

llmatch-struct-parser

A new package designed to enhance structured text processing by leveraging the capabilities of llmatch-messages. This package will take user-provided text as input and return a well-organized, structu

llmdocparser

Using LLM to parse PDF and get better chunk for retrieval

llmextract

A library to extract structured information from unstructured text using LLMs, powered by LangChain.

llmind-cli

Embed signed semantic-metadata layers into images, PDFs, and audio files

llmmd2pdf

A Shiny app to convert LLM Markdown exports to PDF with Quarto

llms-txt-rs

Module for parsing llms.txt files

llmsherpa

Strategic APIs to Accelerate LLM Use Cases

llmstruct

A Python library for reliably extracting structured JSON from text and validating it with Pydantic models.

llmwhisperer-client

Client library for LLM Whisperer

markit-mistral

PDF and image to markdown converter using Mistral AI OCR

markitdown-advanced-pdf-llm-plugin

3-rd party plugin for markitdown library. It is to be used for converting a pdf to markdown purely based on llm's capability

markitdown-haystack

Haystack integration for MarkItDown — Microsoft's multi-format to Markdown converter

md2gemini

Convert Markdown to the Gemini text format

md4llm

Add your description here

mediagram-llm

LLM file processing tool plugin for mediagram

meshagent-markitdown

Markitdown support for Meshagent

mini-document-storage

Fast, inexpensive document storage backed by a standard database connector.

mistral-ai-ocr
mistral-ocr

A tool for OCR using Mistral. Ensure your MISTRAL_API_KEY is exported or in ~/.zshrc or ~/.bashrc

mistral-ocr-cli

A clean command-line tool for OCR processing using Mistral AI's API

mistral-ocr-gui

A graphical user interface for processing images with the Mistral OCR API.

mistral-ocr-parser

A library for parsing PDF documents using Mistral's OCR API

mistral-ocr-pdf

CLI tool to convert PDFs to markdown using Mistral OCR

mistral-ocr-tool

A simple CLI to extract text from documents using the Mistral OCR API.

mistral-pdf-to-markdown

A CLI tool to convert PDF files to Markdown using the Mistral AI OCR API.

mistral-pdf2txt

一个精悍的 PDF OCR 处理 Python 包,使用 Mistral AI OCR API

morphllm

Modular AI subagents for document processing - DOCX editing, PDF filling, and more

mseep-mcp-mistral-ocr

MCP Server for OCR processing using Mistral AI

nb4llm

Convert Jupyter notebooks to/from text format for LLM processing

ndstorage

N-dimensional, multiresolution file format for Micro-Manager

ner-agent

A simple NER agent

notte-llm

LLM-based structured data extraction for Notte sessions

nti.contentfragments

NTI ContentFragments

ocr-llm

Convert PDFs and images to markdown using Large Language Models (LLMs) with vision capabilities

ocragent

Agentic image/PDF/docs digitalization. Router for all your OCRs/VLMs/text-extractors.

odspy

LibreOffice spreadsheet parsing library

ollama-ocr

OCR package using Ollama vision language models.

ollamaocr-python

ollamaocr with Llama vision

ontogpt

OntoGPT is a Python package for extracting structured information from text with large language models (LLMs), instruction prompts, and ontology-based grounding.

opendataloader-pdf-llamaindex

LlamaIndex reader for OpenDataLoader PDF — fast, accurate, local PDF extraction

paddleocr-haystack

An integration of PaddleOCR with Haystack

paper2mdviallm

LLM-native academic PDF to Obsidian Markdown converter.

paragraph2actions

Extraction of actions from experimental procedures

parsedat-bedrock

Lightweight Little-Endian NBT -> JSON CLI utility for Minecraft Bedrock level.dat files

patentgpt-extract

A package for downloading and analysisng us patents.

pdf-agent-kit

Extract structured JSON from PDFs via CLI, Python API, or MCP server.

pdf-autofillr-rag

Self-learning RAG field prediction SDK for PDF form filling.

pdf-gpt4-json

Use GTP4-Vision as a better than OCR data extractor

pdf-llm-tools

A family of LLM-enhanced PDF utilities

pdf-to-markdown-llm

This project contains a command line tool to convert PDF to markdown. It uses image conversion and a LLM to convert the images to markdown.

pdf-to-md-llm

Library and CLI to convert PDF documents to clean, well-structured Markdown using LLM-assisted processing, leveraging Antrhopic and OpenAI models for intelligent extraction of text, tables, and complex layouts.

pdf2llm

Extract PDF content optimized for Large Language Model (LLM) consumption

pdf2markdown4llm

A library to convert PDF files to Markdown format.

pdf2md-claude

Convert PDF documents to Markdown using Claude's native PDF API

pdf2md-llm

A package to convert PDF files to Markdown using a local LLM.

pdf2text-agent

A Python tool to extract text from various PDF types using direct extraction and OCR, with built-in memory management.

pdfgpt-llm

Compiles all readable files into a single PDF for easy sharing with LLMs.

pdfgptlib

Extract PDF contents with the magic of GPT.

pealkoGPT

This is the simplest module for quick work with files.

pg-lo-storage

Use PostgreSQL large objects for file storage

power5p-ocr-gpt

PYPI tutorial package by power5p

preprocess-kgptalkie

This is a text preprocessing package

pyconverters-mistralocr

Convert PDF to structured text using MistralOCR

pymupdf4llm
pymupdf4llm-c

[DEPRECATED] wrapper for fibrumpdf (a fast PDF extractor)

pymupdf4llm-kuberlab

PyMuPDF Utilities for LLM/RAG

pyxmlfrag

Combined tree/event based XML parser

questionnaire-mistral
quillmark

Python bindings for Quillmark - a schema-driven document framework

rag-chunk

CLI tool to parse, chunk, and evaluate Markdown documents for RAG pipelines with token-accurate chunking support

rag-document-viewer

RAG Document Viewer

rag-pdf-highlighter

Highlight text chunks in PDFs – a FastAPI microservice for RAG pipelines

rag-prep

A minimal, extensible framework for preparing documents for RAG/LLM workflows

rag-scrubber

Auto-removes headers, footers, and noise from PDF text for RAG apps.

rag-utils-naveen

A simple utility to read and display markdown in notebooks.

ragchunker

A lightweight RAG chunking and preprocessing library

ragctl

ragctl - Production-ready RAG toolkit with advanced OCR, semantic chunking, and intelligent document processing

ragloader

A tool for uploading and embedding documents for RAG systems

ragparser

A comprehensive document parser for RAG applications with support for PDF, DOCX, PPTX, XLSX, and more

ragtab

Table extraction from images to Markdown for RAG systems

ragtable-extract

PDF table extraction for RAG and LLM — convert PDF tables to clean HTML. Fast, local, no GPU. Handles merged cells, line-wrapped text, no serialization.

refinire-rag-docling

Docling plugin for refinire-rag to read various document formats

rossum-agent

AI agent toolkit for Rossum: document workflows conversationally, debug pipelines automatically, and enable agentic configuration of intelligent document processing.

rossum-agent-client

Python client for Rossum Agent API - AI-powered document processing assistant

screenplay-to-json-openai

A tool to a screenplay PDF to JSON format using OpenAI Vision Transformer Analysis.

semantic-chunker-langchain

Token-aware, LangChain-compatible semantic chunker with PDF and layout support

sinapsis-langchain-readers

Package that provides support for Langchain community data loaders.

sinapsis-langchain-splitters

Package that provides support for Langchain splitters module.

smart-llm-loader

A powerful PDF processing toolkit that seamlessly integrates with LLMs for intelligent document chunking and RAG applications. Features smart context-aware segmentation, multi-LLM support, and optimized content extraction for enhanced RAG performance.

smartchunkllm

Advanced Legal Document Semantic Chunking System

smellman-mbutil

An importer and exporter for MBTiles

spharagusnet

Neural document OCR for Chilean territorial planning documents

sphinx-paragraph-extractor

A builder for Sphinx to extract paragraphs from docs.

split-markdown4gpt

Split large Markdown files into token-bounded chunks for LLM context windows

stirlingpdf-agent

Agent package for communicating with Stirling PDF via REST APIs.

structure-llm

Data structuring with LLM

structx-llm

Structured data extraction from text using LLMs and dynamic model generation

supadata-langchain

Supadata document loader integration for LangChain (Python)

swarmauri_llm_pytesseractimg2text

Swarmauri Tesseract Image to Text Model

More in Data, search & knowledge