Document processing & OCR
1,074 agents · most starred first
Document processing & OCR, page 7 of 11
Support for many storage backends in Django
A Django Model based file storage.
Dead simple document extraction OCR powered by LLMs
A python library to simplify agentic operations on documents, such as writing, editing, summarizing, extracting, and enriching.
Haystack integration for docling
Docling LangChain integration
Docling plugin for LiteLLM picture description
Haystack converter component for DoclingServe — document conversion via HTTP
Deep storage auditing for Google Drive — part of the Docto Trace suite.
Read CSV - Version Test
Protocol Parser for Dr. Storage Dry Air Cabinets
The *dspyce* package helps to communicate with dspace interfaces. Currently saf (Simple Archive Format) packages and the RestAPI are supported.
CLI tool for converting PDF documents to Markdown or HTML using Mistral OCR.
A storage provider which can fetch and store media in Amazon S3.
Convert equation-heavy Word documents (.docx) to Markdown with LaTeX math for LLM recognition.
Add your description here
A fast PDF to Markdown converter optimized for LLM processing
examine fragments of files in the filesystem
A tool to convert folder structures and file contents into markdown for LLMs
A simple tool to extract data from PDFs and images using Google's gemini-2.0-flash-001 model.
Hybrid OCR with gemini and DocumentAI
CLI tool for OCR processing using Google Gemini's vision capabilities
A Python library for processing documents with the Gemini API
This package contains implementation of a PDF file analyser with Google Gemini AI integrated into it.
Extract structured data from receipt images using Gemini AI
A tool that uses the Gemini API to convert files into structured JSON.
Convert Google Gemini chats to Markdown
This package contains implementation of a ".txt" file analyser with Google Gemini AI integrated into it.
A library for orchestrating the processing of document. Typically in a Gen AI applications (but not limited to just Gen AI).
A Python package that utilizes GPT-4V and other tools to convert PDFs into Markdown files.
A Python package that utilizes GPT-4V and other tools to extract and process information from PDF files
General Purpose Tagger using GPT
A tool for converting PDF documents to Markdown using OCR and vision language models
Using GPT to parse PDF
Using GPT to parse PDF files and generate LaTeX code.
A Python SDK for graph document processing
Input document loading utilities for GraphRAG
An integration of Han Language Processing - HanLP as a ChineseDocumentSplitter component.
Haystack converter for oxidize-pdf — fast, Rust-powered PDF parsing with element-disjoint RAG chunking, ByteStream-aware
Utilities to read/write Python types to/from HDF5 files, including MATLAB v7.3 MAT files.
LlamaSearch AI Package
LlamaSearch AI Package
Generate HTR from IIIF Resources
Data Section
Defines the JekyllMarkdownExporter class.
JSON repair using multiple backends: LLMs and FSM-based processing with Pydantic models
Repair broken JSON from LLM outputs
using LLM to extract keywords
Kreuzberg document extraction tool for CrewAI agents
Kreuzberg document converter for Haystack
Kreuzberg document extraction pipeline for txtai and other callable-based frameworks
An integration package connecting Box and LangChain
LangChain document loader for the .cv open file format.
LangChain document loader for the DocDigitizer document processing API
Docling LangChain integration
This is a more advanced integration of Google Drive with langchain.
LangChain integration for HighSNR — compress documents to a token budget, keeping the highest-signal content.
LangChain document loaders for HWP/HWPX using hwp-hwpx-parser
A LangChain integration for jostack-mdparse
Kreuzberg document loader for LangChain — extract text from 88+ file formats with true async and rich metadata
LangChain helpers for working with Logseq documents
LangChain data loaders based on Markdown by @untrueaxioms.
LangChain document loader powered by MinerU — turn PDFs into Markdown
Modular, vision-LLM-powered chain to convert image and PDF documents into clean Markdown.
A LangChain integration for OpenDataLoader PDF
LangChain document loader for oxidize-pdf — fast, Rust-powered PDF parsing with element-disjoint RAG chunking
An integration package connecting PaddleOCR and LangChain
Generate clean, readable PDFs from raw text or LLM output
LangChain document loader for pdfmux — self-healing PDF extraction
An integration package connecting PyMuPDF Layout to LangChain. Load PDF content to Markdown using AI-based, CPU only, layout analysis.
An integration package connecting PyMuPDF4LLM to LangChain
s3 loaders for simple text files
ServiceNow document loaders for LangChain - sync and async loaders for Incidents, CMDB, KB, Changes, Problems, Catalog, and Attachments.
LangChain integration package for Synap DocuAnalyzer.
A LangChain tool for parsing documents using Tensorlake's DocumentAI.
LangChain text splitting utilities
Community contributed LangChain integrations.
LangChain Document Loader for UnDatasIO
An integration package connecting Unstructured and LangChain
LangChain integration with xParse Parse API for intelligent document parsing
YouTube loader for LangChain using yt-dlp
Flatten and clean LaTeX projects, and extract PowerPoint decks with their equations, for LLM consumption
A practical tool for converting PDF to Markdown
A comprehensive document and web page conversion toolkit powered by Llama AI
Project by kotko
llama-index node_parser alibabacloud_aisearch integration
llama-index Chonkie integration
llama-index node_parser dashscope integration
llama-index node_parser dashscope integration
llama-index node_parser docling integration
Element-aware LlamaIndex node parser for kreuzberg-extracted documents
llama-index node_parser relational dashscope integration
llama-index node_parser slide node parser integration
llama-index node_parser topic node parser integration
llama-index packs node_parser integration
llama-index packs node_parser integration
llama-index readers azstorage_blob integration