Data, search & knowledge

Document processing & OCR

1,074 agents · most starred first

Document processing & OCR, page 8 of 11

llama-index-readers-boarddocs

llama-index readers boarddocs integration

llama-index-readers-box

llama-index readers box integration

llama-index-readers-cvfile

LlamaIndex reader for the .cv open file format.

llama-index-readers-docdigitizer

LlamaIndex reader for the DocDigitizer document processing API

llama-index-readers-docling

llama-index readers docling integration

llama-index-readers-docugami

llama-index readers docugami integration

llama-index-readers-feishu-docs

llama-index readers feishu_docs integration

llama-index-readers-feishu-wiki

llama-index readers feishu_wiki integration

llama-index-readers-file

llama-index readers file integration

llama-index-readers-firebase-realtimedb

llama-index readers firebase_realtimedb integration

llama-index-readers-firestore

llama-index readers firestore integration

llama-index-readers-gcs

llama-index readers gcs integration

llama-index-readers-genius

llama-index readers genius integration

llama-index-readers-gitbook

llama-index readers gitbook integration

llama-index-readers-google

llama-index readers google integration

llama-index-readers-graphql

llama-index readers graphql integration

llama-index-readers-guru

llama-index readers guru integration

llama-index-readers-hatena-blog

llama-index readers hatena_blog integration

llama-index-readers-huggingface-fs

llama-index readers huggingface fs integration

llama-index-readers-hwp

llama-index readers hwp integration

llama-index-readers-imdb-review

llama-index readers imdb_review integration

llama-index-readers-jaguar

llama-index readers jaguar integration

llama-index-readers-json

llama-index readers json integration

llama-index-readers-kaltura-esearch

llama-index readers kaltura e-search integration

llama-index-readers-kreuzberg

LlamaIndex reader for 88+ document formats powered by kreuzberg's Rust extraction engine

llama-index-readers-layoutir

llama-index readers LayoutIR integration

llama-index-readers-legacy-office

LlamaIndex Legacy Office Reader, handles .doc files loading with Apache Tika

llama-index-readers-lilac

llama-index readers lilac integration

llama-index-readers-llama-parse

llama-index readers llama-parse integration

llama-index-readers-macrometa-gdn

llama-index readers macrometa_gdn integration

llama-index-readers-mangadex

llama-index readers mangadex integration

llama-index-readers-mangoapps-guides

llama-index readers mangoapps_guides integration

llama-index-readers-maps

llama-index readers maps integration

llama-index-readers-markitdown

llama-index readers MarkItDown integration

llama-index-readers-mbox

llama-index readers mbox integration

llama-index-readers-memos

llama-index readers memos integration

llama-index-readers-metal

llama-index readers metal integration

llama-index-readers-microsoft-onedrive

llama-index readers microsoft_onedrive integration

llama-index-readers-microsoft-outlook

llama-index readers microsoft outlook integration

llama-index-readers-microsoft-outlook-emails

llama-index readers microsoft_outlook_emails integration

llama-index-readers-microsoft-sharepoint

llama-index readers microsoft_sharepoint integration

llama-index-readers-mineru

llama-index readers MinerU integration — parse PDF/Doc/PPT/images into Markdown via MinerU API

llama-index-readers-minio

llama-index readers minio integration

llama-index-readers-nougat-ocr

llama-index readers nougat_ocr integration

llama-index-readers-openapi

llama-index readers openapi integration

llama-index-readers-opendal

Project by kotko

llama-index-readers-opendal-reader

llama-index readers opendal_reader integration

llama-index-readers-oxidize-pdf

LlamaIndex reader for oxidize-pdf — fast, Rust-powered PDF parsing with element-disjoint RAG chunking

llama-index-readers-paddle-ocr

llama-index readers paddle_ocr integration

llama-index-readers-pdf-marker

llama-index readers marker integration

llama-index-readers-pdf-table

llama-index readers pdf_table integration

llama-index-readers-pdfmux

llama-index readers pdfmux integration

llama-index-readers-preprocess

llama-index readers preprocess integration (discontinued)

llama-index-readers-smart-pdf-loader

llama-index readers smart_pdf_loader integration

llama-index-readers-upstage

llama-index readers upstage integration

llama-index-readers-whisper

llama-index readers openai whisper integration

llama-index-readers-youtube-transcript

llama-index readers youtube transcript integration

llama-index-sl

llama_index edited for unicode support and pdfminer.six

llama-ocr

OCR using LLAMA vision model, allowing configuring any OpenAI compliant endpoints and model names.

llama-ocr-py

A package for document extraction using Ollama Vision model

llama-parse

Parse files into RAG-Optimized formats.

llama-parser

Parse files into RAG-Optimized formats.

llama-scan

A tool for converting PDFs to text files using Ollama.

llamarker

A universal GenAI-based local parser for complex documents of all types.

llamasearch-pdf-llamasearch

A comprehensive PDF processing toolkit for document workflows

llm-ctx

Create an LLM XML context document from an llms.txt file

llm-data-converter

Best open-source document to markdown converter for LLM training data. Convert PDF, Word, PowerPoint, Excel, images, URLs to clean markdown, JSON, HTML locally. Alternative to Unstructured, Docling, Marker, MarkItDown, MinerU, PaddleOCR, Tesseract

llm-document-analysis

A Python library for LLM-powered document analysis and processing

llm-documentcloud

LLM integrations for DocumentCloud

llm-extractinator

A framework that enables efficient extraction of structured data from unstructured text using large language models (LLMs).

llm-extractor

Extract structured, validated JSON from any LLM — OpenAI, Anthropic, Gemini — with batch extraction, caching, per-field confidence scoring, schema evolution, multi-schema extraction, output transforms, partial extraction, extraction diff, pipeline extraction, and smart auto-retry.

llm-file-format

Token-efficient data format converter for LLM contexts

llm-fragments-dir

Load files from a local directory as fragments

llm-fragments-doc

Load documents as fragments

llm-fragments-folder

LLM plugin to load entire folder contents as fragments

llm-fragments-markitdown

LLM fragment loader which converts various formats to Markdown.

llm-fragments-pdf

Use PyMuPDF to insert PDFs as markdown

llm-fragments-pypi

LLM fragments plugin for PyPI packages metadata

llm-fragments-us-legislation

Load bills from Congress.gov as LLM fragments

llm-fragments-youtube

LLM plugin for loading YouTube subtitles as fragments

llm-fragments-youtube-transcript

Fetch youtube transcripts and convert them into plaintext for llm consumption.

llm-gemini-youtube

LLM plugin for agentic YouTube video understanding with Gemini

llm-html

LLM-optimized HTML cleaning: hydration extraction, token budgets, multiple output formats

llm-ie

A comprehensive toolkit that provides building blocks for LLM-based named entity recognition, attribute extraction, and relation extraction pipelines.

llm-markdownify

Convert PDFs, images to high-quality Markdown using Vision LLMs.

llm-metadata-harvester

A tool for harvesting metadata from dataset landing pages using Large Language Models.

llm-ner

Schema-driven Named Entity Recognition powered by local LLMs via Ollama

llm-output-parser

Extract and parse JSON from unstructured text outputs from LLMs

llm-parse

Parse data from documents optimised for downstream llm tasks.

llm-parse-json

A simple JSON parsing tool that preprocesses and parses JSON strings.

llm-pdf-chunker

LLM-friendly PDF splitter & image optimizer. Chunk PDFs by size and downsample images for RAG/Bedrock.

llm-pdf-to-images

LLM fragment plugin to load a PDF as a sequence of images

llm-platform-ocr

ocr library

llm-plugin-pdf

LLM plugin for loading text from PDF files (local or URL)

llm-text-splitter

A lightweight, rule-based text splitter for LLM context window management, handles multiple file formats and enriches chunks with metadata.

llm-to-json

Tiny wrapper exposing Prompture helpers to convert LLM output into JSON.

llm-to-toon

Tiny wrapper exposing Prompture helpers to convert LLM output into TOON.

llm-youtube

LLM plugin for pulling content from Youtube videos

llm-youtube-transcript

Plugin for LLM that adds support for fetching transcripts from YouTube videos using Supadata API

llm-yt-transcript

A LLM plugin for YouTube transcripts as fragments

More in Data, search & knowledge