A small Microsoft utility that converts PDF, Word, PowerPoint, Excel and other files into Markdown that is easy to hand to a language model.
All repositories
RAG & vector DBsstanford-futuredata
ColBERT
A retrieval model that compares query and document token by token instead of with a single vector. That gives higher accuracy while searching large collections in tens of milliseconds.
Who it is for
For people who hit the quality ceiling of plain vector search and are ready to dig deeper.
How to start
- Install:
pip install colbert-ai[torch,faiss-gpu](if it fails, create the environment:conda env create -f conda_env.yml). - Download the pretrained ColBERTv2 checkpoint linked in the README.
- Index a collection with
Indexer, then search withSearcherfollowing the README example.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+20Sep 6 — Oct 3
Author's description
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
More in «RAG & vector DBs»
A service that turns any website into clean Markdown or structured data for models. It can search, scrape, crawl a whole site and even click through a page.
A ready-made RAG engine with a UI: it parses documents with templates, chunks them, searches with citations and supports agentic retrieval. Deploys with Docker.
An open-source Python crawler: it visits pages with a real browser and returns clean Markdown for LLMs. Runs locally, in Docker or as a cloud service.
Parses complex PDFs, scans and Office files into Markdown or JSON while keeping tables and formulas. Comes with a CLI, a Python SDK and an agent skill.
An IBM library for document parsing: PDF, Office, HTML and images become one unified structure from which Markdown is easy to get. Supports vision models for hard pages.