
Chunkr
Chunkr is a YC Winter 2024 (W24) company. Team of 3.
About Chunkr
Summary
Chunkr builds an open-source API that converts PDFs, Word documents, spreadsheets, presentations, and images into structured, LLM-ready data. It serves developers and B2B teams building AI applications, replacing hand-rolled document ingestion pipelines with production-grade layout analysis, OCR, semantic chunking, and vision model controls. Common workloads include retrieval-augmented generation and automating extraction from documents such as invoices and medical reports into databases.
Go-to-market
Developers adopt Chunkr through a self-serve API, integrating it directly into their AI application stacks without a sales process.
From the Y Combinator listing
Open source API service to parse complex documents
Battle-tested + highly modular vision infrastructure to convert PDFs, PPTs, Word, Excel, PNG, and JPEGs into LLM-ready data. We started by building lumina.sh - where we needed to parse ~600M pages of scientific literature. The researchers didn't care - but devs wanted our ingestion pipeline. So we built chunkr instead. We offer high quality layout analysis, OCR, bounding boxes, granular VLM controls, semantic chunking, and all the last mile engineering that goes into building standout AI applications. Common use-cases include RAG, and automating document workflows like invoices/medical reports -> database.
Facts
- B2B / B2B -> Engineering, Product and Design
- 3
- Active
- Early
Founders (3)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works