Your project is on StackMap — a curated map of the AI stack

Hi — I curate **[StackMap](https://stackmap.shipwithai.xyz?utm_source=maintainer-outreach)**, a hand-curated knowledge graph of open-source AI/agent tools. Every entry is human-reviewed: a summary, an opinionated note on when to use it (and when not), and typed edges to what it pairs with or competes against — with the *why* written down.

**olmocr** earned a place on the map:
- Your page: https://stackmap.shipwithai.xyz/repos/allenai/olmocr
- On the graph: https://stackmap.shipwithai.xyz/?focus=olmocr

How we mapped it:
- **pairs with `llamaindex`** — olmocr is the document-parsing front-end; LlamaIndex is the indexing/retrieval layer. Run messy PDFs through olmocr to get clean text, then hand that text to LlamaIndex to chunk, embed, and retrieve — a natural two-stage RAG-ingestion pipeline.
- **built with `vllm`** — olmocr runs its OCR vision-language model through a high-throughput inference backend — vLLM (or SGLang) — to batch-process PDFs at scale, so vLLM is the serving engine under olmocr's pipeline.
- **pairs with `chroma`** — olmocr's cleaned text is exactly what you embed and store for retrieval — feed its output into Chroma as the vector store behind a RAG app. Looser than the LlamaIndex pairing since any embedder/DB works, but Chroma is the natural open-source landing spot.

If any of this misrepresents the project — an edge you'd dispute, a sharper "when NOT to use" — reply here and a human fixes it. And feel free to just close this issue; it's only a heads-up.