> ## Documentation Index
> Fetch the complete documentation index at: https://vecgrep.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Acknowledgements

> Credits and citations

## Embedding model

The default embedding model used by VecGrep is [`all-MiniLM-L6-v2-code-search-512`](https://huggingface.co/isuruwijesiri/all-MiniLM-L6-v2-code-search-512), a model fine-tuned specifically for semantic code search by [@isuruwijesiri](https://huggingface.co/isuruwijesiri).

```bibtex theme={null}
@misc{all_MiniLM_L6_v2_code_search_512,
  author    = {isuruwijesiri},
  title     = {all-MiniLM-L6-v2-code-search-512},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/isuruwijesiri/all-MiniLM-L6-v2-code-search-512}
}
```

## Libraries

* [fastembed](https://github.com/qdrant/fastembed) — ONNX Runtime-based embedding (default backend)
* [sentence-transformers](https://www.sbert.net/) — PyTorch embedding backend
* [LanceDB](https://lancedb.github.io/lancedb/) — vector store
* [tree-sitter](https://tree-sitter.github.io/tree-sitter/) — AST-based code chunking
* [MCP](https://modelcontextprotocol.io/) — Model Context Protocol