Menu
Set up the embedding model for semantic search. model2vec-rs downloads models automatically; use when build fails or model download issues occur.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Work with the SQLite database layer including FTS5, sqlite-vec, and schema operations. Use for database queries, indexing issues, or storage debugging.
Run and debug Rust tests for glhf. Use when running tests, fixing test failures, or adding new test cases.
Implement and debug semantic/vector search with model2vec-rs and sqlite-vec. Use for embedding generation, vector queries, hybrid search, or RRF fusion.
Based on SOC occupation classification
| name | setup-environment |
| description | Set up the embedding model for semantic search. model2vec-rs downloads models automatically; use when build fails or model download issues occur. |
glhf uses model2vec-rs with Potion-base-32M for embeddings. The model downloads automatically on first use.
No manual setup required:
cargo build --release
./target/release/glhf index
The embedding model (~130MB) will download to the HuggingFace cache on first run.
| Property | Value |
|---|---|
| Model | minishlab/potion-base-32M |
| Dimensions | 512 |
| Size | ~130MB |
| Cache Location | ~/.cache/huggingface/ |
# Run embedding tests
cargo test embed -- --ignored
| Error | Solution |
|---|---|
Failed to load model | Check internet connection, model will auto-download |
No space left | Clear HuggingFace cache: rm -rf ~/.cache/huggingface/ |
Slow first run | Normal - model downloads once, then cached |
For text-only search (faster indexing, no model download):
glhf index --skip-embeddings
This enables FTS5 search but disables semantic/hybrid modes.