CLI Reference¶
Embenx provides a powerful Command Line Interface (CLI) for benchmarking, setup, and ecosystem interaction.
General Commands¶
info¶
Display system information and status of installed vector backends.
embenx info
check¶
Verify environment health and dependency availability.
embenx check
setup¶
Setup the environment and pull specific models (for Ollama).
embenx setup --model ollama/nomic-embed-text --pull
Benchmarking¶
benchmark¶
Run performance benchmarks on local Parquet files.
embenx benchmark data.parquet --indexers faiss,usearch --max-docs 1000
grand-benchmark¶
Run comprehensive benchmarks across all datasets in the Retrieval Zoo and generate a Grand Technical Report.
embenx grand-benchmark --indexers faiss,scann,hnswlib
Agentic & Visual¶
mcp-start¶
Start the Model Context Protocol (MCP) server to connect AI agents.
embenx mcp-start
explorer¶
Launch the Streamlit web UI for data visualization and HNSW graph inspection.
embenx explorer
Retrieval Zoo¶
zoo-list¶
List available pre-indexed collections in the cloud zoo.
embenx zoo-list
zoo-load¶
Download and load a pre-built collection into local cache.
embenx zoo-load squad-v2
Maintenance¶
cleanup¶
Remove temporary benchmark artifacts and database files to free up space.
embenx cleanup
init-skill¶
Initialize the Embenx skill for Gemini CLI sub-agents.
embenx init-skill