1.1 KiB
1.1 KiB
Start services locally
This is a manual task you need to do in the terminal.
This spins up Neo4j and Weaviate containers and is configuring Weaviate to use embeddings from Hugging Face's Sentence Transformers using the "all-MiniLM-L6-v2" model, which has 384 dimensions.
docker compose -f tests/e2e/docker-compose.yml up
Write data (once)
Run this from the project root to write data to both dbs.
uv run python -m tests/e2e/weaviate_e2e/populate_dbs.py
Install Weaviate client
You need to install the weaviate-client package to use this retriever.
pip install weaviate-client
Search
# search by vector
uv run python -m examples.customize.retrievers.external.weaviate.vector_search
# search by text, with embeddings generated locally (via embedder argument)
uv run python -m examples.customize.retrievers.external.weaviate.text_search_local_embedder
# search by text, with embeddings generated on the Weaviate side, via configured vectorizer
uv run python -m examples.customize.retrievers.external.weaviate.text_search_remote_embedder