Hybrid Search in Weaviate
This template shows you how to use the hybrid search feature in Weaviate. Hybrid search combines multiple search algorithms to improve the accuracy and relevance of search results.
Weaviate uses both sparse and dense vectors to represent the meaning and context of search queries and documents. The results use a combination of
bm25 and vector search ranking to return the top results.
Connect to your hosted Weaviate Vectorstore by setting a few env variables in
You will also need to set your
OPENAI_API_KEY to use the OpenAI models.
To use this package, you should first have the LangChain CLI installed:
pip install -U langchain-cli
To create a new LangChain project and install this as the only package, you can do:
langchain app new my-app --package hybrid-search-weaviate
If you want to add this to an existing project, you can just run:
langchain app add hybrid-search-weaviate
And add the following code to your
from hybrid_search_weaviate import chain as hybrid_search_weaviate_chain
add_routes(app, hybrid_search_weaviate_chain, path="/hybrid-search-weaviate")
(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"
If you are inside this directory, then you can spin up a LangServe instance directly by:
This will start the FastAPI app with a server is running locally at http://localhost:8000
We can see all templates at http://127.0.0.1:8000/docs We can access the playground at http://127.0.0.1:8000/hybrid-search-weaviate/playground
We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/hybrid-search-weaviate")