mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-04 11:25:11 +00:00
d01bad5169
This patch fixes the #18022 issue, converting the SimSIMD internal zero-copy outputs to NumPy. I've also noticed, that oftentimes `dtype=np.float32` conversion is used before passing to SimSIMD. Which numeric types do LangChain users generally care about? We support `float64`, `float32`, `float16`, and `int8` for cosine distances and `float16` seems reasonable for practically any kind of embeddings and any modern piece of hardware, so we can change that part as well 🤗
langchain-pinecone
This package contains the LangChain integration with Pinecone.
Installation
pip install -U langchain-pinecone
And you should configure credentials by setting the following environment variables:
PINECONE_API_KEYPINECONE_INDEX_NAME
Usage
The PineconeVectorStore class exposes the connection to the Pinecone vector store.
from langchain_pinecone import PineconeVectorStore
embeddings = ... # use a LangChain Embeddings class
vectorstore = PineconeVectorStore(embeddings=embeddings)