You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/partners/pinecone
Ash Vardanian d01bad5169
core[patch]: Convert SimSIMD back to NumPy (#19473)
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 🤗
6 months ago
..
langchain_pinecone core[patch]: Convert SimSIMD back to NumPy (#19473) 6 months ago
scripts infra: add print rule to ruff (#16221) 7 months ago
tests pinecone[patch]: integration test debug (#17960) 7 months ago
.gitignore pinecone: init pkg (#16556) 7 months ago
LICENSE pinecone: init pkg (#16556) 7 months ago
Makefile pinecone[patch], docs: PineconeVectorStore, release 0.0.3 (#17896) 7 months ago
README.md docs: update pinecone README to use PineconeVectorStore (#18170) 7 months ago
poetry.lock pinecone[patch], docs: PineconeVectorStore, release 0.0.3 (#17896) 7 months ago
pyproject.toml pinecone[patch], docs: PineconeVectorStore, release 0.0.3 (#17896) 7 months ago

README.md

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_KEY
  • PINECONE_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)