-
Notifications
You must be signed in to change notification settings - Fork 13.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
community: Add InMemoryVectorStore #19326
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
f9467fb
to
8a6e321
Compare
8a6e321
to
2e35112
Compare
@cbornet would you mind moving this to: All in memory implementations are pretty fundamental -- useful as both reference implementations and for testing purposes cc @baskaryan |
Standby! We're trying to figure whether it's langchain-core or langchain |
Ok. Note that I’m using utility functions for cosine similarity and mmr. |
Also the core would have to depend on numpy |
But a no-numpy, zero-dep, less performant implementation could also probably be written. |
Aah got it i didn't notice the numpy dependencies |
OK we can merge as is for now. We're working on breaking langchain dependency on langchain community. Once that's broken, we're likely going to invert it with |
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...
This is a basic VectorStore implementation using an in-memory dict to store the documents.
It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain.
This is useful for quick testing, demos, examples.
Also it allows to write vendor-neutral tutorials, guides, etc...