added FalkorDB vector store support i.e implementation, test, docs an…

[kingtroga]

Description: Added support for FalkorDB Vector Store, including its implementation, unit tests, documentation, and an example notebook. The FalkorDB integration allows users to efficiently manage and query embeddings in a vector database, with relevance scoring and maximal marginal relevance search. The following components were implemented:

• Core implementation for FalkorDBVector store.
• Unit tests ensuring proper functionality and edge case coverage.
• Example notebook demonstrating an end-to-end setup, search, and retrieval using FalkorDB.

Twitter handle: @tariyekorogha

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchain	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Dec 16, 2024 7:37pm

[AviAvni]

some comments also maybe run a formatter to many empty lines

[swilly22]

is that the expected score ?
does the score is actually the distance from the query ?

[kingtroga]

@swilly22 @AviAvni

Thank you both for your valuable feedback on my initial commit. I’ve taken your suggestions into account and have made the necessary adjustments in this new commit (ed2e518). I would greatly appreciate it if you could take a moment to review the changes.

Thanks again for your help!

Also about the online meeting we can have it anytime between 12 pm to 6 pm WAT. My Email: [email protected] or [email protected]

[gkorland]

@baskaryan can you please merge this PR?

[kingtroga]

@baskaryan Please Merge this pull request

[kingtroga]

Please @baskaryan How long are the build, CI Success, and (Check for spelling errors) checks going to take?

[AviAvni]

@kingtroga Can you look at the CI errors and fix them?

[kingtroga]

@AviAvni On it

[gkorland]

@baskaryan can you please re-trigger the CI?

[kingtroga]

😌

@baskaryan PLEASE 🙏🏾 merge this pull request

[efriis]

hey there! had to revert a few things that we don't accept (this added a hard dependency on redis before). Hopefully it passes CI and can merge then.

Also, if you're interested in maintaining this integration without us in the loop, we'd love to get an integration package out! Future PRs against langchain would just be {docs updates, as well as registering your package in libs/packages.yml, deprecating this community integration in favor of your integration package}

Here's the guide, and if you have questions, feel free to leave them in the comments on those pages so others can see them! https://python.langchain.com/docs/contributing/how_to/integrations/

[kingtroga]

@efriss Thank you!!!