Only open-source in ecosystem integrations?

[lukaspetersson]

Hi!
I am the creator of Vectorview an analytics tool for semantic search.
We would love to be part of langchain's ecosystem and add an integration through a callback.

We have not had time to build the self-hosted open source version of vectorview yet, we only have a hosted version (with free trail).
I wonder, is beeing open-source a requirement for being part of langchain?
Otherwise I would be happy to make a PR asap :)

Kind regards, Lukas

[dosubot[bot]]

🤖

Hi Lukas,

Thank you for your interest in integrating Vectorview with LangChain!

To answer your question, it is not a requirement for Vectorview to be open-source in order to be part of LangChain's ecosystem and add an integration through a callback. LangChain supports a variety of vector stores, some of which are open-source (like Elasticsearch, Annoy, FAISS, etc.) and others which are not (like AlibabaCloudOpenSearch, AzureSearch, etc.). This indicates that LangChain's ecosystem is not limited to open-source solutions. You can find this information in the vectorstores init.py file.

As for the process of adding a new integration, I couldn't find specific documentation within the repository. However, making a PR with your proposed integration would be a good start. Please ensure that your PR includes comprehensive documentation and tests for the new integration.

If you need any further assistance, feel free to ask.

Best regards,
Dosu

Sources

• libs/langchain/langchain/vectorstores/init.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.