Show HN: Langchain's new member-A SQL+Vector database built on ClickHouse

[chathero]

https://myscale.com/

MyScale is designed for the storage and analysis of massive vector data with structured metadata. If you are eager to find a high-performance vector search using SQL queries, MyScale could be your preferred option. Thanks to the advantages of native structural database support, it provides you with a flexible filter with a WHERE clause, even JOIN when you want to jointly search vectors with filters on relevant metadata from other tables.

MyScale is now open for registration and offers millions of vectors‘ free tier plan for you! (https://myscale.com/)

Now you can also use MyScale as LangChain VectorStore

1. Go to MyScale (https://myscale.com/) and click on sign up

2. Go to your console to create a cluster: https://docs.myscale.com/en/cluster-management/

3. Get your Connection Details under the Action column under the cluster table.

4. Set the parameters in MyScaleSettings

Use the code snippets below to boost your chain with MyScale:

    ```python
    from langchain.vectorstores import MyScale, MyScaleSettings
    config = MyScaleSetting(host="<your-backend-url>", port=8443, ...)
    index = MyScale(embedding_function, config)
    index.add_documents(...)
    ```

P.S.: If you are interested in the super secret recipe for building high-performance AI+DB applications with MyScale, please visit: https://docs.myscale.com/en/advanced-applications/

[SamTNT]

Hi, I'm trying to build a chatbot for movie recommendations with Langchain and Pinecone. Currently stored movie embeddings in the free tier, but I want to store other types of embeddings for users as well. Is it possible to do that with MyScale?

[chathero → SamTNT]

Yes, MyScale can definitely help with that. Our platform supports storing multiple vector indexes, allowing you to store and perform vector searches on various types of embeddings. You can check out our documentation website for more information.

[newrohto]

So many vector dbs have been released this year. I wonder which will become the most popular db in the future. Anyway, nice work done!

[JumpingPumpkin]

Since pg with pgvector also supports SQL and vector search, can you provide more information on the advantages of using MyScale over pgvector?

[chathero → JumpingPumpkin]

Thanks for asking！MyScale's advanced vector indexes, such as HNSW/HNSWSQ, are designed to provide much faster and more efficient search capabilities for large-scale vector data. Additionally, MyScale's proprietary algorithms further enhance the search capabilities of our vector indexes, allowing for more accurate and relevant search results.

In comparison, pgvector's plugin for Postgres is a valuable tool for adding vector support to Postgres, but it does not offer the same level of performance and advanced features as MyScale. Furthermore, MyScale's storage-optimized instances and distributed support for large-scale vector data provide additional benefits that are not available with pgvector. With MyScale, users can focus on their applications and data, while leaving the management and scaling of their vector database to us.