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/databricks
Yuki Watanabe c7a8af2e75
databricks: add vector search and embeddings (#25648)
### Summary

Add `DatabricksVectorSearch` and `DatabricksEmbeddings` classes to the
`langchain-databricks` partner packages. Core functionality is
unchanged, but the vector search class is largely refactored for
readability and maintainability.

This PR does not add integration tests yet. This will be added once the
Databricks test workspace is ready.

Tagging @efriis as POC


### Tracker
[] Create a package and imgrate ChatDatabricks
[✍️] Migrate DatabricksVectorSearch, DatabricksEmbeddings, and their
docs
~[ ] Migrate UCFunctionToolkit and its doc~
[ ] Add provider document and update README.md
[ ] Add integration tests and set up secrets (after moved to an external
package)
[ ] Add deprecation note to the community implementations.

---------

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
1 month ago
..
langchain_databricks databricks: add vector search and embeddings (#25648) 1 month ago
scripts databricks: Add partner package directory and ChatDatabricks implementation (#25430) 1 month ago
tests databricks: add vector search and embeddings (#25648) 1 month ago
.gitignore databricks: Add partner package directory and ChatDatabricks implementation (#25430) 1 month ago
LICENSE databricks: Add partner package directory and ChatDatabricks implementation (#25430) 1 month ago
Makefile databricks: Add partner package directory and ChatDatabricks implementation (#25430) 1 month ago
README.md databricks: Add partner package directory and ChatDatabricks implementation (#25430) 1 month ago
poetry.lock databricks: add vector search and embeddings (#25648) 1 month ago
pyproject.toml databricks: add vector search and embeddings (#25648) 1 month ago

README.md

langchain-databricks

This package contains the LangChain integration with Databricks

Installation

pip install -U langchain-databricks

And you should configure credentials by setting the following environment variables:

  • TODO: fill this out

Chat Models

ChatDatabricks class exposes chat models from Databricks.

from langchain_databricks import ChatDatabricks

llm = ChatDatabricks()
llm.invoke("Sing a ballad of LangChain.")