From b540ce5f43d249cc171845fdb892ae3da07a2b90 Mon Sep 17 00:00:00 2001 From: Prithvi Kannan <46332835+prithvikannan@users.noreply.github.com> Date: Fri, 13 Dec 2024 15:03:38 -0800 Subject: [PATCH] databricks-langchain as primary package (#34) * databricks-langchain as primary package Signed-off-by: Prithvi Kannan * genie Signed-off-by: Prithvi Kannan --------- Signed-off-by: Prithvi Kannan --- integrations/langchain/README.md | 44 ++++++++++++++++++++++---------- 1 file changed, 30 insertions(+), 14 deletions(-) diff --git a/integrations/langchain/README.md b/integrations/langchain/README.md index c60cef0..0d24f6b 100644 --- a/integrations/langchain/README.md +++ b/integrations/langchain/README.md @@ -1,38 +1,54 @@ -# 🦜🔗 Using Databricks AI Bridge with Langchain +# 🦜🔗 Databricks LangChain Integration -Integrate Databricks AI Bridge package with Langchain to allow seamless usage of Databricks AI features with Langchain/Langgraph applications. - -Note: This repository is the future home for all Databricks integrations currently found in `langchain-databricks` and `langchain-community`. We have now aliased `langchain-databricks` to `databricks-langchain`, consolidating integrations such as ChatDatabricks, DatabricksEmbeddings, DatabricksVectorSearch, and more under this package. +The `databricks-langchain` package provides seamless integration of Databricks AI features into LangChain applications. This repository is now the central hub for all Databricks-related LangChain components, consolidating previous packages such as `langchain-databricks` and `langchain-community`. ## Installation -### Install from PyPI +### From PyPI ```sh pip install databricks-langchain ``` -### Install from source - +### From Source ```sh pip install git+ssh://git@github.com/databricks/databricks-ai-bridge.git#subdirectory=integrations/langchain ``` -## Get started +## Key Features -### Use LLMs on Databricks +- **LLMs Integration:** Use Databricks-hosted large language models (LLMs) like Llama and Mixtral through `ChatDatabricks`. +- **Vector Search:** Store and query vector representations using `DatabricksVectorSearch`. +- **Embeddings:** Generate embeddings with `DatabricksEmbeddings`. +- **Genie:** Use [Genie](https://www.databricks.com/product/ai-bi/genie) in Langchain. +## Getting Started + +### Use LLMs on Databricks ```python from databricks_langchain import ChatDatabricks + llm = ChatDatabricks(endpoint="databricks-meta-llama-3-1-70b-instruct") ``` -### (Preview) Use a Genie space as an agent - -> [!NOTE] -> Requires Genie API Private Preview. Reach out to your account team for enablement. +### Use a Genie Space as an Agent (Preview) +> **Note:** Requires Genie API Private Preview. Contact your Databricks account team for enablement. ```python from databricks_langchain.genie import GenieAgent -genie_agent = GenieAgent("space-id", "Genie", description="This Genie space has access to sales data in Europe") +genie_agent = GenieAgent( + "space-id", "Genie", + description="This Genie space has access to sales data in Europe" +) ``` + +--- + +## Contribution Guide +We welcome contributions! Please see our [contribution guidelines](https://github.com/databricks/databricks-ai-bridge/tree/main/integrations/langchain) for details. + +## License +This project is licensed under the [MIT License](LICENSE). + +Thank you for using Databricks LangChain! +