Databricks Intelligence Platform is the world's first data intelligence platform powered by generative AI. Infuse AI into every facet of your business.

Databricks embraces the LangChain ecosystem in various ways:

1. 🚀Model Serving - Access state-of-the-art LLMs, such as DBRX, Llama3, Mixtral, or your fine-tuned models onDatabricks Model Serving, via a highly available and low-latency inference endpoint. LangChain provides LLM (Databricks), Chat Model (ChatDatabricks), and Embeddings (DatabricksEmbeddings) implementations, streamlining the integration of your models hosted on Databricks Model Serving with your LangChain applications.
2. 📃Vector Search -Databricks Vector Search is a serverless vector database seamlessly integrated within the Databricks Platform. UsingDatabricksVectorSearch, you can incorporate the highly scalable and reliable similarity search engine into your LangChain applications.
3. 📊MLflow -MLflow is an open-source platform to manage full the ML lifecycle, including experiment management, evaluation, tracing, deployment, and more.MLflow's LangChain Integration streamlines the process of developing and operating modern compound ML systems.
4. 🌐SQL Database -Databricks SQL is integrated withSQLDatabase in LangChain, allowing you to access the auto-optimizing, exceptionally performant data warehouse.
5. 💡Open Models - Databricks open sources models, such asDBRX, which are available through theHugging Face Hub. These models can be directly utilized with LangChain, leveraging its integration with thetransformers library.

Installation​

First-party Databricks integrations are now available in the databricks-langchain partner package.

pip install databricks-langchain

The legacy langchain-databricks partner package is still available but will be soon deprecated.

Chat Model​

ChatDatabricks is a Chat Model class to access chat endpoints hosted on Databricks, including state-of-the-art models such as Llama3, Mixtral, and DBRX, as well as your own fine-tuned models.

from databricks_langchain import ChatDatabricks

chat_model = ChatDatabricks(endpoint="databricks-meta-llama-3-70b-instruct")

See theusage example for more guidance on how to use it within your LangChain application.

LLM​

Databricks is an LLM class to access completion endpoints hosted on Databricks.

from langchain_community.llm.databricks import Databricks

llm = Databricks(endpoint="your-completion-endpoint")

See theusage example for more guidance on how to use it within your LangChain application.

Embeddings​

DatabricksEmbeddings is an Embeddings class to access text-embedding endpoints hosted on Databricks, including state-of-the-art models such as BGE, as well as your own fine-tuned models.

from databricks_langchain import DatabricksEmbeddings

embeddings = DatabricksEmbeddings(endpoint="databricks-bge-large-en")

See theusage example for more guidance on how to use it within your LangChain application.

Vector Search​

Databricks Vector Search is a serverless similarity search engine that allows you to store a vector representation of your data, including metadata, in a vector database. With Vector Search, you can create auto-updating vector search indexes fromDelta tables managed byUnity Catalog and query them with a simple API to return the most similar vectors.

from databricks_langchain import DatabricksVectorSearch

dvs = DatabricksVectorSearch(
    endpoint="<YOUT_ENDPOINT_NAME>",
    index_name="<YOUR_INDEX_NAME>",
    index,
    text_column="text",
    embedding=embeddings,
    columns=["source"]
)
docs = dvs.similarity_search("What is vector search?)

See theusage example for how to set up vector indices and integrate them with LangChain.

MLflow Integration​

In the context of LangChain integration, MLflow provides the following capabilities:

• Experiment Tracking: Tracks and stores models, artifacts, and traces from your LangChain experiments.
• Dependency Management: Automatically records dependency libraries, ensuring consistency among development, staging, and production environments.
• Model Evaluation Offers native capabilities for evaluating LangChain applications.
• Tracing: Visually traces data flows through your LangChain application.

SeeMLflow LangChain Integration to learn about the full capabilities of using MLflow with LangChain through extensive code examples and guides.

SQLDatabase​

To connect to Databricks SQL or query structured data, see theDatabricks structured retriever tool documentation and to create an agent using the above created SQL UDF seeDatabricks UC Integration.

Open Models​

To directly integrate Databricks's open models hosted on HuggingFace, you can use theHuggingFace Integration of LangChain.

from langchain_huggingface import HuggingFaceEndpoint

llm = HuggingFaceEndpoint(
    repo_id="databricks/dbrx-instruct",
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
)
llm.invoke("What is DBRX model?")