Bigtable

Bigtable is a scalable, fully managed key-value and wide-column store ideal for fast access to structured, semi-structured, or unstructured data. This page provides an overview of Bigtable's LangChain integrations.

Client Library Documentation: cloud.google.com/python/docs/reference/langchain-google-bigtable/latest

Product Documentation: cloud.google.com/bigtable

Quick Start

To use this library, you first need to:

1. Select or create a Cloud Platform project.
2. Enable billing for your project.
3. Enable the Google Cloud Bigtable API.
4. Set up Authentication.

Installation

The main package for this integration is langchain-google-bigtable.

pip install -U langchain-google-bigtable

Integrations

The langchain-google-bigtable package provides the following integrations:

Vector Store

With BigtableVectorStore, you can store documents and their vector embeddings to find the most similar or relevant information in your database.

• Full VectorStore Implementation: Supports all methods from the LangChain VectorStore abstract class.
• Async/Sync Support: All methods are available in both asynchronous and synchronous versions.
• Metadata Filtering: Powerful filtering on metadata fields, including logical AND/OR combinations.
• Multiple Distance Strategies: Supports both Cosine and Euclidean distance for similarity search.
• Customizable Storage: Full control over how content, embeddings, and metadata are stored in Bigtable columns.

from langchain_google_bigtable import BigtableVectorStore

# Your embedding service and other configurations
# embedding_service = ...

engine = await BigtableEngine.async_initialize(project_id="your-project-id")
vector_store = await BigtableVectorStore.create(
    engine=engine,
    instance_id="your-instance-id",
    table_id="your-table-id",
    embedding_service=embedding_service,
    collection="your_collection_name",
)
await vector_store.aadd_documents([your_documents])
results = await vector_store.asimilarity_search("your query")

Learn more in the Vector Store how-to guide.

Key-value Store

Use BigtableByteStore as a persistent, scalable key-value store for caching, session management, or other storage needs. It supports both synchronous and asynchronous operations.

from langchain_google_bigtable import BigtableByteStore

# Initialize the store
store = await BigtableByteStore.create(
    project_id="your-project-id",
    instance_id="your-instance-id",
    table_id="your-table-id",
)

# Set and get values
await store.amset([("key1", b"value1")])
retrieved = await store.amget(["key1"])

Learn more in the Key-value Store how-to guide.

Document Loader

Use the BigtableLoader to load data from a Bigtable table and represent it as LangChain Document objects.

from langchain_google_bigtable import BigtableLoader

loader = BigtableLoader(
    project_id="your-project-id",
    instance_id="your-instance-id",
    table_id="your-table-name"
)
docs = loader.load()

Learn more in the Document Loader how-to guide.

Chat Message History

Use BigtableChatMessageHistory to store conversation histories, enabling stateful chains and agents.

from langchain_google_bigtable import BigtableChatMessageHistory

history = BigtableChatMessageHistory(
    project_id="your-project-id",
    instance_id="your-instance-id",
    table_id="your-message-store",
    session_id="user-session-123"
)

history.add_user_message("Hello!")
history.add_ai_message("Hi there!")

Learn more in the Chat Message History how-to guide.

Contributions

Contributions to this library are welcome. Please see the CONTRIBUTING guide in the package repo for more details

License

This project is licensed under the Apache 2.0 License - see the LICENSE file in the package repo for details.

Disclaimer

This is not an officially supported Google product.