Build LLM-powered applications using LangChain

This page introduces how to build large language model (LLM)-powered applications using LangChain . The overviews on this page link to procedure guides in GitHub.

What's LangChain?

LangChain is an LLM orchestration framework that helps developers build generative AI applications or retrieval-augmented generation (RAG) workflows. It provides the structure, tools, and components to streamline complex LLM workflows.

For more information about LangChain, see the Google LangChain page. For more information about the LangChain framework, see the LangChain product documentation.

LangChain components for Memorystore for Valkey

Memorystore for Valkey offers the following LangChain interfaces:

• Vector store
• Document loader
• Chat message history

Learn how to use LangChain with the LangChain Quickstart .

Vector store for Memorystore for Valkey

Vector store retrieves and stores documents and metadata from a vector database. Vector store gives an application the ability to perform semantic searches that interpret the meaning of a user query. This type of search is a called a vector search, and it can find topics that match the query conceptually. At query time, Vector store retrieves the embedding vectors that are most similar to the embedding of the search request. In LangChain, a vector store takes care of storing embedded data and performing the vector search for you.

To work with vector store in Memorystore for Valkey, use the RedisVectorStore class.

For more information, see the LangChain product documentation.

Vector store procedure guide

The guide for Vector store shows you how to do the following:

• Install the integration package and LangChain.
• Initialize a vector index.
• Prepare documents for Vector store.
• Add documents to Vector store.
• Perform a similarity search (KNN).
• Perform a range-based similarity search.
• Perform a Maximal Marginal Relevance (MMR) search.
• Use Vector store as a Retriever.
• Delete documents from Vector store.
• Delete a vector index.

Document loader for Memorystore for Valkey

The document loader saves, loads, and deletes LangChain Document objects. For example, you can load data for processing into embeddings and either store it in Vector store or use it as a tool to provide specific context to chains.

To load documents from the document loader in Memorystore for Valkey, use the MemorystoreDocumentLoader class. To save and delete documents, use the MemorystoreDocumentSaver class.

For more information, see Document loaders .

Document loader procedure guide

The guide for document loader shows you how to do the following:

• Install the integration package and LangChain.
• Load documents from a table.
• Add a filter to the document loader.
• Customize the connection and authentication.
• Customize document construction by specifying customer content and metadata.
• Use and customize the MemorystoreDocumentSaver class to store and delete documents.

Chat message history for Memorystore for Valkey

Question-and-answer applications require a history of the things said in the conversation to give the application context for answering further questions from the user. The LangChain ChatMessageHistory class lets the application save messages to a database and retrieve them when needed to formulate further answers. A message can be a question, an answer, a statement, a greeting, or any other piece of text that the user or application gives during the conversation. ChatMessageHistory stores each message and chains messages together for each conversation.

Memorystore for Valkey extends this class with MemorystoreChatMessageHistory .

Chat message history procedure guide

The guide for chat message history shows you how to:

• Install LangChain and authenticate to Google Cloud.
• Initialize the MemorystoreChatMessageHistory class to add and delete messages.