langchain-google-alloydb-pg 0.15.0

Installation

Install this library in a virtualenv using pip. virtualenv is a tool to create isolated Python environments. The basic problem it addresses is one of dependencies and versions, and indirectly permissions.

With virtualenv, it’s possible to install this library without needing system install permissions, and without clashing with the installed system dependencies.

pip install virtualenv
virtualenv <your-env>
source <your-env>/bin/activate
<your-env>/bin/pip install langchain-google-alloydb-pg

pip install virtualenv
virtualenv <your-env>
<your-env>\Scripts\activate
<your-env>\Scripts\pip.exe install langchain-google-alloydb-pg

Vector Store Usage

Use a vector store to store embedded data and perform vector search.

from langchain_google_alloydb_pg import AlloyDBEngine, AlloyDBVectorStore
from langchain_google_vertexai import VertexAIEmbeddings


engine = AlloyDBEngine.from_instance("project-id", "region", "my-cluster", "my-instance", "my-database")
embeddings_service = VertexAIEmbeddings(model_name="textembedding-gecko@003")
vectorstore = AlloyDBVectorStore.create_sync(
    engine,
    table_name="my-table",
    embedding_service=embeddings_service
)

Hybrid Search

The AlloyDBVectorStore supports hybrid search (dense vectors + full text) for more comprehensive and relevant search results.

from langchain_google_alloydb_pg import HybridSearchConfig, reciprocal_rank_fusion

vs = AlloyDBVectorStore.create_sync(
    engine=engine,
    table_name=TABLE_NAME,
    embedding_service=embedding,
    hybrid_search_config=HybridSearchConfig(
      fusion_function=reciprocal_rank_fusion
    ),
)
hybrid_docs = vector_store.similarity_search("products", k=5)

See the full Vector Store tutorial.

Document Loader Usage

Use a document loader to load data as LangChain Documents.

from langchain_google_alloydb_pg import AlloyDBEngine, AlloyDBLoader


engine = AlloyDBEngine.from_instance("project-id", "region", "my-cluster", "my-instance", "my-database")
loader = AlloyDBLoader.create_sync(
    engine,
    table_name="my-table-name"
)
docs = loader.lazy_load()

See the full Document Loader tutorial.

Chat Message History Usage

Use ChatMessageHistory to store messages and provide conversation history to LLMs.

from langchain_google_alloydb_pg import AlloyDBChatMessageHistory, AlloyDBEngine


engine = AlloyDBEngine.from_instance("project-id", "region", "my-cluster", "my-instance", "my-database")
history = AlloyDBChatMessageHistory.create_sync(
    engine,
    table_name="my-message-store",
    session_id="my-session-id"
)

See the full Chat Message History tutorial.

Langgraph Checkpoint Usage

Use AlloyDBSaver to save snapshots of the graph state at a given point in time.

from langchain_google_alloydb_pg import AlloyDBSaver, AlloyDBEngine


engine = AlloyDBEngine.from_instance("project-id", "region", "my-cluster", "my-instance", "my-database")
checkpoint = AlloyDBSaver.create_sync(engine)

See the full Checkpoint tutorial.

Converting Sync to Async

Update sync methods to await async methods

engine = await AlloyDBEngine.afrom_instance("project-id", "region", "my-cluster", "my-instance", "my-database")
await engine.ainit_vectorstore_table(table_name="my-table", vector_size=768)
vectorstore = await AlloyDBVectorStore.create(
   engine,
   table_name="my-table",
   embedding_service=VertexAIEmbeddings(model_name="textembedding-gecko@003")
)

@app.get("/invoke/")
async def invoke(query: str):
   return await retriever.ainvoke(query)

async def main():
   response = await retriever.ainvoke(query)
   print(response)

asyncio.run(main())