This template is an application that utilizes Google Vertex AI Search, a machine learning powered search service, and PaLM 2 for Chat (chat-bison). The application uses a Retrieval chain to answer questions based on your documents.
For more context on building RAG applications with Vertex AI Search, check here.
Before using this template, please ensure that you are authenticated with Vertex AI Search. See the authentication guide: here.
You will also need to create:
A suitable dataset to test this template with is the Alphabet Earnings Reports, which you can
find here. The data is also available
Set the following environment variables:
GOOGLE_CLOUD_PROJECT_ID- Your Google Cloud project ID.
DATA_STORE_ID- The ID of the data store in Vertex AI Search, which is a 36-character alphanumeric value found on the data store details page.
MODEL_TYPE- The model type for Vertex AI Search.
To use this package, you should first have the LangChain CLI installed:
pip install -U langchain-cli
To create a new LangChain project and install this as the only package, you can do:
langchain app new my-app --package rag-google-cloud-vertexai-search
If you want to add this to an existing project, you can just run:
langchain app add rag-google-cloud-vertexai-search
And add the following code to your
from rag_google_cloud_vertexai_search.chain import chain as rag_google_cloud_vertexai_search_chain
add_routes(app, rag_google_cloud_vertexai_search_chain, path="/rag-google-cloud-vertexai-search")
(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"
If you are inside this directory, then you can spin up a LangServe instance directly by:
This will start the FastAPI app with a server running locally at http://localhost:8000
We can see all templates at http://127.0.0.1:8000/docs We can access the playground at http://127.0.0.1:8000/rag-google-cloud-vertexai-search/playground
We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/rag-google-cloud-vertexai-search")