Add rag google vertex ai search template (#13294)

- **Description:** This is a template demonstrating how to utilize
Google Vertex AI Search in conjunction with ChatVertexAI()

templates/rag-google-cloud-vertexai-search/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

templates/rag-google-cloud-vertexai-search/README.md

@@ -0,0 +1,88 @@
+# rag-google-cloud-vertexai-search
+
+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](https://cloud.google.com/generative-ai-app-builder/docs/enterprise-search-introduction).
+
+## Environment Setup
+
+Before using this template, please ensure that you are authenticated with Vertex AI Search. See the authentication
+guide: [here](https://cloud.google.com/generative-ai-app-builder/docs/authentication).
+
+You will also need to create:
+
+- A search application [here](https://cloud.google.com/generative-ai-app-builder/docs/create-engine-es)
+- A data store [here](https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es)
+
+A suitable dataset to test this template with is the Alphabet Earnings Reports, which you can
+find [here](https://abc.xyz/investor/). The data is also available
+at `gs://cloud-samples-data/gen-app-builder/search/alphabet-investor-pdfs`.
+
+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.
+
+## Usage
+
+To use this package, you should first have the LangChain CLI installed:
+
+```shell
+pip install -U langchain-cli
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+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:
+
+```shell
+langchain app add rag-google-cloud-vertexai-search
+```
+
+And add the following code to your `server.py` file:
+
+```python
+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](https://smith.langchain.com/).
+If you don't have access, you can skip this section
+
+```shell
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=<your-api-key>
+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:
+
+```shell
+langchain serve
+```
+
+This will start the FastAPI app with a server running locally at
+[http://localhost:8000](http://localhost:8000)
+
+We can see all templates at [http://127.0.0.1:8000/docs](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](http://127.0.0.1:8000/rag-google-cloud-vertexai-search/playground)
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/rag-google-cloud-vertexai-search")
+```

templates/rag-google-cloud-vertexai-search/main.py

@@ -0,0 +1,5 @@
+from rag_google_cloud_vertexai_search.chain import chain
+
+if __name__ == "__main__":
+    query = "Who is the CEO of Google Cloud?"
+    print(chain.invoke(query))

templates/rag-google-cloud-vertexai-search/pyproject.toml

@@ -0,0 +1,27 @@
+[tool.poetry]
+name = "rag-google-cloud-vertexai-search"
+version = "0.0.1"
+description = ""
+authors = ["Juan Calvo <juan.calvo@datatonic.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.333"
+google-cloud-aiplatform = ">=1.35.0"
+
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.15"
+fastapi = "^0.104.0"
+sse-starlette = "^1.6.5"
+
+[tool.langserve]
+export_module = "rag_google_cloud_vertexai_search"
+export_attr = "chain"
+
+[build-system]
+requires = [
+    "poetry-core",
+]
+build-backend = "poetry.core.masonry.api"

templates/rag-google-cloud-vertexai-search/rag_google_cloud_vertexai_search/chain.py

@@ -0,0 +1,50 @@
+import os
+
+from langchain.chat_models import ChatVertexAI
+from langchain.prompts import ChatPromptTemplate
+from langchain.pydantic_v1 import BaseModel
+from langchain.retrievers import GoogleVertexAISearchRetriever
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+
+# Get region and profile from env
+project_id = os.environ.get("GOOGLE_CLOUD_PROJECT_ID")
+data_store_id = os.environ.get("DATA_STORE_ID")
+model_type = os.environ.get("MODEL_TYPE")
+
+if not data_store_id:
+    raise ValueError(
+        "No value provided in env variable 'DATA_STORE_ID'. "
+        "A  data store is required to run this application."
+    )
+
+# Set LLM and embeddings
+model = ChatVertexAI(model_name=model_type, temperature=0.0)
+
+# Create Kendra retriever
+retriever = GoogleVertexAISearchRetriever(
+    project_id=project_id, search_engine_id=data_store_id
+)
+
+# RAG prompt
+template = """Answer the question based only on the following context:
+{context}
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+# RAG
+chain = (
+    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
+    | prompt
+    | model
+    | StrOutputParser()
+)
+
+
+# Add typing for input
+class Question(BaseModel):
+    __root__: str
+
+
+chain = chain.with_types(input_type=Question)