added template to use Vertex Vector Search for q&a (#12622)

added template to use Vertex Vector Search for q&a

templates/rag-matching-engine/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-matching-engine/README.md

@@ -0,0 +1 @@
+# rag-matching-engine

templates/rag-matching-engine/pyproject.toml

@@ -0,0 +1,24 @@
+[tool.poetry]
+name = "rag_matching_engine"
+version = "0.0.1"
+description = ""
+authors = []
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313, <0.1"
+google-cloud-aiplatform = "^1.35.0"
+
+[tool.poetry.group.dev.dependencies]
+langchain-cli = ">=0.0.4"
+fastapi = "^0.104.0"
+sse-starlette = "^1.6.5"
+
+[tool.langserve]
+export_module = "rag_matching_engine.chain"
+export_attr = "chain"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/rag-matching-engine/rag_matching_engine/chain.py

@@ -0,0 +1,69 @@
+import os
+
+from langchain.embeddings import VertexAIEmbeddings
+from langchain.llms import VertexAI
+from langchain.prompts import PromptTemplate
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.vectorstores import MatchingEngine
+
+# you need to preate the index first, for example, as described here:
+# https://github.com/GoogleCloudPlatform/generative-ai/blob/main/language/use-cases/document-qa/question_answering_documents_langchain_matching_engine.ipynb
+expected_variables = [
+    "project_id",
+    "me_region",
+    "gcs_bucket",
+    "me_index_id",
+    "me_endpoint_id",
+]
+variables = []
+for variable_name in expected_variables:
+    variable = os.environ.get(variable_name.upper())
+    if not variable:
+        raise Exception(f"Missing `{variable_name}` environment variable.")
+    variables.append(variable)
+
+project_id, me_region, gcs_bucket, me_index_id, me_endpoint_id = variables
+
+
+vectorstore = MatchingEngine.from_components(
+    project_id=project_id,
+    region=me_region,
+    gcs_bucket_name=gcs_bucket,
+    embedding=VertexAIEmbeddings(),
+    index_id=me_index_id,
+    endpoint_id=me_endpoint_id,
+)
+
+model = VertexAI()
+
+template = (
+    "SYSTEM: You are an intelligent assistant helping the users with their questions"
+    "on research papers.\n\n"
+    "Question: {question}\n\n"
+    "Strictly Use ONLY the following pieces of context to answer the question at the "
+    "end. Think step-by-step and then answer.\n\n"
+    "Do not try to make up an answer:\n"
+    "- If the answer to the question cannot be determined from the context alone, "
+    'say \n"I cannot determine the answer to that."\n'
+    '- If the context is empty, just say "I do not know the answer to that."\n\n'
+    "=============\n{context}\n=============\n\n"
+    "Question: {question}\nHelpful Answer: "
+)
+
+prompt = PromptTemplate.from_template(template)
+
+retriever = vectorstore.as_retriever(
+    search_type="similarity",
+    search_kwargs={
+        "k": 10,
+        "search_distance": 0.6,
+    },
+)
+
+chain = (
+    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
+    | prompt
+    | model
+    | StrOutputParser()
+)