mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
480626dc99
…tch]: import models from community ran ```bash git grep -l 'from langchain\.chat_models' | xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g" git grep -l 'from langchain\.llms' | xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g" git grep -l 'from langchain\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g" git checkout master libs/langchain/tests/unit_tests/llms git checkout master libs/langchain/tests/unit_tests/chat_models git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py make format cd libs/langchain; make format cd ../experimental; make format cd ../core; make format ```
69 lines
2.1 KiB
Python
69 lines
2.1 KiB
Python
import os
|
|
|
|
import weaviate
|
|
from langchain.prompts import ChatPromptTemplate
|
|
from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever
|
|
from langchain_community.chat_models import ChatOpenAI
|
|
from langchain_core.output_parsers import StrOutputParser
|
|
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
|
|
|
|
# Check env vars
|
|
if os.environ.get("WEAVIATE_API_KEY", None) is None:
|
|
raise Exception("Missing `WEAVIATE_API_KEY` environment variable.")
|
|
|
|
if os.environ.get("WEAVIATE_ENVIRONMENT", None) is None:
|
|
raise Exception("Missing `WEAVIATE_ENVIRONMENT` environment variable.")
|
|
|
|
if os.environ.get("WEAVIATE_URL", None) is None:
|
|
raise Exception("Missing `WEAVIATE_URL` environment variable.")
|
|
|
|
if os.environ.get("OPENAI_API_KEY", None) is None:
|
|
raise Exception("Missing `OPENAI_API_KEY` environment variable.")
|
|
|
|
# Initialize the retriever
|
|
WEAVIATE_INDEX_NAME = os.environ.get("WEAVIATE_INDEX", "langchain-test")
|
|
WEAVIATE_URL = os.getenv("WEAVIATE_URL")
|
|
auth_client_secret = (weaviate.AuthApiKey(api_key=os.getenv("WEAVIATE_API_KEY")),)
|
|
client = weaviate.Client(
|
|
url=WEAVIATE_URL,
|
|
additional_headers={
|
|
"X-Openai-Api-Key": os.getenv("OPENAI_API_KEY"),
|
|
},
|
|
)
|
|
retriever = WeaviateHybridSearchRetriever(
|
|
client=client,
|
|
index_name=WEAVIATE_INDEX_NAME,
|
|
text_key="text",
|
|
attributes=[],
|
|
create_schema_if_missing=True,
|
|
)
|
|
|
|
# # Ingest code - you may need to run this the first time
|
|
# # Load
|
|
# loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
|
# data = loader.load()
|
|
#
|
|
# # Split
|
|
# text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
|
|
# all_splits = text_splitter.split_documents(data)
|
|
#
|
|
# # Add to vectorDB
|
|
# retriever.add_documents(all_splits)
|
|
|
|
|
|
# RAG prompt
|
|
template = """Answer the question based only on the following context:
|
|
{context}
|
|
Question: {question}
|
|
"""
|
|
prompt = ChatPromptTemplate.from_template(template)
|
|
|
|
# RAG
|
|
model = ChatOpenAI()
|
|
chain = (
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
|
| prompt
|
|
| model
|
|
| StrOutputParser()
|
|
)
|