Spaces:
Paused
Paused
import os | |
from typing import List | |
from langchain.embeddings.openai import OpenAIEmbeddings | |
from langchain.vectorstores.pinecone import Pinecone | |
from langchain.chains import ConversationalRetrievalChain | |
from langchain.chat_models import ChatOpenAI | |
from langchain.memory import ChatMessageHistory, ConversationBufferMemory | |
from langchain.docstore.document import Document | |
import pinecone | |
import chainlit as cl | |
pinecone.init( | |
api_key=os.environ.get("PINECONE_API_KEY"), | |
environment=os.environ.get("PINECONE_ENV"), | |
) | |
index_name = "langchain-demo" | |
embeddings = OpenAIEmbeddings() | |
welcome_message = "Welcome to the Chainlit Pinecone demo! Ask anything about Shakespeare's King Lear vectorized documents from Pinecone DB." | |
async def start(): | |
await cl.Message(content=welcome_message).send() | |
docsearch = Pinecone.from_existing_index( | |
index_name=index_name, embedding=embeddings | |
) | |
message_history = ChatMessageHistory() | |
memory = ConversationBufferMemory( | |
memory_key="chat_history", | |
output_key="answer", | |
chat_memory=message_history, | |
return_messages=True, | |
) | |
chain = ConversationalRetrievalChain.from_llm( | |
ChatOpenAI( | |
model_name="gpt-3.5-turbo", | |
temperature=0, | |
streaming=True), | |
chain_type="stuff", | |
retriever=docsearch.as_retriever(search_kwargs={'k': 3}), # I only want maximum of three document back with the highest similarity score | |
memory=memory, | |
return_source_documents=True, | |
) | |
cl.user_session.set("chain", chain) | |
async def main(message: cl.Message): | |
chain = cl.user_session.get("chain") # type: ConversationalRetrievalChain | |
cb = cl.AsyncLangchainCallbackHandler() | |
res = await chain.acall(message.content, callbacks=[cb]) | |
answer = res["answer"] | |
source_documents = res["source_documents"] # type: List[Document] | |
text_elements = [] # type: List[cl.Text] | |
if source_documents: | |
for source_idx, source_doc in enumerate(source_documents): | |
source_name = f"source_{source_idx}" | |
# Create the text element referenced in the message | |
text_elements.append( | |
cl.Text(content=source_doc.page_content, name=source_name) | |
) | |
source_names = [text_el.name for text_el in text_elements] | |
if source_names: | |
answer += f"\nSources: {', '.join(source_names)}" | |
else: | |
answer += "\nNo sources found" | |
await cl.Message(content=answer, elements=text_elements).send() | |