chatbox / app.py
roi159's picture
Rename main.py to app.py
746ace3
Raw History Blame Contribute Delete
3.53 kB
#import library
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains import ConversationalRetrievalChain
import customnotiondbload as custom_notion
from getpass import getpass
NOTION_TOKEN ="secret_89vVgMQ1jAHNrbWWjAm0g2h9oEPZafSylgqEHmDvHhk"
DATABASE_ID = "2bd913bed8374780854c776954cc9001"
import os
os.environ[
"OPENAI_API_KEY"] = "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"
from langchain.chat_models import ChatOpenAI
llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo")
#Load data
from langchain.document_loaders import DirectoryLoader
# pdf_loader = DirectoryLoader('./Reports/', glob="**/*.pdf")
# txt_loader = DirectoryLoader('./Reports/', glob="**/*.txt")
# word_loader = DirectoryLoader('./Reports/', glob="**/*.docx")
# html_loader = DirectoryLoader('./Reports/', glob="**/*.html")
# lzone_loader= DirectoryLoader('./Reports/', glob="**/*.html")
# csv_loader = DirectoryLoader('./Reports/', glob="**/*.csv")
notion_loader = custom_notion.NotionDBLoader(
integration_token=NOTION_TOKEN,
database_id=DATABASE_ID,
request_timeout_sec=60, # optional, defaults to 10
)
loaders = [notion_loader]
documents = []
for loader in loaders:
documents.extend(loader.load())
print(f"Total number of documents: {documents}")
print(f"Total number of documents: {len(documents)}")
#Chun data, Embeddings and save to VectorStore
from langchain.vectorstores.utils import filter_complex_metadata
text_splitter = CharacterTextSplitter(chunk_size=2000, chunk_overlap=200)
# Filter out documents with complex metadata
filtered_documents = []
for document in documents:
print(document.metadata.values())
# print(all(value is None or isinstance(value, (str, int, float, bool)) for value in document.metadata.values()))
if all(value is None or isinstance(value, (str, int, float, bool))
for value in document.metadata.values()):
filtered_documents.append(document)
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(filtered_documents, embeddings)
#Calling the Langchain's QA chain with Chat History
qa = ConversationalRetrievalChain.from_llm(llm,
vectorstore.as_retriever(),
return_source_documents=True)
#Gradio Chat UI
import gradio as gr
# def greet(name):
# return "Hello " + name + "!"
# demo = gr.Interface(
# fn=greet,
# inputs="text",
# outputs="text",
# css="footer{display:none !important}"
# )
# demo.launch()
# Define chat interface
with gr.Blocks() as demo:
chatbot = gr.Chatbot()
msg = gr.Textbox()
clear = gr.Button("Clear")
chat_history = []
def user(query, chat_history):
print("User query:", query)
print("Chat history:", chat_history)
# Convert chat history to list of tuples
chat_history_tuples = []
for message in chat_history:
chat_history_tuples.append((message[0], message[1]))
# Get result from QA chain
result = qa({"question": query, "chat_history": chat_history_tuples})
# Append user message and response to chat history
chat_history.append((query, result["answer"]))
print("Updated chat history:", chat_history)
return gr.update(value=""), chat_history
msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False)
clear.click(lambda: None, None, chatbot, queue=False)
if __name__ == "__main__":
demo.launch(share=True)