Spaces:
Sleeping
Sleeping
File size: 3,153 Bytes
3bbfff2 085c7bf 3bbfff2 f1a7e30 3bbfff2 3372024 3bbfff2 085c7bf 3bbfff2 3372024 79ff5ca b9ca76a 3372024 3bbfff2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | import os
import streamlit as st
import pandas as pd
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings
from langchain_openai import ChatOpenAI # Updated import statement
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.text_splitter import CharacterTextSplitter
OPENAI_API_KEY = "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"
os.environ['OPENAI_API_KEY'] = OPENAI_API_KEY
# Initialize variables
vectorstore = None
conversation_chain = None
chat_history = []
# Function to process uploaded CSV file
def process_csv(csv_file):
try:
df = pd.read_csv(csv_file)
text = df.to_string(index=False)
text_chunks = get_text_chunks(text)
vectorstore = get_vectorstore(text_chunks)
conversation_chain = get_conversation_chain(vectorstore)
return conversation_chain
except Exception as e:
st.error(f"Error processing CSV file: {e}")
# Function to split text into chunks
def get_text_chunks(text):
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks = text_splitter.split_text(text)
return chunks
# Function to create vectorstore from text chunks
def get_vectorstore(text_chunks):
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
return vectorstore
# Function to create conversation chain
def get_conversation_chain(vectorstore):
llm = ChatOpenAI() # Use the correct class from langchain-openai
memory = ConversationBufferMemory(
memory_key='chat_history', return_messages=True)
conversation_chain = ConversationalRetrievalChain.from_llm(
llm=llm,
retriever=vectorstore.as_retriever(),
memory=memory
)
return conversation_chain
# Streamlit app
def main():
global vectorstore, conversation_chain, chat_history
st.title('CSV Chatbot')
# Page to upload CSV file
st.subheader('Upload CSV File')
csv_file = st.file_uploader('Upload CSV', type=['csv'])
if csv_file:
conversation_chain = process_csv(csv_file)
if conversation_chain:
# Chat interface
st.subheader('Chat Interface')
user_question = st.text_input('Ask a question:')
if st.button('Ask'):
st.spinner("Generating Response.....")
response = conversation_chain.invoke({'question': user_question})
chat_history = response['chat_history']
for message in chat_history:
if message['role'] == 'user':
st.write(f"You: {message['content']}")
elif message['role'] == 'assistant':
st.write(f"Assistant: {message['content']}")
else:
st.error("Failed to process CSV file. Please try again.")
else:
st.error("Failed to process CSV file. Please try again.")
if __name__ == '__main__':
main()
|