File size: 4,664 Bytes
7b850f8 5f70dc2 7b850f8 cb14e97 7b850f8 cb14e97 7b850f8 5f70dc2 cb14e97 5f70dc2 cb14e97 7b850f8 cb14e97 7b850f8 cb14e97 7b850f8 6090e99 7b850f8 6090e99 7b850f8 6090e99 7b850f8 6090e99 7b850f8 cb14e97 7b38ee1 |
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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 |
import os
import logging
import time
from dotenv import load_dotenv
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_cohere import CohereEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_groq import ChatGroq
# Load environment variables
load_dotenv()
# Set up logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s'
)
# Function to extract text from PDF files
def get_pdf_text(pdf_docs):
text = ""
for pdf in pdf_docs:
pdf_reader = PdfReader(pdf)
for page in pdf_reader.pages:
text += page.extract_text()
return text
# Function to split the extracted 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 a FAISS vectorstore with batching
def get_vectorstore(text_chunks):
cohere_api_key = os.getenv("COHERE_API_KEY")
embeddings = CohereEmbeddings(model="embed-english-v3.0", cohere_api_key=cohere_api_key)
# Batch processing to respect Cohere's rate limit
batch_size = 40
all_embeddings = []
for i in range(0, len(text_chunks), batch_size):
batch = text_chunks[i:i + batch_size]
logging.info(f"Processing batch {i // batch_size + 1}: {len(batch)} texts")
try:
batch_embeddings = embeddings.embed_documents(batch)
all_embeddings.extend(batch_embeddings)
except Exception as e:
logging.error(f"Error embedding batch {i // batch_size + 1}: {e}")
st.error(f"An error occurred while embedding batch {i // batch_size + 1}.")
if i + batch_size < len(text_chunks): # Enforce delay only if more batches remain
logging.info("Waiting for 60 seconds to respect API rate limits...")
time.sleep(60) # Wait for 60 seconds
vectorstore = FAISS.from_texts_with_embeddings(texts=text_chunks, embeddings=all_embeddings)
return vectorstore
# Function to set up the conversational retrieval chain
def get_conversation_chain(vectorstore):
try:
llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0.5)
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
conversation_chain = ConversationalRetrievalChain.from_llm(
llm=llm,
retriever=vectorstore.as_retriever(),
memory=memory
)
logging.info("Conversation chain created successfully.")
return conversation_chain
except Exception as e:
logging.error(f"Error creating conversation chain: {e}")
st.error("An error occurred while setting up the conversation chain.")
# Handle user input
def handle_userinput(user_question):
if st.session_state.conversation is not None:
response = st.session_state.conversation({'question': user_question})
st.session_state.chat_history = response['chat_history']
for i, message in enumerate(st.session_state.chat_history):
if i % 2 == 0:
st.write(f"*User:* {message.content}")
else:
st.write(f"*Bot:* {message.content}")
else:
st.warning("Please process the documents first.")
# Main function to run the Streamlit app
def main():
load_dotenv()
st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
if "conversation" not in st.session_state:
st.session_state.conversation = None
if "chat_history" not in st.session_state:
st.session_state.chat_history = None
st.header("Chat with multiple PDFs :books:")
user_question = st.text_input("Ask a question about your documents:")
if user_question:
handle_userinput(user_question)
with st.sidebar:
st.subheader("Your documents")
pdf_docs = st.file_uploader(
"Upload your PDFs here and click on 'Process'", accept_multiple_files=True
)
if st.button("Process"):
with st.spinner("Processing..."):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
vectorstore = get_vectorstore(text_chunks)
st.session_state.conversation = get_conversation_chain(vectorstore)
if __name__ == '__main__':
main()
|