Update app.py

app.py

@@ -4,13 +4,11 @@ from dotenv import load_dotenv
 import streamlit as st
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
-# from langchain.embeddings import HuggingFaceInstructEmbeddings
-from langchain_cohere import CohereEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
-# from langchain.llms import Ollama
-from langchain_groq import ChatGroq
+from langchain.llms import HuggingFaceHub
 
 # Load environment variables
 load_dotenv()
@@ -21,16 +19,14 @@ logging.basicConfig(
     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()
+            text += page.extract_text() or ""
     return text
 
-# Function to split the extracted text into chunks
 def get_text_chunks(text):
     text_splitter = CharacterTextSplitter(
         separator="\n",
@@ -38,74 +34,54 @@ def get_text_chunks(text):
         chunk_overlap=200,
         length_function=len
     )
-    chunks = text_splitter.split_text(text)
-    return chunks
-
-# Function to create a FAISS vectorstore
-# def get_vectorstore(text_chunks):
-#     embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
-#     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-#     return vectorstore
+    return text_splitter.split_text(text)
 
 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)
-    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-    return vectorstore
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
 
-# Function to set up the conversational retrieval chain
 def get_conversation_chain(vectorstore):
     try:
-        # llm = Ollama(model="llama3.2:1b")
-        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5)
+        llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.1", model_kwargs={"temperature": 0.5})
         memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
         
-        conversation_chain = ConversationalRetrievalChain.from_llm(
+        return 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.")
+        return None
 
-# Handle user input
 def handle_userinput(user_question):
-    if st.session_state.conversation is not None:
+    if st.session_state.conversation:
         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}")
+            role = "User" if i % 2 == 0 else "Bot"
+            st.write(f"*{role}:* {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:")
+    st.set_page_config(page_title="Chat with 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:")
+    st.header("Chat with 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
-        )
+        pdf_docs = st.file_uploader("Upload PDFs and click 'Process'", accept_multiple_files=True)
         if st.button("Process"):
             with st.spinner("Processing..."):
                 raw_text = get_pdf_text(pdf_docs)
@@ -114,4 +90,4 @@ def main():
                 st.session_state.conversation = get_conversation_chain(vectorstore)
 
 if __name__ == '__main__':
-    main()
+    main()