Upload 2 files

app.py

@@ -0,0 +1,124 @@
+import streamlit as st
+from streamlit_chat import message
+from langchain.chains import ConversationalRetrievalChain
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.llms import LlamaCpp
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.memory import ConversationBufferMemory
+from langchain.document_loaders import PyPDFLoader
+import os
+import tempfile
+
+def initialize_session_state():
+    if 'history' not in st.session_state:
+        st.session_state['history'] = []
+
+    if 'generated' not in st.session_state:
+        st.session_state['generated'] = ["Hello! Ask me anything about 🤗"]
+
+    if 'past' not in st.session_state:
+        st.session_state['past'] = ["Hey! 👋"]
+
+def conversation_chat(query, chain, history):
+    result = chain({"question": query, "chat_history": history})
+    history.append((query, result["answer"]))
+    return result["answer"]
+
+def display_chat_history(chain):
+    reply_container = st.container()
+    container = st.container()
+
+    with container:
+        with st.form(key='my_form', clear_on_submit=True):
+            user_input = st.text_input("Question:", placeholder="Ask about your PDF", key='input')
+            submit_button = st.form_submit_button(label='Send')
+
+        if submit_button and user_input:
+            with st.spinner('Generating response...'):
+                output = conversation_chat(user_input, chain, st.session_state['history'])
+
+            st.session_state['past'].append(user_input)
+            st.session_state['generated'].append(output)
+
+    if st.session_state['generated']:
+        with reply_container:
+            for i in range(len(st.session_state['generated'])):
+                message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
+                message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
+
+def create_conversational_chain(vector_store):
+    model_path = "E:/users/sriva/mistral_llm/mistral-7b-instruct-v0.1.Q4_K_M-001.gguf"  # Updated model path
+    
+    # Debugging output
+    print(f"Attempting to load model from: {model_path}")
+    print("Checking if model file exists...")
+    if not os.path.exists(model_path):
+        raise FileNotFoundError(f"The model file does not exist at: {model_path}")
+
+    # Initialize LlamaCpp
+    try:
+        llm = LlamaCpp(
+            streaming=True,
+            model_path=model_path,
+            temperature=0.75,
+            top_p=1,
+            verbose=True,
+            n_ctx=4096
+        )
+        print("Model loaded successfully.")
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        raise
+
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+    chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        chain_type='stuff',
+        retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
+        memory=memory
+    )
+    return chain
+
+def main():
+    # Initialize session state
+    initialize_session_state()
+    st.title("Multi-PDF ChatBot using Mistral-7B-Instruct :books:")
+    # Initialize Streamlit
+    st.sidebar.title("Document Processing")
+    uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
+
+    if uploaded_files:
+        text = []
+        for file in uploaded_files:
+            file_extension = os.path.splitext(file.name)[1]
+            with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+                temp_file.write(file.read())
+                temp_file_path = temp_file.name
+
+            loader = None
+            if file_extension == ".pdf":
+                loader = PyPDFLoader(temp_file_path)
+
+            if loader:
+                text.extend(loader.load())
+                os.remove(temp_file_path)
+
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=20)
+        text_chunks = text_splitter.split_documents(text)
+
+        # Create embeddings
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", 
+                                           model_kwargs={'device': 'cpu'})
+
+        # Create vector store
+        vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
+
+        # Create the chain object
+        chain = create_conversational_chain(vector_store)
+
+        display_chat_history(chain)
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,13 @@
+langchain
+torch
+accelerate
+sentence_transformers
+streamlit_chat
+streamlit
+faiss-cpu
+tiktoken
+huggingface-hub
+pypdf
+llama-cpp-python
+
+