Upload 3 files

app.py

@@ -10,53 +10,69 @@ from langchain.prompts import PromptTemplate
 from dotenv import load_dotenv
 import os
 
-# Load the environment variables from .env file
+# Load environment variables from .env file
 load_dotenv()
 
 # Fetch the Google API key from the .env file
 api_key = os.getenv("GOOGLE_API_KEY")
 
+# Set the page configuration for the Streamlit app
 st.set_page_config(page_title="Document Genie", layout="wide")
 
+# Header and Instructions
 st.markdown("""
-## Document Genie: Get instant insights from your Documents
+## Document Genie: Get Instant Insights from Your Documents
 
-This chatbot is built using the Retrieval-Augmented Generation (RAG) framework, leveraging Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by breaking them down into manageable chunks, creates a searchable vector store, and generates accurate answers to user queries. This advanced approach ensures high-quality, contextually relevant responses for an efficient and effective user experience.
+This chatbot utilizes the Retrieval-Augmented Generation (RAG) framework with Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by segmenting them into chunks, creating a searchable vector store, and generating precise answers to your questions. This method ensures high-quality, contextually relevant responses for an efficient user experience.
 
 ### How It Works
 
-Follow these simple steps to interact with the chatbot:
-
-1. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights.
-
-2. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer.
+1. **Upload Your Documents**: You can upload multiple PDF files simultaneously for comprehensive analysis.
+2. **Ask a Question**: After processing the documents, type your question related to the content of your uploaded documents for a detailed answer.
 """)
 
 def get_pdf_text(pdf_docs):
+    """
+    Extract text from uploaded PDF documents.
+    """
     text = ""
     for pdf in pdf_docs:
         pdf_reader = PdfReader(pdf)
         for page in pdf_reader.pages:
-            text += page.extract_text()
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text
     return text
 
 def get_text_chunks(text):
+    """
+    Split text into manageable chunks for processing.
+    """
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
     chunks = text_splitter.split_text(text)
     return chunks
 
 def get_vector_store(text_chunks, api_key):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-def get_conversational_chain():
+    """
+    Create and save a FAISS vector store from text chunks.
+    """
+    try:
+        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
+        vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+        vector_store.save_local("faiss_index")
+        st.success("FAISS index created and saved successfully.")
+    except Exception as e:
+        st.error(f"Error creating FAISS index: {e}")
+
+def get_conversational_chain(api_key):
+    """
+    Set up the conversational chain using the Gemini-PRO model.
+    """
     prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-
+    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, 
+    say "Answer is not available in the context". Do not provide incorrect information.\n\n
+    Context:\n{context}\n
+    Question:\n{question}\n
     Answer:
     """
     model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, google_api_key=api_key)
@@ -65,30 +81,48 @@ def get_conversational_chain():
     return chain
 
 def user_input(user_question, api_key):
+    """
+    Handle user input and generate a response from the chatbot.
+    """
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
-    new_db = FAISS.load_local("faiss_index", embeddings)
-    docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-    st.write("Reply: ", response["output_text"])
+    
+    try:
+        new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+        docs = new_db.similarity_search(user_question)
+        chain = get_conversational_chain(api_key)
+        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+        st.write("Reply:", response["output_text"])
+    except ValueError as e:
+        st.error(f"Error loading FAISS index or generating response: {e}")
 
 def main():
-    st.header("AI clone chatbot💁")
+    """
+    Main function to run the Streamlit app.
+    """
+    st.header("AI Chatbot 💁")
 
     user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
 
-    if user_question:  # Only check for the user question now
+    if user_question:  # Trigger user input function only if there's a question
         user_input(user_question, api_key)
 
     with st.sidebar:
         st.title("Menu:")
         pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True, key="pdf_uploader")
-        if st.button("Submit & Process", key="process_button"):  # No need to check for API key here
-            with st.spinner("Processing..."):
-                raw_text = get_pdf_text(pdf_docs)
-                text_chunks = get_text_chunks(raw_text)
-                get_vector_store(text_chunks, api_key)
-                st.success("Done")
+        
+        if st.button("Submit & Process", key="process_button"):
+            if not api_key:
+                st.error("Google API key is missing. Please add it to the .env file.")
+                return
+            
+            if pdf_docs:
+                with st.spinner("Processing..."):
+                    raw_text = get_pdf_text(pdf_docs)
+                    text_chunks = get_text_chunks(raw_text)
+                    get_vector_store(text_chunks, api_key)
+                    st.success("Processing complete. You can now ask questions based on the uploaded documents.")
+            else:
+                st.error("No PDF files uploaded. Please upload at least one PDF file to proceed.")
 
 if __name__ == "__main__":
     main()