Update app.py

app.py

@@ -19,25 +19,24 @@ def text_to_speech(text):
     os.remove(temp_filename)
 
 def get_pdf_text(pdf_docs):
-    text=""
+    text = ""
     for pdf in pdf_docs:
-        pdf_reader= PdfReader(pdf)
+        pdf_reader = PdfReader(pdf)
         for page in pdf_reader.pages:
-            text+= page.extract_text()
-    return  text
+            text += page.extract_text()
+    return text
 
 def get_text_chunks(text):
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     chunks = text_splitter.split_text(text)
     return chunks
-    
+
 def get_vector_store(text_chunks, api_key):
     embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     vector_store.save_local("faiss_index")
 
 def get_conversational_chain():
-
     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
@@ -45,73 +44,56 @@ def get_conversational_chain():
     Question: \n{question}\n
     Answer:
     """
-
     model = ChatGroq(temperature=0, groq_api_key=os.environ["groq_api_key"], model_name="llama3-8b-8192")
-
     prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-
     return chain
 
 def user_input(user_question, api_key):
     embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
-    
     new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     docs = new_db.similarity_search(user_question)
-
     chain = get_conversational_chain()
-
-    response = chain(
-        {"input_documents":docs, "question": user_question}
-        , return_only_outputs=True)
-
-    print(response)  # Debugging line
-    
+    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
     st.write("Replies:")
     if isinstance(response["output_text"], str):
         response_list = [response["output_text"]]
     else:
         response_list = response["output_text"]
-    
     for text in response_list:
         st.write(text)
         # Convert text to speech for each response
         text_to_speech(text)
 
 def main():
-    st.set_page_config(layout="centered")
+    st.set_page_config(layout="wide")
     st.header("Chat with DOCS")
     st.markdown("<h1 style='font-size:20px;'>ChatBot by Muhammad Huzaifa</h1>", unsafe_allow_html=True)
     api_key = st.secrets["inference_api_key"]
-    
-    with st.sidebar:
-        st.header("Chat with PDF")
-    
-    pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit Button", accept_multiple_files=True, type=["pdf"])
-    
-    if st.button("Submit") and pdf_docs:
-        with st.spinner("Processing..."):
+
+    # Sidebar column for file upload
+    st.sidebar.header("Chat with PDF")
+    pdf_docs = st.sidebar.file_uploader("Upload your PDF Files", accept_multiple_files=True, type=["pdf"])
+
+    # Main column for displaying extracted text and user interaction
+    col1, col2 = st.columns([1, 2])
+
+    if pdf_docs and col1.button("Submit"):
+        with col1.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")
-
-    if pdf_docs:
-        user_question = st.text_input("Ask a question from the Docs")
-        if user_question:
-            user_input(user_question, api_key)
-    else:
-        st.write("Please upload PDF documents to proceed.")
-        
+            col1.success("Processing Complete")
+            if col1.success("Processing Complete"):
+                user_question = st.text_input("Ask a question from the Docs")
+                if user_question:
+                    user_input(user_question, api_key)
     if raw_text:
-        get_pdf_text(pdf_docs)
-    # # Check if any document is uploaded
-    # if pdf_docs:
-    #     user_question = st.text_input("Ask a question from the Docs")
-    #     if user_question:
-    #         user_input(user_question, api_key)
-    # else:
-    #     st.write("Please upload a document first to ask questions.")
-           
+        with col2:
+            st.subheader("Extracted Text from PDF:")
+            st.text(raw_text)
+
+
+
 if __name__ == "__main__":
     main()