Update app.py

app.py

@@ -1,7 +1,4 @@
 import streamlit as st
-from bokeh.models.widgets import Button
-from bokeh.models import CustomJS
-from streamlit_bokeh_events import streamlit_bokeh_events
 from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 import os
@@ -12,110 +9,113 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
 from dotenv import load_dotenv
+import speech_recognition as sr
 
-# Load environment variables and configure API
 load_dotenv()
 os.getenv("GOOGLE_API_KEY")
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
+
+
+
+
+
 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=10000, chunk_overlap=1000)
     chunks = text_splitter.split_text(text)
     return chunks
 
+
 def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
     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
+    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:
     """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+
+    model = ChatGoogleGenerativeAI(model="gemini-pro",
+                             temperature=0.3)
+
+    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):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
+    
     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)
+
+    
+    response = chain(
+        {"input_documents":docs, "question": user_question}
+        , return_only_outputs=True)
+
+    print(response)
     st.write("Reply: ", response["output_text"])
 
-def main():
-    st.set_page_config("Chat PDF")
-    st.header("Chat with PDF using Gemini💁")
 
-    # Organizing layout to separate PDF upload and STT
-    col1, col2 = st.columns(2)
+def record_audio():
+    r = sr.Recognizer()
+    with sr.Microphone() as source:
+        st.write("Please speak your question...")
+        audio = r.listen(source)
+        try:
+            text = r.recognize_google(audio)
+            st.write("You said: " + text)
+            return text
+        except sr.UnknownValueError:
+            st.error("Could not understand audio")
+            return None
+        except sr.RequestError as e:
+            st.error(f"Could not request results; {e}")
+            return None
 
-    with col1:
-        st.subheader("Upload PDF")
-        pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True)
-        if st.button("Process PDF"):
-            with st.spinner("Processing PDF..."):
+ef main():
+    st.set_page_config("Chat PDF")
+    st.header("Chat with PDF using Gemini💁")
+    
+    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)
+        if st.button("Submit & Process"):
+            with st.spinner("Processing..."):
                 raw_text = get_pdf_text(pdf_docs)
                 text_chunks = get_text_chunks(raw_text)
                 get_vector_store(text_chunks)
-                st.success("PDF processing complete.")
-
-    with col2:
-        st.subheader("Voice Question")
-        # Bokeh button to activate speech recognition
-        stt_button = Button(label="Speak", width=100)
-        stt_button.js_on_event("button_click", CustomJS(code="""
-            var recognition = new webkitSpeechRecognition();
-            recognition.continuous = true;
-            recognition.interimResults = true;
-        
-            recognition.onresult = function (e) {
-                var value = "";
-                for (var i = e.resultIndex; i < e.results.length; ++i) {
-                    if (e.results[i].isFinal) {
-                        value += e.results[i][0].transcript;
-                    }
-                }
-                if (value != "") {
-                    document.dispatchEvent(new CustomEvent("GET_TEXT", {detail: value}));
-                }
-            }
-            recognition.onerror = function (event) {
-                console.error('Speech recognition error', event);
-            }
-            recognition.start();
-            """))
-
-        # Streamlit Bokeh event for receiving transcribed text
-        result = streamlit_bokeh_events(
-            stt_button,
-            events="GET_TEXT",
-            key="listen",
-            refresh_on_update=False,
-            override_height=75,
-            debounce_time=0
-        )
-
-        # Process the transcribed text
-        if result:
-            if "GET_TEXT" in result:
-                user_question = result.get("GET_TEXT")
-                st.write(f"Transcribed Question: {user_question}")
-                user_input(user_question)
+                st.success("Done")
+
+    # User can choose to input question via text or voice
+    user_question = st.text_input("Ask a Question from the PDF Files")
+    if st.button("Record Question via Microphone"):
+        user_question = record_audio()
+
+    if user_question:
+        user_input(user_question)
 
 if __name__ == "__main__":
-    main()
+    main()