Update app.py

app.py

@@ -9,25 +9,10 @@ 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 whisper
 
-
-
-load_dotenv()
-os.getenv("GOOGLE_API_KEY")
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
 
-# Load the Whisper model
-model_1 = whisper.load_model("large")
-
-def speech_to_text(audio_path):
-    # Load and decode the audio file
-    result = model_1.transcribe(audio_path, language="en",fp16=False)
-    return result['text']
-
-
-
 def get_pdf_text(pdf_docs):
     text=""
     for pdf in pdf_docs:
@@ -61,7 +46,7 @@ def get_conversational_chain():
     """
 
     model = ChatGoogleGenerativeAI(model="gemini-pro",
-                             temperature=0.3)
+                             temperature=0.1)
 
     prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
@@ -73,7 +58,7 @@ def get_conversational_chain():
 def user_input(user_question):
     embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
     
-    new_db = FAISS.load_local("faiss_index", embeddings)
+    new_db = FAISS.load_local("faiss_index", embeddings,allow_dangerous_deserialization= True)
     docs = new_db.similarity_search(user_question)
 
     chain = get_conversational_chain()
@@ -87,36 +72,28 @@ def user_input(user_question):
     st.write("Reply: ", response["output_text"])
 
 
-# Constants
-DURATION = 5  # seconds
-SAMPLERATE = 44100  # Hz
 
 
 def main():
     st.set_page_config("Chat PDF")
     st.header("QnA with Multiple PDF files💁")
 
+    user_question = st.text_input("Ask a Question from the PDF Files")
+
+    if user_question:
+        user_input(user_question)
+
     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)
-        audio_file = st.file_uploader("Upload your voice query", type=['wav', 'mp3', 'ogg'])
         if st.button("Submit & Process"):
-            if pdf_docs and audio_file:
-                with st.spinner("Processing..."):
-                    # Handle PDF text extraction and processing
-                    raw_text = get_pdf_text(pdf_docs)
-                    text_chunks = get_text_chunks(raw_text)
-                    get_vector_store(text_chunks)
-
-                    # Handle audio processing
-                    audio_path = audio_file.name
-                    with open(audio_path, "wb") as f:
-                        f.write(audio_file.getbuffer())
-                    user_question = speech_to_text(audio_path)
-                    st.write(f"Your question: {user_question}")
-                    user_input(user_question)
-
-                    st.success("Done")
+            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("Done")
+
+
 
 if __name__ == "__main__":
-    main()
+    main()