Update app.py

app.py

@@ -9,7 +9,7 @@ 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
-
+from streamlit_webrtc import webrtc_streamer, WebRtcMode, ClientSettings
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
 
@@ -78,10 +78,34 @@ 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)
+    # Audio recording
+    webrtc_ctx = webrtc_streamer(
+        key="audio_recorder",
+        mode=WebRtcMode.SENDONLY,
+        audio_receiver_size=256,
+        client_settings=ClientSettings(
+            media_stream_constraints={"audio": True},
+        ),
+    )
+
+    if webrtc_ctx.audio_receiver:
+        audio_frames = []
+        while True:
+            frame = webrtc_ctx.audio_receiver.get_frame(timeout=1)
+            if frame is None:
+                break
+            audio_frames.append(frame)
+
+        if len(audio_frames) > 0:
+            audio_bytes = b"".join(frame.to_ndarray().tobytes() for frame in audio_frames)
+            with open("query.wav", "wb") as f:
+                f.write(audio_bytes)
+
+            model = whisper.load_model("large")
+            result = model.transcribe("query.wav", language="en", fp16=False)
+            user_question = result["text"]
+            st.write("Transcribed Question:", user_question)
+            user_input(user_question)
 
     with st.sidebar:
         st.title("Menu:")
@@ -91,8 +115,7 @@ def main():
                 raw_text = get_pdf_text(pdf_docs)
                 text_chunks = get_text_chunks(raw_text)
                 get_vector_store(text_chunks)
-                st.success("Done")
-
+            st.success("Done")
 
 
 if __name__ == "__main__":