Update app.py

app.py

@@ -1,4 +1,7 @@
 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
@@ -9,140 +12,90 @@ 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
 
+# Environment and API setup
 load_dotenv()
 os.getenv("GOOGLE_API_KEY")
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
-
-def transcribe_audio(audio_file):
-    model = whisper.load_model("small")
-    audio = whisper.load_audio(audio_file)
-    audio = whisper.pad_or_trim(audio)
-    mel = whisper.log_mel_spectrogram(audio).to(model.device)
-    prediction = model.transcribe(mel, language="en", fp16=False)
-    return prediction['text']
-
-
 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)
-
-    print(response)
+    response = chain({"input_documents":docs, "question": user_question}, return_only_outputs=True)
     st.write("Reply: ", response["output_text"])
 
-import streamlit.components.v1 as components
-
-def voice_recorder(key=None):
-    component_html = """
-    <script src="https://cdn.jsdelivr.net/npm/@ffmpeg/ffmpeg"></script>
-    <button id="recordButton">Record</button>
-    <button id="stopButton" disabled>Stop</button>
-    <audio id="audioPlayback" controls></audio>
-    <script>
-    let recordButton = document.getElementById("recordButton");
-    let stopButton = document.getElementById("stopButton");
-    let audioPlayback = document.getElementById("audioPlayback");
-
-    let recorder;
-    let audioData;
-
-    recordButton.onclick = () => {
-        navigator.mediaDevices.getUserMedia({ audio: true })
-        .then(stream => {
-            const mediaRecorder = new MediaRecorder(stream);
-            mediaRecorder.start();
-            const audioChunks = [];
-            mediaRecorder.addEventListener("dataavailable", event => {
-                audioChunks.push(event.data);
-            });
-            recorder = mediaRecorder;
-            stopButton.disabled = false;
-            recordButton.disabled = true;
-        });
-    };
-
-    stopButton.onclick = () => {
-        recorder.stop();
-        recorder.addEventListener("stop", () => {
-            const audioBlob = new Blob(audioChunks);
-            const audioUrl = URL.createObjectURL(audioBlob);
-            audioPlayback.src = audioUrl;
-            const reader = new FileReader();
-            reader.readAsDataURL(audioBlob);
-            reader.onload = () => {
-                window.parent.postMessage({ audioData: reader.result }, '*');
-            };
-        });
-        stopButton.disabled = true;
-        recordButton.disabled = false;
-    };
-    </script>
-    """
-    audio_base64 = components.html(component_html, height=150, key=key)
-    return audio_base64
-    
 def main():
     st.set_page_config("Chat PDF")
     st.header("Chat with PDF using Gemini💁")
 
-    # Replace the existing audio file uploader with the custom voice recorder component
-    audio_data = voice_recorder("audio_recorder")
-    if audio_data and st.button("Process Recorded Audio"):
-        with st.spinner("Processing audio..."):
-            user_question = transcribe_audio(audio_data)
+    # 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.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)
 
@@ -157,4 +110,4 @@ def main():
                 st.success("Done")
 
 if __name__ == "__main__":
-    main()
+    main()