Delete sppech_input_interim.py

sppech_input_interim.py

@@ -1,194 +0,0 @@
-Hugging Face's logo
-Hugging Face
-Search models, datasets, users...
-Models
-Datasets
-Spaces
-Posts
-Docs
-Enterprise
-Pricing
-
-
-
-Spaces:
-
-DrishtiSharma
-/
-chat-w-docs-via-speech-or-text
-
-
-like
-1
-
-Logs
-App
-Files
-Community
-Settings
-chat-w-docs-via-speech-or-text
-/
-app.py
-
-DrishtiSharma's picture
-DrishtiSharma
-Update app.py
-230a23e
-verified
-3 minutes ago
-raw
-
-Copy download link
-history
-blame
-edit
-delete
-
-5.38 kB
-#ref: https://www.youtube.com/watch?v=3ZDVmzlM6Nc
-
-import os
-import chromadb
-import streamlit as st
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain_chroma import Chroma
-from langchain_groq import ChatGroq
-from langchain.memory import ConversationBufferMemory
-from langchain.chains import ConversationalRetrievalChain
-from PyPDF2 import PdfReader
-from groq import Groq
-from streamlit_webrtc import webrtc_streamer, AudioProcessorBase, WebRtcMode
-import av
-
-# Clear ChromaDB cache to fix tenant issue
-chromadb.api.client.SharedSystemClient.clear_system_cache()
-
-# Ensure required environment variables are set
-GROQ_API_KEY = os.getenv("GROQ_API_KEY")
-if not GROQ_API_KEY:
-    st.error("GROQ_API_KEY is not set. Please configure it in environment variables.")
-    st.stop()
-
-# Initialize Groq Client for transcription and LLM
-groq_client = Groq(api_key=GROQ_API_KEY)
-llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0, groq_api_key=GROQ_API_KEY)
-
-# Function to process PDFs and set up the vectorstore
-def process_and_store_pdfs(uploaded_files):
-    texts = []
-    for uploaded_file in uploaded_files:
-        reader = PdfReader(uploaded_file)
-        for page in reader.pages:
-            texts.append(page.extract_text())
-
-    embeddings = HuggingFaceEmbeddings()
-    vectorstore = Chroma.from_texts(texts, embedding=embeddings, persist_directory="vector_db_dir")
-    return vectorstore
-
-# Function to set up the chat chain
-def chat_chain(vectorstore):
-    retriever = vectorstore.as_retriever()
-    memory = ConversationBufferMemory(output_key="answer", memory_key="chat_history", return_messages=True)
-
-    chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        retriever=retriever,
-        chain_type="stuff",
-        memory=memory,
-        verbose=True,
-        return_source_documents=True
-    )
-    return chain
-
-# Transcribe audio using Groq Whisper
-def transcribe_audio(file_path):
-    """Transcribe audio using Groq's Whisper model."""
-    with open(file_path, "rb") as file:
-        transcription = groq_client.audio.transcriptions.create(
-            file=(file_path, file.read()),
-            model="distil-whisper-large-v3-en",
-            response_format="json",
-            language="en"
-        )
-    return transcription.text
-
-# Audio Processor Class for Recording
-class AudioProcessor(AudioProcessorBase):
-    def recv(self, frame: av.AudioFrame) -> av.AudioFrame:
-        return frame
-
-# Streamlit UI
-st.title("Chat with PDFs via Speech/Text 🎙️📝📚")
-
-uploaded_files = st.file_uploader("Upload PDF Files", accept_multiple_files=True, type=["pdf"])
-
-if uploaded_files:
-    vectorstore = process_and_store_pdfs(uploaded_files)
-    chain = chat_chain(vectorstore)
-    st.success("PDFs processed! Ready to chat.")
-
-    input_method = st.radio("Choose Input Method", ["Text Input", "Record Audio", "Upload Audio File"])
-
-    # Text Input Mode
-    if input_method == "Text Input":
-        query = st.text_input("Ask your question:")
-        if query:
-            with st.spinner("Thinking..."):
-                response = chain({"question": query})["answer"]
-                st.write(f"**Response:** {response}")
-
-    # Record Audio
-    elif input_method == "Record Audio":
-        st.write("Record your audio query:")
-        webrtc_ctx = webrtc_streamer(
-            key="record",
-            mode=WebRtcMode.SENDONLY,
-            audio_receiver_size=1024,
-            audio_processor_factory=AudioProcessor,
-            media_stream_constraints={"audio": True, "video": False},
-        )
-
-        if webrtc_ctx.audio_receiver:
-            st.write("Recording...")
-            audio_frames = []
-            while True:
-                frame = webrtc_ctx.audio_receiver.recv()
-                audio_frames.append(frame)
-                if len(audio_frames) > 5:  # Stop recording after a few frames
-                    break
-
-            # Save the recorded audio
-            audio_file_path = "recorded_audio.wav"
-            with av.open(audio_file_path, "w") as f:
-                for frame in audio_frames:
-                    f.write(frame)
-            st.success("Recording complete!")
-
-            # Transcribe and Generate Response
-            st.write("Transcribing audio...")
-            transcription = transcribe_audio(audio_file_path)
-            st.write(f"**You said:** {transcription}")
-
-            with st.spinner("Generating response..."):
-                response = chain({"question": transcription})["answer"]
-                st.write(f"**Response:** {response}")
-
-    # Upload Audio File Mode
-    elif input_method == "Upload Audio File":
-        uploaded_audio = st.file_uploader("Upload an audio file (.wav, .mp3)", type=["wav", "mp3"])
-        if uploaded_audio:
-            audio_file_path = "uploaded_audio.wav"
-            with open(audio_file_path, "wb") as f:
-                f.write(uploaded_audio.read())
-
-            st.audio(audio_file_path, format="audio/wav")
-            st.write("Transcribing audio...")
-            transcription = transcribe_audio(audio_file_path)
-            st.write(f"**You said:** {transcription}")
-
-            with st.spinner("Generating response..."):
-                response = chain({"question": transcription})["answer"]
-                st.write(f"**Response:** {response}")
-else:
-    st.info("Please upload PDF files to start chatting.")
-