Create app.py

app.py

@@ -0,0 +1,200 @@
+import os
+import streamlit as st
+from groq import Groq
+from PyPDF2 import PdfReader
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import whisper
+from gtts import gTTS
+from tempfile import NamedTemporaryFile
+import json
+import gdown
+
+# Initialize Groq client
+client = Groq(api_key="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")
+
+# Load embedding model
+embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Load Whisper model
+whisper_model = whisper.load_model("base")
+
+# Initialize FAISS
+embedding_dimension = 384  # Dimension of embeddings from the model
+index = faiss.IndexFlatL2(embedding_dimension)
+metadata = []
+
+# List of Google Drive PDF links
+google_drive_links = [
+    "https://drive.google.com/file/d/1_9vZ5jw6Lpoh7jDnqqIiyq082d3uT2dp/view?usp=sharing"
+]
+
+# Streamlit App Configuration
+st.set_page_config(page_title="Voice/Text Chatbot with RAG PDF Query", page_icon="🔊", layout="wide")
+
+# Title
+st.markdown("<h1 style='text-align: center; color: #006400;'> ProManage AI </h1>", unsafe_allow_html=True)
+st.markdown("---")
+
+# Sidebar for PDF Upload
+st.sidebar.header("Upload Your PDF File")
+uploaded_file = st.sidebar.file_uploader("Upload a PDF file", type="pdf")
+
+# Function to extract file ID from Google Drive link
+def extract_file_id(drive_link):
+    return drive_link.split("/d/")[1].split("/view")[0]
+
+# Function to download PDF from Google Drive
+def download_pdf_from_google_drive(file_id, output_path):
+    download_url = f"https://drive.google.com/uc?id={file_id}"
+    gdown.download(download_url, output_path, quiet=False)
+
+# Function for text extraction from PDF
+def extract_text_from_pdf(file):
+    reader = PdfReader(file)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function for text-to-speech
+def text_to_speech(response_text):
+    tts = gTTS(text=response_text, lang="en")
+    audio_file = NamedTemporaryFile(delete=False, suffix=".mp3")
+    tts.save(audio_file.name)
+    return audio_file.name
+
+# Save embeddings and metadata
+def save_database(faiss_index, metadata, file_path="vector_database.json"):
+    all_embeddings = []
+    for i in range(faiss_index.ntotal):
+        all_embeddings.append(faiss_index.reconstruct(i).tolist())
+    data = {
+        "embeddings": all_embeddings,
+        "metadata": metadata
+    }
+    with open(file_path, "w") as f:
+        json.dump(data, f)
+    st.success(f"Vector database saved to {file_path}!")
+
+# Process Google Drive PDFs
+st.sidebar.header("Processing Google Drive PDFs")
+with st.spinner("Downloading and processing Google Drive PDFs..."):
+    for link in google_drive_links:
+        file_id = extract_file_id(link)
+        output_pdf_path = f"downloaded_{file_id}.pdf"
+
+        # Download PDF
+        if not os.path.exists(output_pdf_path):  # Avoid re-downloading
+            download_pdf_from_google_drive(file_id, output_pdf_path)
+
+        # Extract text and process
+        pdf_text = extract_text_from_pdf(output_pdf_path)
+        if pdf_text.strip():
+            # Split text into chunks and create embeddings
+            chunk_size = 500
+            chunks = [pdf_text[i:i + chunk_size] for i in range(0, len(pdf_text), chunk_size)]
+            embeddings = embedding_model.encode(chunks, convert_to_numpy=True)
+            index.add(embeddings)
+
+            # Store metadata
+            metadata.extend([{"chunk": chunk, "source": f"Google Drive: {output_pdf_path}"} for chunk in chunks])
+
+# PDF Text Processing
+if uploaded_file:
+    pdf_text = extract_text_from_pdf(uploaded_file)
+    if pdf_text.strip():
+        st.success("PDF text successfully extracted!")
+        with st.expander("View Extracted Text", expanded=False):
+            st.write(pdf_text[:3000] + "..." if len(pdf_text) > 3000 else pdf_text)
+
+        # Split text into chunks and create embeddings
+        chunk_size = 500
+        chunks = [pdf_text[i:i + chunk_size] for i in range(0, len(pdf_text), chunk_size)]
+        embeddings = embedding_model.encode(chunks, convert_to_numpy=True)
+        index.add(embeddings)
+
+        # Store metadata
+        metadata.extend([{"chunk": chunk, "source": uploaded_file.name} for chunk in chunks])
+        save_database(index, metadata)
+
+        st.success(f"Processed {len(chunks)} chunks and stored embeddings in FAISS!")
+
+# Main Chatbot Interface
+st.header("🤖 Gen-AI Powered Chatbot")
+
+# Input Method Selection
+input_method = st.radio("Select Input Method:", options=["Text", "Audio"])
+
+if input_method == "Text":
+    st.subheader("💬 Text Query Input")
+    text_query = st.text_input("Enter your query:")
+    if st.button("Submit Text Query"):
+        if text_query:
+            try:
+                # Search FAISS for nearest chunks
+                query_embedding = embedding_model.encode([text_query], convert_to_numpy=True)
+                distances, indices = index.search(query_embedding, k=5)
+                relevant_chunks = [metadata[idx]["chunk"] for idx in indices[0]]
+
+                # Generate response using Groq API
+                prompt = f"Use these references to answer the query:\n\n{relevant_chunks}\n\nQuery: {text_query}"
+                chat_completion = client.chat.completions.create(
+                    messages=[{"role": "user", "content": prompt}],
+                    model="llama-3.3-70b-versatile",
+                )
+                response = chat_completion.choices[0].message.content
+
+                # Display text response
+                st.write(f"**Chatbot Response:** {response}")
+
+                # Generate and play audio response
+                response_audio_path = text_to_speech(response)
+                st.audio(response_audio_path, format="audio/mp3", start_time=0)
+
+            except Exception as e:
+                st.error(f"Error processing your query: {e}")
+
+elif input_method == "Audio":
+    st.subheader("🎤 Audio Query Input")
+    uploaded_audio = st.file_uploader("Upload your audio file", type=["m4a", "mp3", "wav"])
+
+    if uploaded_audio:
+        try:
+            audio_data = uploaded_audio.read()
+            audio_file = NamedTemporaryFile(delete=False, suffix=".m4a")
+            audio_file.write(audio_data)
+            audio_file_path = audio_file.name
+
+            st.success("Audio file uploaded successfully!")
+
+            # Transcribe the audio using Whisper model
+            transcription = whisper_model.transcribe(audio_file_path)["text"]
+            st.write(f"**You said:** {transcription}")
+
+            # Search FAISS for nearest chunks
+            query_embedding = embedding_model.encode([transcription], convert_to_numpy=True)
+            distances, indices = index.search(query_embedding, k=5)
+            relevant_chunks = [metadata[idx]["chunk"] for idx in indices[0]]
+
+            # Generate response using Groq API
+            prompt = f"Use these references to answer the query:\n\n{relevant_chunks}\n\nQuery: {transcription}"
+            chat_completion = client.chat.completions.create(
+                messages=[{"role": "user", "content": prompt}],
+                    model="llama-3.3-70b-versatile",
+                )
+            response = chat_completion.choices[0].message.content
+
+            # Display text response
+            st.write(f"**Chatbot Response:** {response}")
+
+            # Generate and play audio response
+            response_audio_path = text_to_speech(response)
+            st.audio(response_audio_path, format="audio/mp3", start_time=0)
+
+        except Exception as e:
+            st.error(f"Error processing your query: {e}")
+
+# Footer
+st.markdown("<p style='text-align: center;'> Muhammad Zaeem Ilyas-PMP®| PMO NESPAK </p>", unsafe_allow_html=True)