Update app.py

app.py

@@ -1,64 +1,108 @@
+import os
+import requests
+from io import BytesIO
+from PyPDF2 import PdfReader
+from tempfile import NamedTemporaryFile
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from groq import Groq
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Initialize Groq client
+client = Groq(api_key="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")
 
+# Predefined list of Google Drive links
+drive_links = [
+    "https://drive.google.com/file/d/1vku86qnrvJtCtHTxKXvSOJwtCYC6u3sp/view",
+    # Add more links here as needed
+]
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Function to download PDF from Google Drive
+def download_pdf_from_drive(drive_link):
+    file_id = drive_link.split('/d/')[1].split('/')[0]
+    download_url = f"https://drive.google.com/uc?id={file_id}&export=download"
+    response = requests.get(download_url)
+    if response.status_code == 200:
+        return BytesIO(response.content)
+    else:
+        raise Exception("Failed to download the PDF file from Google Drive.")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Function to extract text from a PDF
+def extract_text_from_pdf(pdf_stream):
+    pdf_reader = PdfReader(pdf_stream)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
 
-    messages.append({"role": "user", "content": message})
+# Function to split text into chunks
+def chunk_text(text, chunk_size=500, chunk_overlap=50):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=chunk_size, chunk_overlap=chunk_overlap
+    )
+    return text_splitter.split_text(text)
 
-    response = ""
+# Function to create embeddings and store them in FAISS
+def create_embeddings_and_store(chunks):
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    vector_db = FAISS.from_texts(chunks, embedding=embeddings)
+    return vector_db
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Function to query the vector database and interact with Groq
+def query_vector_db(query, vector_db):
+    # Retrieve relevant documents
+    docs = vector_db.similarity_search(query, k=3)
+    context = "\n".join([doc.page_content for doc in docs])
 
-        response += token
-        yield response
+    # Interact with Groq API
+    chat_completion = client.chat.completions.create(
+        messages=[
+            {"role": "system", "content": f"Use the following context:\n{context}"},
+            {"role": "user", "content": query},
+        ],
+        model="llama3-8b-8192",
+    )
+    return chat_completion.choices[0].message.content
 
+# Process the predefined Google Drive links
+def process_drive_links():
+    all_chunks = []
+    for link in drive_links:
+        try:
+            # Download PDF
+            pdf_stream = download_pdf_from_drive(link)
+            # Extract text
+            text = extract_text_from_pdf(pdf_stream)
+            # Chunk text
+            chunks = chunk_text(text)
+            all_chunks.extend(chunks)
+        except Exception as e:
+            return f"Error processing link {link}: {e}"
+    
+    if all_chunks:
+        # Generate embeddings and store in FAISS
+        vector_db = create_embeddings_and_store(all_chunks)
+        return vector_db
+    return None
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+# Gradio interface
+vector_db = process_drive_links()
+
+def gradio_query_interface(user_query):
+    if vector_db is None:
+        return "Error: Could not process Google Drive links."
+    if not user_query:
+        return "Please enter a query."
+    response = query_vector_db(user_query, vector_db)
+    return response
 
+iface = gr.Interface(
+    fn=gradio_query_interface,
+    inputs=gr.Textbox(label="Enter your query:"),
+    outputs=gr.Textbox(label="Response from LLM:"),
+    title="RAG-Based Application with Google Drive Support",
+    description="This application processes predefined Google Drive links, extracts text, and uses embeddings for querying."
+)
 
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()