Update app.py

app.py

@@ -1,64 +1,88 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_community.vectorstores import FAISS
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain_huggingface import HuggingFaceHub
+import zipfile
 
-"""
-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")
+# Extract PDFs from zip file
+def extract_pdfs_from_zip(zip_path="data.zip", extract_to="data"):
+    if not os.path.exists(zip_path):
+        raise FileNotFoundError(f"Zip file '{zip_path}' not found.")
+    
+    if not os.path.exists(extract_to):
+        os.makedirs(extract_to)
+    
+    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+        zip_ref.extractall(extract_to)
 
+def load_pdfs(directory="data"):
+    if not os.path.exists(directory):
+        raise FileNotFoundError(f"The directory '{directory}' does not exist.")
+    
+    raw_documents = []
+    for filename in os.listdir(directory):
+        if filename.endswith(".pdf"):
+            loader = PyMuPDFLoader(os.path.join(directory, filename))
+            docs = loader.load()
+            raw_documents.extend(docs)
+    return raw_documents
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def split_documents(documents):
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    return text_splitter.split_documents(documents)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def initialize_qa_system():
+    print("📦 Extracting PDFs from zip...")
+    extract_pdfs_from_zip()
+    
+    print("🔄 Loading PDFs...")
+    raw_docs = load_pdfs()
+    print(f"✅ Loaded {len(raw_docs)} raw documents.")
 
-    messages.append({"role": "user", "content": message})
+    if len(raw_docs) == 0:
+        raise ValueError("No PDF documents found in the 'data' directory.")
 
-    response = ""
+    print("🪓 Splitting documents into chunks...")
+    docs = split_documents(raw_docs)
+    print(f"✅ Split into {len(docs)} chunks.")
 
-    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
+    print("🧠 Generating embeddings...")
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-        response += token
-        yield response
+    print("📦 Creating FAISS vector store...")
+    db = FAISS.from_documents(docs, embeddings)
+    print("✅ Vector store created successfully!")
 
+    print("🤖 Initializing LLM...")
+    llm = HuggingFaceHub(
+        repo_id="google/flan-t5-xxl",
+        model_kwargs={"temperature": 0.5, "max_length": 512}
+    )
+    
+    qa = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=db.as_retriever(search_kwargs={"k": 3})
+    )
+    return qa
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Initialize the QA system
+qa_system = initialize_qa_system()
+
+def chat_response(message, history):
+    response = qa_system({"query": message})
+    return response["result"]
+
+# Create Gradio interface
 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)",
-        ),
-    ],
+    fn=chat_response,
+    title="PDF Knowledge Chatbot",
+    description="Ask questions about the content in your PDF documents"
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()