Update app.py

app.py

@@ -1,64 +1,101 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-"""
-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")
+# Configuration
+DOCS_DIR = "business_docs"
+EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
+MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.1"
 
+# Initialize components once at startup
+def initialize_system():
+    # Load and process PDFs from business_docs folder
+    if not os.path.exists(DOCS_DIR):
+        raise FileNotFoundError(f"Business documents folder '{DOCS_DIR}' not found")
+        
+    pdf_files = [os.path.join(DOCS_DIR, f) for f in os.listdir(DOCS_DIR) if f.endswith(".pdf")]
+    if not pdf_files:
+        raise ValueError(f"No PDF files found in {DOCS_DIR} folder")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Process documents
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200
+    )
+    
+    texts = []
+    for pdf in pdf_files:
+        loader = PyPDFLoader(pdf)
+        pages = loader.load_and_split(text_splitter)
+        texts.extend(pages)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Create vector store
+    embeddings = HuggingFaceEmbeddings(model_name=EMBEDDING_MODEL)
+    vector_store = FAISS.from_documents(texts, embeddings)
+    
+    # Load model with quantization for faster inference
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_NAME,
+        device_map="auto",
+        load_in_8bit=True
+    )
+    
+    return vector_store, model, tokenizer
 
-    messages.append({"role": "user", "content": message})
+# Initialize system components
+try:
+    vector_store, model, tokenizer = initialize_system()
+    print("System initialized successfully with business documents")
+except Exception as e:
+    print(f"Initialization error: {str(e)}")
+    raise
 
-    response = ""
+# Response generation with context
+def generate_response(query):
+    # Retrieve relevant context
+    docs = vector_store.similarity_search(query, k=3)
+    context = "\n".join([doc.page_content for doc in docs])
+    
+    # Create instruction prompt
+    prompt = f"""<s>[INST] You are a customer support agent. 
+    Answer ONLY using information from the provided business documents.
+    If unsure, say "I don't have information about that."
+    
+    Context: {context}
+    Question: {query} [/INST]"""
+    
+    # Generate response
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=500,
+        temperature=0.3,
+        do_sample=True
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True).split("[/INST]")[-1].strip()
 
-    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
+# Chat interface
+with gr.Blocks() as demo:
+    gr.Markdown("## Business Support Chatbot\nAsk questions about our services!")
+    
+    chatbot = gr.Chatbot(label="Conversation")
+    msg = gr.Textbox(label="Type your question")
+    clear = gr.Button("Clear History")
+    
+    def respond(message, chat_history):
+        try:
+            response = generate_response(message)
+        except Exception as e:
+            response = "Sorry, I'm having trouble answering right now. Please try again later."
+        chat_history.append((message, response))
+        return "", chat_history
+    
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
-        response += token
-        yield response
-
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()