Update app.py

app.py

@@ -1,64 +1,80 @@
+import os
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.document_loaders import PyPDFLoader
+from langchain.chains import RetrievalQA
+from langchain_groq import ChatGroq
 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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
+# Initialize Groq
+llm = ChatGroq(
+    api_key="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",
+    model_name="deepseek-r1-distill-llama-70b"
+)
 
-    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
+def create_rag_system():
+    try:
+        # 1. Load Documents
+        pdf_loader = PyPDFLoader("smarthome_hub_documentation.pdf")
+        pdf_docs = pdf_loader.load()
+        
+        # 2. Split Documents
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=2000,
+            chunk_overlap=200,
+            length_function=len,
+        )
+        
+        chunks = text_splitter.split_documents(pdf_docs)
+        
+        # 3. Create Embeddings and Vector Store
+        embeddings = HuggingFaceEmbeddings(
+            model_name="all-MiniLM-L6-v2"  # Smaller model
+        )
+        vectorstore = FAISS.from_documents(chunks, embeddings)
+        
+        return vectorstore
+    except Exception as e:
+        print(f"Error creating RAG system: {e}")
+        return None
 
-        response += token
-        yield response
+# Initialize the RAG system
+vectorstore = create_rag_system()
 
+def respond(message, history):
+    try:
+        if vectorstore is None:
+            return "Sorry, the system is currently unavailable. Please try again later."
+            
+        # Create QA chain for each query
+        qa_chain = RetrievalQA.from_chain_type(
+            llm=llm,
+            chain_type="stuff",
+            retriever=vectorstore.as_retriever(
+                search_type="mmr",
+                search_kwargs={"k": 3}
+            )
+        )
+        
+        # Get response
+        response = qa_chain.run(message)
+        return response
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# 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=respond,
+    title="SmartHome Hub X1000 Assistant",
+    description="Ask me anything about SmartHome Hub X1000!",
+    examples=[
+        "Apa saja fitur utama dari SmartHome Hub X1000?",
+        "Bagaimana cara menginstall SmartHome Hub X1000?",
+        "Jelaskan sistem keamanan SmartHome Hub X1000"
     ],
+    theme=gr.themes.Soft()
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()