Update app.py

app.py

@@ -29,10 +29,17 @@ print("Loading the model...")
 llm = Llama(model_path=model_path)
 print("Model loaded successfully!")
 
-def generate_response(prompt, temperature=0.7, top_p=1.0, max_tokens=256):
+def generate_response(message, history, temperature=0.7, top_p=1.0, max_tokens=256):
+    # history_langchain_format = []
+    # for human, ai in history:
+    #     history_langchain_format.append(HumanMessage(content=human))
+    #     history_langchain_format.append(AIMessage(content=ai))
+
+    # history_langchain_format.append(HumanMessage(content=message))
+    
     try:
-        response = llm(prompt, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
-        return response["choices"][0]["text"].strip()
+        gpt_response = llm(message, max_tokens=max_tokens, temperature=temperature, top_p=top_p)
+        return gpt_response["choices"][0]["text"].strip()
     except Exception as e:
         return f"Error generating response: {e}"
 
@@ -43,4 +50,4 @@ if __name__ == "__main__":
         description=description,
     )
 
-    rag.launch()
+    rag.launch(share=True)