Update app.py

app.py

@@ -4,6 +4,10 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 import chromadb
 from sentence_transformers import SentenceTransformer
+import logging
+
+# Initialize logging
+logging.basicConfig(level=logging.INFO)
 
 # Initialize the Llama model
 llm = Llama(
@@ -52,7 +56,7 @@ def generate_text(
         input_prompt += f"{interaction[0]} [/INST] {interaction[1]} </s><s> [INST] "
     input_prompt += f"{message} [/INST] "
 
-    print("Input prompt:", input_prompt)  # Debugging output
+    logging.info("Input prompt:\n%s", input_prompt)  # Debugging output
 
     temp = ""
     output = llm(
@@ -67,30 +71,29 @@ def generate_text(
     )
     for out in output:
         temp += out["choices"][0]["text"]
+        logging.info("Model output:\n%s", temp)  # Log model output
         yield temp
 
 # Define the Gradio interface
-demo = gr.ChatInterface(
-    generate_text,
-    title="llama-cpp-python on GPU with ChromaDB",
-    description="Running LLM with context retrieval from ChromaDB",
+demo = gr.Interface(
+    fn=generate_text,
+    title="LLM Chatbot with ChromaDB Integration",
+    description="Generate responses based on context and user queries.",
     examples=[
         ["I have leftover rice, what can I make out of it?"],
         ["Can I make lunch for two people with this?"],
     ],
-    cache_examples=False,
-    retry_btn=None,
-    undo_btn="Delete Previous",
-    clear_btn="Clear",
-    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)"),
+    inputs=[
+        gr.Textbox(label="Message"),
+        gr.Textbox(label="System message", default="You are a friendly Chatbot."),
+        gr.Textbox(label="History", default="[('USER', 'Hi there!')]"),
+        gr.Slider(minimum=1, maximum=2048, step=1, default=512, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, step=0.1, default=0.7, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, step=0.05, default=0.95, label="Top-p (nucleus sampling)"),
     ],
+    outputs=gr.Textbox(label="Response"),
+    live=True,
 )
 
 if __name__ == "__main__":
     demo.launch()
-
-