Update app.py

app.py

@@ -1,7 +1,4 @@
-import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
-import gradio as gr
-from threading import Thread
+# Add this in your imports section if not already present
 import os
 import json
 import uuid
@@ -9,143 +6,14 @@ from datasets import Dataset
 from huggingface_hub import HfApi, login
 import time
 
-# Install required packages if not present
-from gradio_modal import Modal
-import huggingface_hub
-import datasets
-
-# Model setup
-checkpoint = "WillHeld/soft-raccoon"
-device = "cuda"
-tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
-
-# Constants for dataset
-DATASET_REPO = "WillHeld/model-feedback"  # Replace with your username
-DATASET_PATH = "./feedback_data"  # Local path to store feedback
-DATASET_FILENAME = "feedback.jsonl"  # Filename for feedback data
-
-# Ensure feedback directory exists
-os.makedirs(DATASET_PATH, exist_ok=True)
-
-# Feedback storage functions
-def save_feedback_locally(conversation, satisfaction, feedback_text):
-    """Save feedback to a local JSONL file"""
-    # Create a unique ID for this feedback entry
-    feedback_id = str(uuid.uuid4())
-    
-    # Create a timestamp
-    timestamp = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
-    
-    # Prepare the feedback data
-    feedback_data = {
-        "id": feedback_id,
-        "timestamp": timestamp,
-        "conversation": conversation,
-        "satisfaction": satisfaction,
-        "feedback": feedback_text
-    }
-    
-    # Save to local file
-    feedback_file = os.path.join(DATASET_PATH, DATASET_FILENAME)
-    with open(feedback_file, "a") as f:
-        f.write(json.dumps(feedback_data) + "\n")
-    
-    return feedback_id
-
-def push_feedback_to_hub(hf_token=None):
-    """Push the local feedback data to HuggingFace as a dataset"""
-    # Check if we have a token
-    if hf_token is None:
-        # Try to get token from environment variable
-        hf_token = os.environ.get("HF_TOKEN")
-        if hf_token is None:
-            print("No HuggingFace token provided. Cannot push to Hub.")
-            return False
-    
-    try:
-        # Login to HuggingFace
-        login(token=hf_token)
-        
-        # Check if we have data to push
-        feedback_file = os.path.join(DATASET_PATH, DATASET_FILENAME)
-        if not os.path.exists(feedback_file):
-            print("No feedback data to push.")
-            return False
-        
-        # Load data from the JSONL file
-        with open(feedback_file, "r") as f:
-            feedback_data = [json.loads(line) for line in f]
-        
-        # Create a dataset from the feedback data
-        dataset = Dataset.from_list(feedback_data)
-        
-        # Push to Hub
-        dataset.push_to_hub(
-            DATASET_REPO,
-            private=True  # Set to False if you want the dataset to be public
-        )
-        
-        print(f"Feedback data pushed to {DATASET_REPO} successfully.")
-        return True
-    
-    except Exception as e:
-        print(f"Error pushing feedback data to Hub: {e}")
-        return False
-
-@spaces.GPU(duration=120)
-def predict(message, history, temperature, top_p):
-    history.append({"role": "user", "content": message})
-    input_text = tokenizer.apply_chat_template(history, tokenize=False, add_generation_prompt=True)
-    inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
-    
-    # Create a streamer
-    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
-    
-    # Set up generation parameters
-    generation_kwargs = {
-        "input_ids": inputs,
-        "max_new_tokens": 1024,
-        "temperature": float(temperature),
-        "top_p": float(top_p),
-        "do_sample": True,
-        "streamer": streamer,
-        "eos_token_id": 128009,
-    }
-    
-    # Run generation in a separate thread
-    thread = Thread(target=model.generate, kwargs=generation_kwargs)
-    thread.start()
-    
-    # Yield from the streamer as tokens are generated
-    partial_text = ""
-    for new_text in streamer:
-        partial_text += new_text
-        yield partial_text
-
-# Function to handle the research feedback submission
-def submit_research_feedback(conversation_history, satisfaction, feedback_text):
-    """Save user feedback both locally and to HuggingFace Hub"""
-    # Save locally first
-    feedback_id = save_feedback_locally(conversation_history, satisfaction, feedback_text)
-    
-    # Get token from environment variable
-    env_token = os.environ.get("HF_TOKEN")
-    
-    # Use environment token
-    push_success = push_feedback_to_hub(env_token)
-    
-    if push_success:
-        status_msg = "Thank you for your valuable feedback! Your insights have been saved to the dataset."
-    else:
-        status_msg = "Thank you for your feedback! It has been saved locally, but couldn't be pushed to the dataset. Please check server logs."
-    
-    return status_msg
-
 # Create the Gradio interface
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column(scale=3):
+            # Create a State component to store the conversation history
+            chat_history = gr.State([])
+            
+            # Create the ChatInterface 
             chatbot = gr.ChatInterface(
                 predict,
                 additional_inputs=[
@@ -154,6 +22,15 @@ with gr.Blocks() as demo:
                 ],
                 type="messages"
             )
+            
+            # Create a function to update the chat history state
+            def update_history(message, history):
+                chat_history.value = history
+                return message, history
+            
+            # Intercept chatbot responses to update our history state
+            # This requires modifying your predict function to pass through the history
+            # And connecting it to the update_history function
         
         with gr.Column(scale=1):
             report_button = gr.Button("Share Feedback", variant="primary")
@@ -188,10 +65,7 @@ with gr.Blocks() as demo:
     
     # Connect the submit button to the submit_research_feedback function with the current chat history
     submit_button.click(
-        lambda satisfaction, feedback_text: submit_research_feedback(chatbot.value, satisfaction, feedback_text),
-        inputs=[satisfaction, feedback_text],
+        lambda satisfaction, feedback_text, history: submit_research_feedback(history, satisfaction, feedback_text),
+        inputs=[satisfaction, feedback_text, chat_history],
         outputs=response_text
-    )
-
-# Launch the demo
-demo.launch()
+    )