Update app.py

app.py

@@ -8,16 +8,13 @@ import gradio as gr
 import torch
 import torch.nn as nn
 import torch.optim as optim
-from torch.utils.data import DataLoader, IterableDataset
-from sklearn.ensemble import IsolationForest, RandomForestClassifier
+from torch.utils.data import DataLoader, Dataset
+from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import OneHotEncoder
-from sklearn.neural_network import MLPClassifier
 from deap import base, creator, tools, algorithms
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline, AutoModelForSequenceClassification
 import gc
-import multiprocessing as mp
-from joblib import Parallel, delayed
 
 warnings.filterwarnings('ignore', category=FutureWarning, module='huggingface_hub.file_download')
 
@@ -153,7 +150,7 @@ def evolve_emotions():
     emotions['ideal_state']['percentage'] = ideal_state
 
 def predict_emotion(context):
-    emotion_prediction_pipeline = pipeline('text-classification', model=emotion_prediction_model, tokenizer=emotion_prediction_tokenizer, return_all_scores=True)
+    emotion_prediction_pipeline = pipeline('text-classification', model=emotion_prediction_model, tokenizer=emotion_prediction_tokenizer, top_k=None)
     predictions = emotion_prediction_pipeline(context)
     emotion_scores = {prediction['label']: prediction['score'] for prediction in predictions[0]}
     emotion_pred = max(emotion_scores, key=emotion_scores.get)
@@ -187,7 +184,7 @@ def generate_text(prompt, emotion=None, max_length=100):
     return finetuned_lm_tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 def optimize_ai_model(emotion_history):
-    if not emotion_history:
+    if len(emotion_history) < 2:
         return None, None
 
     contexts = [entry['context'] for entry in emotion_history]
@@ -197,9 +194,6 @@ def optimize_ai_model(emotion_history):
     X = encoder.fit_transform(np.array(contexts).reshape(-1, 1))
     y = np.array(pd.Categorical(emotions).codes)
 
-    if len(X) == 0 or len(y) == 0:
-        return None, None
-
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
     
     classifier = RandomForestClassifier(n_estimators=100, random_state=42)
@@ -208,7 +202,7 @@ def optimize_ai_model(emotion_history):
     score = classifier.score(X_test, y_test)
     return classifier, score
 
-def respond(context, previous_responses, previous_emotions):
+def respond(context, conversation_history, emotion_history_state):
     normalized_context = normalize_context(context)
     emotion_pred = predict_emotion(normalized_context)
 
@@ -222,7 +216,7 @@ def respond(context, previous_responses, previous_emotions):
 
     evolve_emotions()
 
-    response_prompt = f"{normalized_context}\n\n{previous_responses}\n\n{emotion_pred}"
+    response_prompt = f"{normalized_context}\n\n{conversation_history}\n\n{emotion_pred}"
     generated_response = generate_text(response_prompt, emotion=emotion_pred)
 
     return generated_response, emotion_pred
@@ -246,3 +240,6 @@ with gr.Blocks() as demo:
     submit_button.click(respond_wrapper, [context_input, conversation_history, emotion_history_state], [response_output, emotion_output, conversation_history, emotion_history_state])
 
     demo.launch(share=True)
+
+gc.collect()
+torch.cuda.empty_cache()