Update app.py

app.py

@@ -2,25 +2,22 @@ import os
 import gradio as gr
 import numpy as np
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, TextGenerationPipeline
+from transformers import pipeline
 from sklearn.datasets import fetch_california_housing
 from sklearn.linear_model import LinearRegression, LogisticRegression
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import r2_score, accuracy_score
 
-# ─── 1) LOAD LOCAL LLM ─────────────────────────────────────────────────────────
-model_dir = "model"  # folder to upload your safetensors+configs into
+# ─── 1) LOAD A PUBLIC LLM ──────────────────────────────────────────────────────
 device = 0 if torch.cuda.is_available() else -1
-
-tokenizer = AutoTokenizer.from_pretrained(model_dir, local_files_only=True)
-model     = AutoModelForCausalLM.from_pretrained(model_dir, local_files_only=True)
-generator = TextGenerationPipeline(
-    model=model,
-    tokenizer=tokenizer,
+generator = pipeline(
+    "text-generation",
+    model="distilgpt2",
+    tokenizer="distilgpt2",
     device=device,
     max_new_tokens=100,
     do_sample=True,
-    temperature=0.7
+    temperature=0.7,
 )
 
 def chat_response(prompt: str) -> str:
@@ -28,26 +25,26 @@ def chat_response(prompt: str) -> str:
     return out[0]["generated_text"].strip()
 
 # ─── 2) PREPARE HOUSING ML MODELS ───────────────────────────────────────────────
-data    = fetch_california_housing()
-X, y    = data.data, data.target
+data = fetch_california_housing()
+X, y = data.data, data.target
 
 # linear regression
 Xtr, Xte, ytr, yte = train_test_split(X, y, test_size=0.2, random_state=42)
-reg     = LinearRegression().fit(Xtr, ytr)
-r2      = r2_score(yte, reg.predict(Xte))
+reg = LinearRegression().fit(Xtr, ytr)
+r2  = r2_score(yte, reg.predict(Xte))
 
-# logistic classification (above/below median)
-y_bin   = (y > np.median(y)).astype(int)
+# logistic classification
+y_bin = (y > np.median(y)).astype(int)
 Xtr2, Xte2, ytr2, yte2 = train_test_split(X, y_bin, test_size=0.2, random_state=42)
-clf     = LogisticRegression(max_iter=1000).fit(Xtr2, ytr2)
-acc     = accuracy_score(yte2, clf.predict(Xte2))
+clf = LogisticRegression(max_iter=1000).fit(Xtr2, ytr2)
+acc = accuracy_score(yte2, clf.predict(Xte2))
 
-# ─── 3) ORCHESTRATOR ───────────────────────────────────────────────────────────
+# ─── 3) ORCHESTRATOR / STATE MACHINE ─────────────────────────────────────────
 def respond(message, chat_history, state):
     stage   = state.get("stage", "chat")
     ml_type = state.get("ml_type")
 
-    # clarify step
+    # Clarify step
     if stage == "clarify":
         m = message.lower()
         if "linear" in m:
@@ -57,40 +54,40 @@ def respond(message, chat_history, state):
             state.update(stage="ml", ml_type="classification")
             chat_history.append(("Bot","Running logistic classification…"))
         else:
-            chat_history.append(("Bot","⚠️ Please say ‘linear regression’ or ‘classification’"))
+            chat_history.append(("Bot","⚠️ Say ‘linear regression’ or ‘classification’."))
             return chat_history, state
 
     # ML execution
     if state["stage"] == "ml":
         if state["ml_type"] == "regression":
-            chat_history.append(("Bot",f"✅ Regression R²={r2:.3f}\nCoefs={np.round(reg.coef_,3).tolist()}"))
+            chat_history.append(("Bot",f"✅ R²={r2:.3f}\nCoefs={np.round(reg.coef_,3).tolist()}"))
         else:
-            chat_history.append(("Bot",f"✅ Classification accuracy={acc:.3f}"))
+            chat_history.append(("Bot",f"✅ Accuracy={acc:.3f}"))
         state.update(stage="chat", ml_type=None)
         return chat_history, state
 
-    # detect ML intent
+    # Detect intent
     if any(k in message.lower() for k in ["predict","regression","classification"]):
         state["stage"] = "clarify"
         chat_history.append(("Bot","Sure—linear regression or classification?"))
         return chat_history, state
 
-    # fallback to LLM
+    # Fallback to LLM
     reply = chat_response(message)
     chat_history.append(("Bot", reply))
     return chat_history, state
 
 # ─── 4) GRADIO UI ───────────────────────────────────────────────────────────────
 with gr.Blocks() as demo:
-    gr.Markdown("## 🤖 Local‐LLM + Housing‐ML Chatbot")
-    chat = gr.Chatbot()
-    txt  = gr.Textbox(placeholder="Type here…", show_label=False)
-    state = gr.State({"stage":"chat","ml_type":None})
-    txt.submit(respond, [txt, chat, state], [chat, state])
+    gr.Markdown("## 🤖 LLM + Housing‐ML Chatbot")
+    chat    = gr.Chatbot()
+    user_in = gr.Textbox(placeholder="Type here…", show_label=False)
+    state   = gr.State({"stage":"chat","ml_type":None})
+    user_in.submit(respond, [user_in, chat, state], [chat, state])
 
-# this .queue() creates /api/predict so Spaces detects your app
+# queue() creates the /api/predict endpoint that Spaces needs
 demo = demo.queue()
 
-if __name__=="__main__":
+if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
     demo.launch(server_name="0.0.0.0", server_port=port)