Update app.py

app.py

@@ -12,6 +12,13 @@ from langchain_core.output_parsers import StrOutputParser
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 from langdetect import detect
 
+# ✅ Switched to Flan-T5 Model
+MODEL_ID = "google/flan-t5-large"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_ID)
+pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+
+
 # ✅ Device setup
 device = "cuda" if torch.cuda.is_available() else "cpu"
 print(f"✅ Using device: {device}")
@@ -31,12 +38,13 @@ st.set_page_config(page_title="HAL - NASA ChatBot", page_icon="🚀")
 if "chat_history" not in st.session_state:
     st.session_state.chat_history = [{"role": "assistant", "content": "Hello! How can I assist you today?"}]
 
-# ✅ Switched to Flan-T5 Model
-MODEL_ID = "google/flan-t5-large"
+def load_local_llm(model_id):
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+    model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+    return pipeline("text2text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+
+
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
-pipe = pipeline("text2text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
 
 llm = HuggingFacePipeline(pipeline=pipe)