Update app.py

app.py

@@ -1,36 +1,29 @@
 from fastapi import FastAPI
 from pydantic import BaseModel
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Load Model from Hugging Face Model Hub
-MODEL_NAME = "your_username/aws-bot-model"  # Replace with your actual Hugging Face model path
-model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
+# Load model and tokenizer
+MODEL_NAME = "meta-llama/Llama-3.2-1B"  # Replace with your model
+
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16)
 
-def generate_response(user_input: str):
-    inputs = tokenizer(user_input, return_tensors="pt", truncation=True, max_length=128)
-    outputs = model.generate(**inputs, max_length=128)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+def generate_response(prompt: str):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=200)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# FastAPI App
 app = FastAPI()
 
 class Query(BaseModel):
-    message: str
+    text: str
 
 @app.post("/chat")
 def chat(query: Query):
-    user_input = query.message.lower()
-    
-    # Placeholder for external API handling (Uncomment when you have API key)
-    # if is_unrelated_query(user_input):
-    #     return {"response": handle_external_query(user_input)}
-    
-    bot_response = generate_response(user_input)
-    return {"response": bot_response}
+    response = generate_response(query.text)
+    return {"response": response}
 
 @app.get("/")
 def root():
-    return {"message": "AWS Bot API is running!"}
+    return {"message": "AWS-Bot is running!"}