fixing cache issue

app.py

@@ -1,12 +1,11 @@
 import os
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/cache"  # MUST be before HF imports
+
 from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import uvicorn
 
-# Set writable cache directory
-os.environ["TRANSFORMERS_CACHE"] = "/tmp/cache"
-
 MODEL_NAME = "16pramodh/t2s_model"
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
@@ -18,13 +17,9 @@ class QueryRequest(BaseModel):
 
 @app.post("/predict")
 def predict(request: QueryRequest):
-    try:
-        inputs = tokenizer(request.text, return_tensors="pt")
-        outputs = model.generate(**inputs, max_length=256)
-        sql_query = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return {"sql": sql_query}
-    except Exception as e:
-        return {"error": str(e)}
+    inputs = tokenizer(request.text, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=256)
+    return {"sql": tokenizer.decode(outputs[0], skip_special_tokens=True)}
 
 if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    uvicorn.run(app, host="0.0.0.0", port=7860)