idpate

app.py

@@ -12,7 +12,11 @@ llm = Llama(
 
 @app.get("/")
 def home():
-    return {"message":"Hello World"}
+    print("helloe here")
+    output= llm("What is the difference btw RAG and Fine tunning", max_tokens=1000)
+    print(output["choices"][0]["text"])
+    ## return the generate text in Json reposne
+    return {"output":output["choices"][0]["text"]}
 
 # Define a function to handle the GET request at `/generate`