new

app.py

@@ -61,6 +61,7 @@ def inference(input_sentence, max_length, sample_or_greedy, seed=42):
     )
     res = pipe(input_sentence)
     generation = res["generated_text"]
+    print(generation)
 
     #data = query(payload)
 
@@ -68,7 +69,7 @@ def inference(input_sentence, max_length, sample_or_greedy, seed=42):
     #    return (None, None, f"<span style='color:red'>ERROR: {data['error']} </span>")
 
     #generation = data[0]["generated_text"].split(input_sentence, 1)[1]
-    generation  = res["generated_text"].split(input_sentence, 1)[1]
+    generation  = res[0]["generated_text"].split(input_sentence, 1)[1]
 
     return (
         before_prompt
@@ -76,7 +77,7 @@ def inference(input_sentence, max_length, sample_or_greedy, seed=42):
         + prompt_to_generation
         + generation
         + after_generation,
-        data[0]["generated_text"],
+        res[0]["generated_text"],
         "",
     )