Update app.py

app.py

@@ -9,18 +9,11 @@ huggingface_hub.login(token=os.environ["HF_TOKEN"])
 # Fava prompt
 INPUT = "Read the following references:\n{evidence}\nPlease identify all the errors in the following text using the information in the references provided and suggest edits if necessary:\n[Text] {output}\n[Edited] "
 
-article = """
-<center>
-The bot was trained to answer questions based on Rick and Morty dialogues. Ask Rick anything!
-<img src="images/fava.png" width=800px>
-</center>
-"""
+_article = f'<center><img src="images/fava.png" width=800px></center>'
 
 model = vllm.LLM(model="fava-uw/fava-model") 
 def result(passage, reference):
     prompt = [INPUT.format_map({"evidence":reference, "output":passage})]
-    print(prompt)
-    print("\n")
     sampling_params = vllm.SamplingParams(
         temperature=0,
         top_p=1.0,
@@ -48,5 +41,5 @@ def result(passage, reference):
     return f'<div style="font-weight: normal;">{output}</div>'; #output;
 
 if __name__ == "__main__":
-    demo = gradio.Interface(fn=result, flagging_dir="flagged/", inputs=["text", "text"], outputs="html", title="Fine-grained Hallucination Detection and Editing (FAVA)", description="Enter some text and a reference for the text and FAVA will detect and edit any hallucinations present.", article=article)
+    demo = gradio.Interface(fn=result, inputs=["text", "text"], outputs="html", title="Fine-grained Hallucination Detection and Editing (FAVA)", description="Enter some text and a reference for the text and FAVA will detect and edit any hallucinations present.", article=_article)
     demo.launch(share=True)