update

app.py

@@ -58,10 +58,13 @@ def search(query, index="pubmed", num_docs=3):
 
     return docs
 
-def analyse(text: str) -> str:
+def analyse(reference: str, passage: str) -> str:
+    fava_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] "
+    prompt = [fava_input.format_map({"evidence": reference, "output": passage})]
+
     model = vllm.LLM(model="fava-uw/fava-model") 
     sampling_params = vllm.SamplingParams(temperature=0, top_p=1.0, max_tokens=500)
-    outputs = model.generate(text, sampling_params)
+    outputs = model.generate(prompt, sampling_params)
     outputs = [it.outputs[0].text for it in outputs]
     output = outputs[0].replace("<mark>", "<span style='color: green; font-weight: bold;'> ")
     output = output.replace("</mark>", " </span>")
@@ -146,7 +149,7 @@ def rag_pipeline(prompt, index="pubmed", num_docs=3, model_name="HuggingFaceH4/z
         print('HF_RESPONSE', hf_response)
         response = hf_response[0]['generated_text']
     
-    analysed_response = analyse(response)
+    analysed_response = analyse(joined_docs, response)
 
     # Return the generated text and the documents
     return response, analysed_response, joined_docs