prompt adjusted

app.py

@@ -72,7 +72,7 @@ def llm_expand_query(query):
   """ Expands a query to variations of fulltext searches """
 
   response = client.chat.completions.create(
-    model="gpt-4o",
+    model="gpt-4o-mini",
     messages=[
       {
         "role": "user",
@@ -108,7 +108,7 @@ def llm_expand_query(query):
     response_format={
       "type": "text"
     },
-    temperature=1,
+    temperature=0,
     max_tokens=2048,
     top_p=1,
     frequency_penalty=0,
@@ -121,7 +121,7 @@ def llm_generate_answer(prompt):
   """ Generate a response from the LLM """
 
   response = client.chat.completions.create(
-    model="gpt-4o",
+    model="gpt-4o-mini",
     messages=[
       {
         "role": "system",
@@ -131,12 +131,13 @@ def llm_generate_answer(prompt):
             "text": """You are part of a Retrieval Augmented Generation system
             (RAG) and are asked with a query and a context of results. Generate an
             answer substantiated by the results provided and citing them using
-            their index when used to provide an answer text. Do not generate text
-            that is not grounded in a reference, so all paragraphs should cite a
+            their index when used to provide an answer text. Do not put two or more
+            references together (ex: use [1][2] instead of [1,2]. Do not generate an answer
+            that cannot be entailed from cited abstract, so all paragraphs should cite a
             search result. End the answer with the query and a brief answer as
             summary of the previous discussed results. Do not consider results
-            that are not related to the query and, if no specif answer can be
-            provided, explain that in the brief answer."""
+            that are not related to the query and, if no specific answer can be
+            provided, assert that in the brief answer."""
           }
         ]
       },
@@ -153,7 +154,7 @@ def llm_generate_answer(prompt):
     response_format={
       "type": "text"
     },
-    temperature=1,
+    temperature=0,
     max_tokens=2048,
     top_p=1,
     frequency_penalty=0,
@@ -185,7 +186,7 @@ def clean_refs(answer, results):
 
   new_i = 1
   for i in unique_ordered:
-    answer = answer.replace(f"[{i}]", f"[**__NEW_REF_ID_{new_i}**]")
+    answer = answer.replace(f"[{i}]", f"**[__NEW_REF_ID_{new_i}]**")
     new_i += 1
   answer = answer.replace("__NEW_REF_ID_", "")