Update app.py

app.py

@@ -2295,7 +2295,9 @@ def generate_query_tree(context: str, breadth: int, depth: int, selected_engines
     prompt = f"""
 
     Generate a list of {breadth} search queries relevant to the following context:
+
     "{context}"
+
 // Requirements
 - The queries should be suitable for a search engine.
 - Each query should combine terms using logical operators (AND, OR) where appropriate.
@@ -2315,9 +2317,8 @@ def generate_query_tree(context: str, breadth: int, depth: int, selected_engines
 Do not include any extra text, markdown formatting, or commentary. Output the JSON starting from "{{" and ending with "}}".
 Now generate the result.
 """
-    # Increase the token limit to allow more output (e.g., 150 tokens)
-    messages = []  # Use prompt directly in openai_call, messages is handled there.
-    llm_response = openai_call(prompt=prompt, messages=messages, temperature=0, max_tokens_param=150)
+    messages = []
+    llm_response = openai_call(prompt=prompt, messages=messages, model="o3-mini", temperature=0, max_tokens_param=150)
     logging.info(f"Generated query tree: {llm_response}")
 
     cleaned_response = llm_response.strip().strip("`").strip()
@@ -2884,7 +2885,7 @@ def iterative_deep_research_gen(initial_query: str, reportstyle: str, breadth: i
         if followup_suggestions:
             # Deduplicate follow-up suggestions before adding them to context.
             unique_suggestions = list(set(followup_suggestions))
-            combined_context += "\nFollow-up suggestions: " + ", ".join(unique_suggestions)
+            combined_context += "\n\nFollow-up suggestions: " + ", ".join(unique_suggestions)
         queries = generate_serp_queries(combined_context, breadth, depth, initial_query, selected_engines, results_per_query)
 
         # ===================================================================