Update helper_functions_api.py

helper_functions_api.py

@@ -72,6 +72,12 @@ llm_default_medium = "meta-llama/Llama-3-70b-chat-hf"
 
 SysPromptData = "You are an information retriever and summarizer, return only the factual information regarding the user query"
 SysPromptDefault = "You are an expert AI, complete the given task. Do not add any additional comments."
+SysPromptSearch = """You are a search query generator, create a concise Google search query, focusing only on the main topic and omitting additional redundant details, include year if necessory, 2024, Do not add any additional comments. OUTPUT ONLY THE SEARCH QUERY
+                        #Additional instructions:
+                        ##Use the following search operators if necessory
+                        OR #to cover multiple topics
+                        * #wildcard to match any word or phrase
+                        AND #to include specific topics."""
 
 import tiktoken # Used to limit tokens
 encoding = tiktoken.encoding_for_model("gpt-3.5-turbo") # Instead of Llama3 using available option/ replace if found anything better
@@ -214,12 +220,11 @@ def fetch_and_extract_content(data_format, urls, query):
     return all_text_with_urls
 
 
+@retry(tries=3, delay=0.25)
 def search_brave(query, num_results=5):
-
+    cleaned_query = re.sub(r'[^a-zA-Z0-9]+', '', query)
+    search_query = together_response(cleaned_query, model=llm_default_small, SysPrompt=SysPromptSearch, max_tokens = 25).strip()
+    cleaned_search_query = re.sub(r'[^a-zA-Z0-9*]+', '', search_query)
     brave = Brave(BRAVE_API_KEY)
-
-    search_results = brave.search(q=query, count=num_results)
-
+    search_results = brave.search(q=cleaned_search_query, count=num_results)
     return [url.__str__() for url in search_results.urls]
-
-