Changes suggested by Helene

backend/src/agents/web_agent.py

@@ -32,7 +32,11 @@ async def web_general_search_core(search_query, llm, model) -> str:
         answer_to_user = await answer_user_ques(search_query, llm, model)
         answer_result = json.loads(answer_to_user)
         if answer_result["status"] == "error":
-            return ""
+            response = {
+                    "content": "Error in finding the answer.",
+                    "ignore_validation": "false"
+                }
+            return json.dumps(response, indent=4)
         logger.info(f'Answer found successfully {answer_result}')
         valid_answer = json.loads(answer_result["response"]).get("is_valid", "")
         if valid_answer:
@@ -149,7 +153,6 @@ async def web_pdf_download(pdf_url, llm, model) -> str:
 
 async def web_scrape_core(url: str) -> str:
     try:
-        logger.info(f"Scraping the price of the book from URL: {url}")
         # Scrape the content from the provided URL
         content = await perform_scrape(url)
         if not content:
@@ -162,7 +165,6 @@ async def web_scrape_core(url: str) -> str:
             }
         return json.dumps(response, indent=4)
     except Exception as e:
-        logger.error(f"Error in web_scrape_price_core: {e}")
         return json.dumps({"status": "error", "error": str(e)})
 
 

backend/src/prompts/templates/answer-user-ques.j2

@@ -51,4 +51,4 @@ Reply only in JSON format with the following structure:
 }
 
 
-Important: If the question is realted to real time data, the LLM should provide is_valid is false.
+Important: If the question is related to real time data, the LLM should provide is_valid is false.

backend/src/prompts/templates/best-tool.j2

@@ -11,15 +11,15 @@ Trust the information below completely (100% accurate)
 
 Pick 1 tool (no more than 1) from the list below to complete this task.
 Fit the correct parameters from the task to the tool arguments.
-Ensure that numerical values are formatted correctly, including the use of currency symbols (e.g., "$") and units of measurement (e.g., "million") if applicable.
+Ensure that numerical values are formatted correctly, including the use of currency symbols (e.g., "£") and units of measurement (e.g., "million") if applicable.
 Parameters with required as False do not need to be fit.
 Add if appropriate, but do not hallucinate arguments for these parameters
 
 {{ tools }}
 
 Important:
-If the task involves financial data, ensure that all monetary values are expressed with appropriate currency (e.g., "$") and rounded to the nearest million if specified.
-If the task involves scaling (e.g., thousands, millions), ensure that the extracted parameters reflect the appropriate scale (e.g., "$15 million", "$5000").
+If the task involves financial data, ensure that all monetary values are expressed with appropriate currency (e.g., "£") and rounded to the nearest million if specified.
+If the task involves scaling (e.g., thousands, millions), ensure that the extracted parameters reflect the appropriate scale (e.g., "£15 million", "£5000").
 
 From the task you should be able to extract the parameters. If it is data driven, it should be turned into a cypher query
 

backend/src/prompts/templates/create-search-term.j2

@@ -13,4 +13,4 @@ Reply only in JSON format, following this structure:
 {
     "search_term": "The optimized Google search term based on the user's question",
     "reasoning": "A sentence on why you chose that search term"
-}
+}

backend/src/prompts/templates/intent.j2

@@ -4,7 +4,7 @@ The question is:
 
 {{ question }} 
 
-The prvious chat history is: 
+The previous chat history is: 
 
 {{ chat_history }}
 
@@ -84,4 +84,4 @@ Finally, if no tool fits the task, return the following:
 }
 
 Important:
-Please always create the last intent to append the retrieved info in a 'conversation-history.txt' file and make sure this history file is always 'conversation-history.txt'
+Please always create the last intent to append the retrieved info in a 'conversation-history.txt' file and make sure this history file is always named 'conversation-history.txt'

backend/src/prompts/templates/math-solver.j2

@@ -23,3 +23,4 @@ query: Round 81.462 billion to the nearest million
     "steps": "1. Convert 81.462 billion to million by multiplying by 1000. Round the result to the nearest million.",
     "reasoning": "Rounding to the nearest million ensures that the result is represented in a more practical figure, without exceeding or falling short of the actual value."
 }
+

backend/src/prompts/templates/tool-selection-format.j2

@@ -1,4 +1,4 @@
-Reply only in json with the following format, in the tool_paramters please include the curreny and measuring scale used in the content provided.:
+Reply only in json with the following format, in the tool_parameters please include the currency and measuring scale used in the content provided.:
 
 
 {

backend/src/prompts/templates/validator.j2

@@ -27,7 +27,7 @@ Reasoning: The answer is for Spotify not Amazon.
 Task: Please find tesla's revenue every year since its creation.
 Answer: Tesla's annual revenue history from FY 2008 to FY 2023 is available, with figures for 2008 through 2020 taken from previous annual reports.
 Response: False
-Reasoning: The answer is not prvoding any actual figures but just talk about the figures.
+Reasoning: The answer is not providing any actual figures but just talk about the figures.
 
 Task: Please find tesla's revenue every year since its creation in the US dollars.
 Answer: Tesla's annual revenue in USD since its creation is as follows: 2024 (TTM) $75.92 billion, 2023 $75.95 billion, 2022 $67.33 billion, 2021 $39.76 billion, 2020 $23.10 billion, 2019 $18.52 billion, 2018 $16.81 billion, 2017 $8.70 billion, 2016 $5.67 billion, 2015 $2.72 billion, 2014 $2.05 billion, 2013 $1.21 billion, 2012 $0.25 billion, 2011 $0.13 billion, 2010 $75.88 million, 2009 $69.73 million.