Enhance regulatory sources in settings.py by adding full names for each source and improving formatting for better readability. Update web_tools.py to utilize the new SOURCE_FULL_NAMES for clearer title handling in regulatory updates.

config/settings.py

@@ -11,34 +11,55 @@ OPENAI_BASE_URL = "https://api.keywordsai.co/api/"
 # Regulatory websites mapping
 REGULATORY_SOURCES = {
     "US": {
-        "SEC": "https://www.sec.gov/news/pressreleases",  
-        "FDA": "https://www.fda.gov/news-events/fda-newsroom/press-announcements",  
-        "FTC": "https://www.ftc.gov/news-events/news/press-releases",  
+        "SEC": "https://www.sec.gov/news/pressreleases",
+        "FDA": "https://www.fda.gov/news-events/fda-newsroom/press-announcements",
+        "FTC": "https://www.ftc.gov/news-events/news/press-releases",
         "Federal Register": "https://www.federalregister.gov/documents/current",
-        "CFTC": "https://www.cftc.gov/PressRoom/PressReleases", 
-        "FDIC": "https://www.fdic.gov/news/press-releases/",  
-        "FINRA": "https://www.finra.org/media-center/newsreleases", 
-        "Federal Reserve Board": "https://www.federalreserve.gov/newsevents/pressreleases.htm",  
+        "CFTC": "https://www.cftc.gov/PressRoom/PressReleases",
+        "FDIC": "https://www.fdic.gov/news/press-releases/",
+        "FINRA": "https://www.finra.org/media-center/newsreleases",
+        "Federal Reserve Board": "https://www.federalreserve.gov/newsevents/pressreleases.htm",
     },
     "EU": {
-        "ESMA": "https://www.esma.europa.eu/press-news/esma-news",  
-        "EBA": "https://www.eba.europa.eu/publications-and-media",  
-        "EIOPA": "https://www.eiopa.europa.eu/media/news_en",  
-        "European Parliament News": "https://www.europarl.europa.eu/news/en/press-room",  
-        "ECB": "https://www.ecb.europa.eu/press/pr/html/index.en.html",  
+        "ESMA": "https://www.esma.europa.eu/press-news/esma-news",
+        "EBA": "https://www.eba.europa.eu/publications-and-media",
+        "EIOPA": "https://www.eiopa.europa.eu/media/news_en",
+        "European Parliament News": "https://www.europarl.europa.eu/news/en/press-room",
+        "ECB": "https://www.ecb.europa.eu/press/pr/html/index.en.html",
     },
     "Asia": {
-        "Japan FSA": "https://www.fsa.go.jp/en/news/",  
-        "Reserve Bank of India (RBI)": "https://www.rbi.org.in/Scripts/BS_PressReleaseDisplay.aspx",  
+        "Japan FSA": "https://www.fsa.go.jp/en/news/",
+        "Reserve Bank of India (RBI)": "https://www.rbi.org.in/Scripts/BS_PressReleaseDisplay.aspx",
     },
     "Global": {
-        "BIS": "https://www.bis.org/press/index.htm",  
-        "IMF": "https://www.imf.org/en/News",  
-        "World Bank": "https://www.worldbank.org/en/news/all",  
-        "OECD": "https://www.oecd.org/newsroom/",  
+        "BIS": "https://www.bis.org/press/index.htm",
+        "IMF": "https://www.imf.org/en/News",
+        "World Bank": "https://www.worldbank.org/en/news/all",
+        "OECD": "https://www.oecd.org/newsroom/",
     },
 }
 
+SOURCE_FULL_NAMES = {
+    "SEC": "U.S. Securities and Exchange Commission",
+    "FDA": "U.S. Food and Drug Administration",
+    "FTC": "Federal Trade Commission",
+    "Federal Register": "Federal Register",
+    "CFTC": "Commodity Futures Trading Commission",
+    "FDIC": "Federal Deposit Insurance Corporation",
+    "FINRA": "Financial Industry Regulatory Authority",
+    "Federal Reserve Board": "Federal Reserve Board",
+    "ESMA": "European Securities and Markets Authority",
+    "EBA": "European Banking Authority",
+    "EIOPA": "European Insurance and Occupational Pensions Authority",
+    "European Parliament News": "European Parliament News",
+    "ECB": "European Central Bank",
+    "Japan FSA": "Financial Services Agency of Japan",
+    "Reserve Bank of India (RBI)": "Reserve Bank of India",
+    "BIS": "Bank for International Settlements",
+    "IMF": "International Monetary Fund",
+    "World Bank": "World Bank",
+    "OECD": "Organisation for Economic Co-operation and Development",
+}
 
 # UI settings
 AVATAR_IMAGES = (
@@ -49,4 +70,3 @@ AVATAR_IMAGES = (
 # Default chat parameters
 DEFAULT_LLM_TEMPERATURE = 0.3
 DEFAULT_LLM_MODEL = "gpt-4.1-mini"
-

tools/web_tools.py

@@ -3,12 +3,13 @@ from typing import Dict
 
 from tavily import TavilyClient
 
-from config.settings import REGULATORY_SOURCES, TAVILY_API_KEY
+from config.settings import REGULATORY_SOURCES, SOURCE_FULL_NAMES, TAVILY_API_KEY
 from tools.llm import call_llm
 
 # Initialize Tavily client
 tavily_client = TavilyClient(api_key=TAVILY_API_KEY)
 
+
 class WebTools:
     def __init__(self):
         self.cached_searches = {}
@@ -28,7 +29,9 @@ class WebTools:
         urls_to_crawl = REGULATORY_SOURCES.get(region, REGULATORY_SOURCES["US"])
         all_results = []
 
-        crawl_instructions = f"{industry} regulatory updates, compliance, {keywords}, 30d"
+        crawl_instructions = (
+            f"{industry} regulatory updates, compliance, {keywords}, 30d"
+        )
 
         # Crawl regulatory sites
         for source_name, url in list(urls_to_crawl.items())[:3]:
@@ -37,11 +40,14 @@ class WebTools:
                     url=url, max_depth=2, limit=5, instructions=crawl_instructions
                 )
                 for result in crawl_response.get("results", []):
+                    title = result.get("title")
+                    if not title or title == "No Title...":
+                        title = SOURCE_FULL_NAMES.get(source_name, source_name)
                     all_results.append(
                         {
                             "source": source_name,
-                            "url": url,
-                            "title": result.get("title", ""),
+                            "url": result.get("url", url),
+                            "title": title,
                             "content": result.get("raw_content", "")[:1500],
                         }
                     )