created tool to get latest SEC filing info

app.py

@@ -4,19 +4,98 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
-
 from Gradio_UI import GradioUI
+from xml.etree import ElementTree
+from typing import Union, List, Dict, Any
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
 @tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
+def get_lastest_filing_info(company: str = None, cik: str = None, type: str = "10-K", dateb: str = None, start: str = '0', count: str = '50') -> Union[List[Dict[str, Any]], Dict[str, str]]:
+    """A tool that gets the most recent 10-K filings (including addendums) of a company from the SEC.
     Args:
-        arg1: the first argument
-        arg2: the second argument
+        company: The name of the company.
+        cik: The Central Index Key (CIK) of the company.
+        type: The type of filing. (Default is "10-K" for this function.)
+        dateb: The date before which the filings were made (format: YYYYMMDD).
+        start: The starting point for pagination.
+        count: The number of filings to retrieve per page.
+    Returns:
+        The latest filings of a company from the SEC.
     """
-    return "What magic will you build ?"
+    # Validate dateb format
+    if dateb:
+        try:
+            datetime.datetime.strptime(dateb, "%Y%m%d")
+        except ValueError:
+            return {"error": "Invalid dateb format. Use YYYYMMDD."}
+    
+    # Ensure dateb is not after the current time
+    current_date = datetime.datetime.now().strftime("%Y%m%d")
+    if dateb and dateb > current_date:
+        return {"error": "dateb cannot be after the current date."}
+    
+    base_url = "https://www.sec.gov/cgi-bin/browse-edgar?action=getcurrent"
+    params = {
+        "CIK": cik,
+        "type": type,
+        "company": company,
+        "dateb": dateb,
+        "owner": "include",
+        "start": start,
+        "count": count,
+        "output": "atom"
+    }
+    
+    response = requests.get(base_url, params=params)
+    if response.status_code != 200:
+        return {"error": "Failed to retrieve data from SEC"}
+    
+    filings = []
+    try:
+        feed = response.content
+        root = ElementTree.fromstring(feed)
+        # Process filings from the first page
+        for entry in root.findall("{http://www.w3.org/2005/Atom}entry"):
+            filing = {
+                "title": entry.find("{http://www.w3.org/2005/Atom}title").text,
+                "link": entry.find("{http://www.w3.org/2005/Atom}link").attrib['href'],
+                "summary": entry.find("{http://www.w3.org/2005/Atom}summary").text,
+                "updated": entry.find("{http://www.w3.org/2005/Atom}updated").text,
+                "category": entry.find("{http://www.w3.org/2005/Atom}category").attrib['term'],
+                "id": entry.find("{http://www.w3.org/2005/Atom}id").text
+            }
+            # Only include filings where category starts with "10-K"
+            if filing["category"].startswith("10-K"):
+                filings.append(filing)
+        
+        # Fetch additional pages until we have 100 filings or no more are available
+        while len(filings) < 100:
+            params["start"] = str(int(params["start"]) + int(params["count"]))
+            response = requests.get(base_url, params=params)
+            if response.status_code != 200:
+                break
+            feed = response.content
+            root = ElementTree.fromstring(feed)
+            entries = root.findall("{http://www.w3.org/2005/Atom}entry")
+            if not entries:
+                break
+            for entry in entries:
+                filing = {
+                    "title": entry.find("{http://www.w3.org/2005/Atom}title").text,
+                    "link": entry.find("{http://www.w3.org/2005/Atom}link").attrib['href'],
+                    "summary": entry.find("{http://www.w3.org/2005/Atom}summary").text,
+                    "updated": entry.find("{http://www.w3.org/2005/Atom}updated").text,
+                    "category": entry.find("{http://www.w3.org/2005/Atom}category").attrib['term'],
+                    "id": entry.find("{http://www.w3.org/2005/Atom}id").text
+                }
+                if filing["category"].startswith("10-K"):
+                    filings.append(filing)
+                    if len(filings) >= 100:
+                        break
+
+    except Exception as e:
+        return {"error": f"Failed to parse XML: {str(e)}"}
+    
+    return filings
 
 @tool
 def get_current_time_in_timezone(timezone: str) -> str: