Added filereader, removed wikipedia. 30%

.gitignore

@@ -173,4 +173,6 @@ cython_debug/
 # PyPI configuration file
 .pypirc
 
-.langgraph_api/
+.langgraph_api/
+
+files/

agent.py

@@ -8,14 +8,13 @@ from langgraph.prebuilt import tools_condition, ToolNode
 from langchain_core.runnables import RunnableConfig
 
 # Wikepedia tool
-from langchain_community.tools import WikipediaQueryRun
-from langchain_community.utilities import WikipediaAPIWrapper
 from langchain_community.document_loaders import WikipediaLoader
-from langchain_community.retrievers import WikipediaRetriever
 
 # Tavily web search
 from langchain_community.tools.tavily_search import TavilySearchResults
 
+# Python loader
+from langchain_community.document_loaders import PythonLoader
 
 load_dotenv()
 
@@ -51,7 +50,7 @@ def wikipedia_search(query: str) -> str:
 
     for next_doc in documents:
         formatted_doc = f'<Document source="{next_doc.metadata["source"]}" title="{next_doc.metadata.get("title", "")}"/>\n{next_doc.page_content}\n</Document>'
-        formatted_search_docs.join(formatted_doc)
+        formatted_search_docs = formatted_search_docs + formatted_doc
 
     result = f"{{wiki_results: {formatted_search_docs}}}"
 
@@ -89,7 +88,30 @@ def web_search(query: str) -> str:
     return result
 
 
-tools = [meaning_of_life, wikipedia_search, web_search]
+# https://python.langchain.com/api_reference/community/document_loaders/langchain_community.document_loaders.python.PythonLoader.html
+def python_file_reader(file_name: str) -> str:
+    """Reads a python file and returns the content
+
+    Args:
+        file_name: the filename to read
+    """
+    file_path = os.path.join(os.path.dirname(__file__), "files", file_name)
+    loader = PythonLoader(file_path=file_path)
+    documents = loader.load()
+    formatted_search_docs = "\n\n---\n\n"
+
+    for next_doc in documents:
+        formatted_doc = (
+            f'<Document source="{file_name}"/>\n{next_doc.page_content}\n</Document>'
+        )
+        formatted_search_docs = formatted_search_docs + formatted_doc
+
+    result = f"{{python_code: {formatted_search_docs}}}"
+
+    return result
+
+
+tools = [meaning_of_life, web_search, python_file_reader]
 
 
 # --- GRAPH ---
@@ -180,7 +202,7 @@ if __name__ == "__main__":
     for m in messages["messages"]:
         m.pretty_print()
 
-"""
+
 
     print("******** TESTING WEB SEARCH TOOL ********")
     # expected answer is "Samuel"
@@ -189,3 +211,11 @@ if __name__ == "__main__":
     messages = graph.invoke({"messages": messages})
     for m in messages["messages"]:
         m.pretty_print()
+"""
+
+    print("******** PYTHON LOAD TOOL ********")
+    question = "what does this python code do? filename is f918266a-b3e0-4914-865d-4faa564f1aef.py"
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

app.py

@@ -80,6 +80,31 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
+    # 2.5 Download Files
+    for item in questions_data:
+        task_id = item.get("task_id")
+        file_name = item.get("file_name")
+        file_url = f"{api_url}/files/{task_id}"
+        try:
+            if file_name != "":
+                file_path = os.path.join("files", file_name)
+                if not os.path.exists(file_path):
+                    print(f"Downloading file from {file_url} for task {task_id}...")
+                    response = requests.get(file_url, timeout=15)
+                    response.raise_for_status()
+                    file_path = os.path.join("files", file_name)
+                    with open(file_path, "wb") as f:
+                        f.write(response.content)
+                    print(f"Downloaded {file_name}.")
+                else:
+                    print(f"File {file_name} already exists. Skipping download.")
+        except requests.exceptions.RequestException as e:
+            print(f"Error downloading file for task {task_id}: {e}")
+        except Exception as e:
+            print(
+                f"An unexpected error occurred downloading file for task {task_id}: {e}"
+            )
+
     # 3. Run your Agent
     results_log = []
     answers_payload = []
@@ -87,6 +112,12 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+
+        # if there is a file add it to the question
+        file_name = item.get("file_name")
+        if file_name != "":
+            question_text += " File to use is " + file_name
+
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue