graph test

app.py

@@ -7,8 +7,9 @@ from typing import Any, Dict, List, Optional, TypedDict
 import gradio as gr
 import pandas as pd
 import requests
-from langchain_community.tools import DuckDuckGoSearchRun
-from langchain_community.utilities.wikipedia import WikipediaAPIWrapper
+
+from langchain_community.tools import DuckDuckGoSearchRun, WikipediaQueryRun
+from langchain_community.utilities import WikipediaAPIWrapper
 
 from langchain_core import messages
 from langchain_core.messages import (
@@ -48,7 +49,8 @@ Extract ALL Parameters Identify search terms, URLs, code, file paths
 Plan Steps: Break down the problem into logical steps required to reach the final answer
 2. Delegate Strategically
 For each step, choose the best  Agent Tool. Call the tool with a single string argument `request` containing ALL information the specialist needs
-Available Tools: `DuckDuckGoSearchAgent`, `CodeExecutorAgent`
+Available Tools: `DuckDuckGoSearchAgent`, `CodeExecutorAgent`, `WikipediaAgent`
+- For wikipedia searches, **strongly prefer** `WikipediaAgent` formatting the query like WikipediaAgent(`request`='search query')
 - For general web searches, **strongly prefer** `DuckDuckGoSearchAgent` formatting the query like DuckDuckGoSearchAgent(`request`='search query') for potentially higher quality results"
 - For standard Python execution, **strongly prefer** `CodeExecutorAgent` formatting the query like  BuiltinCodeExecutorAgent(`request`='python code') for reliability."
 
@@ -141,7 +143,8 @@ class BasicAgent:
 
     def wiki_search(self, state: AnswerState) -> Dict[str, Any]:
         print("[wiki_search] Searching for: " + str(state["search_request"]))
-        wiki_tool = WikipediaAPIWrapper()
+        api_wrapper = WikipediaAPIWrapper(top_k_results=1, doc_content_chars_max=5000)
+        wiki_tool = WikipediaQueryRun(api_wrapper=api_wrapper)
         results = wiki_tool.run(str(state["search_request"]))
         print(f"Wiki results: {results}")
         state["messages"].append(