From 706ebd8f9c4b64563bc4dc384faebe17464d7fce Mon Sep 17 00:00:00 2001 From: Alex Iribarren Date: Sun, 16 Apr 2023 17:30:57 +0200 Subject: [PATCH] Enforce maximum Wikipedia query length (#2969) I got the following stacktrace when the agent was trying to search Wikipedia with a huge query: ``` Thought:{ "action": "Wikipedia", "action_input": "Outstanding is a song originally performed by the Gap Band and written by member Raymond Calhoun. The song originally appeared on the group's platinum-selling 1982 album Gap Band IV. It is one of their signature songs and biggest hits, reaching the number one spot on the U.S. R&B Singles Chart in February 1983. \"Outstanding\" peaked at number 51 on the Billboard Hot 100." } Traceback (most recent call last): File "/usr/src/app/tests/chat.py", line 121, in answer = agent_chain.run(input=question) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/chains/base.py", line 216, in run return self(kwargs)[self.output_keys[0]] ^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/chains/base.py", line 116, in __call__ raise e File "/usr/local/lib/python3.11/site-packages/langchain/chains/base.py", line 113, in __call__ outputs = self._call(inputs) ^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/agents/agent.py", line 828, in _call next_step_output = self._take_next_step( ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/agents/agent.py", line 725, in _take_next_step observation = tool.run( ^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/tools/base.py", line 73, in run raise e File "/usr/local/lib/python3.11/site-packages/langchain/tools/base.py", line 70, in run observation = self._run(tool_input) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/agents/tools.py", line 17, in _run return self.func(tool_input) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/langchain/utilities/wikipedia.py", line 40, in run search_results = self.wiki_client.search(query) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/wikipedia/util.py", line 28, in __call__ ret = self._cache[key] = self.fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/site-packages/wikipedia/wikipedia.py", line 109, in search raise WikipediaException(raw_results['error']['info']) wikipedia.exceptions.WikipediaException: An unknown error occured: "Search request is longer than the maximum allowed length. (Actual: 373; allowed: 300)". Please report it on GitHub! ``` This commit limits the maximum size of the query passed to Wikipedia to avoid this issue. --- langchain/utilities/wikipedia.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/langchain/utilities/wikipedia.py b/langchain/utilities/wikipedia.py index 5b7ab964c0a..811a6258553 100644 --- a/langchain/utilities/wikipedia.py +++ b/langchain/utilities/wikipedia.py @@ -3,6 +3,8 @@ from typing import Any, Dict, Optional from pydantic import BaseModel, Extra, root_validator +WIKIPEDIA_MAX_QUERY_LENGTH = 300 + class WikipediaAPIWrapper(BaseModel): """Wrapper around WikipediaAPI. @@ -37,7 +39,7 @@ class WikipediaAPIWrapper(BaseModel): def run(self, query: str) -> str: """Run Wikipedia search and get page summaries.""" - search_results = self.wiki_client.search(query) + search_results = self.wiki_client.search(query[:WIKIPEDIA_MAX_QUERY_LENGTH]) summaries = [] len_search_results = len(search_results) if len_search_results == 0: