feat(tools): add WikipediaSearchTool to crewai-tools - #6848
Open
Toprak1yu wants to merge 9 commits into
Open
Conversation
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughAdds ChangesWikipedia search tool
Sequence Diagram(s)sequenceDiagram
participant Caller
participant WikipediaSearchTool
participant WikipediaClient
participant WikipediaAPI as Wikipedia REST API
Caller->>WikipediaSearchTool: submit search query and options
WikipediaSearchTool->>WikipediaClient: search with language, limit, and User-Agent
WikipediaClient->>WikipediaAPI: request search results
WikipediaAPI-->>WikipediaClient: return article titles
WikipediaSearchTool->>WikipediaClient: retrieve summaries or full content
WikipediaClient->>WikipediaAPI: request page data
WikipediaAPI-->>WikipediaClient: return article data or errors
WikipediaSearchTool-->>Caller: return formatted results
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@lib/crewai-tools/pyproject.toml`:
- Around line 155-157: Replace the global wikipedia dependency in
lib/crewai-tools/pyproject.toml (lines 155-157) with an instance-configurable
Wikipedia client, then update the configuration logic in
WikipediaSearchTool._run
(lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py,
lines 90-94) to create and use a client instance whose language and User-Agent
are scoped per call instead of mutating global package state.
In
`@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py`:
- Around line 52-54: Constrain the WikipediaSearchTool limit field to the valid
1–10 range and add equivalent validation at the start of _run() so direct calls
cannot bypass WikipediaSearchToolSchema. Reject invalid configured or runtime
limits before invoking wikipedia.search, while preserving the existing
valid-result behavior.
- Line 134: Update the result formatting return in the Wikipedia search tool to
create one separator containing the divider and surrounding blank lines, then
join formatted_results with that separator so no divider precedes the first
result. Add a test covering at least two search results and verifying the
separator appears only between them.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 3d59f6a0-50a6-454f-b417-1bd9ad442d00
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (7)
lib/crewai-tools/pyproject.tomllib/crewai-tools/src/crewai_tools/__init__.pylib/crewai-tools/src/crewai_tools/tools/__init__.pylib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.mdlib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/__init__.pylib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.pylib/crewai-tools/tests/tools/test_wikipedia_search_tool.py
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds a new WikipediaSearchTool to crewai_tools, including documentation and pytest coverage, and exposes it via package exports.
Changes:
- Introduces
WikipediaSearchToolwith language/limit configuration, summary vs full content retrieval, and error handling. - Adds a README documenting installation, arguments, and usage examples.
- Adds pytest unit tests and exports the tool from
crewai_toolsandcrewai_tools.tools.
Reviewed changes
Copilot reviewed 6 out of 8 changed files in this pull request and generated 7 comments.
Show a summary per file
| File | Description |
|---|---|
| lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py | Implements the Wikipedia search tool and its schema. |
| lib/crewai-tools/tests/tools/test_wikipedia_search_tool.py | Adds unit tests for main success/error paths. |
| lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.md | Documents tool installation, arguments, and examples. |
| lib/crewai-tools/src/crewai_tools/tools/init.py | Exports WikipediaSearchTool from the tools package. |
| lib/crewai-tools/src/crewai_tools/init.py | Exports WikipediaSearchTool from the top-level package. |
| lib/crewai-tools/pyproject.toml | Adds an optional dependency group for wikipedia. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| f"Title: {title}\nNote: Error retrieving details: {e!s}" | ||
| ) | ||
|
|
||
| return "\n\n" + "-" * 80 + "\n\n".join(formatted_results) |
Comment on lines
+59
to
+68
| def __init__(self, **kwargs: Any) -> None: | ||
| super().__init__(**kwargs) | ||
| self._initialize_wikipedia() | ||
|
|
||
| def _initialize_wikipedia(self) -> None: | ||
| if not WIKIPEDIA_AVAILABLE: | ||
| raise ImportError( | ||
| "The 'wikipedia' package is required to use the WikipediaSearchTool. " | ||
| "Please install it using your package manager (e.g., `pip install wikipedia` or `uv add wikipedia`)." | ||
| ) |
Comment on lines
+78
to
+82
| if not WIKIPEDIA_AVAILABLE: | ||
| return ( | ||
| "Error: The 'wikipedia' package is required to use WikipediaSearchTool. " | ||
| "Please install it using your package manager (e.g., `pip install wikipedia` or `uv add wikipedia`)." | ||
| ) |
Comment on lines
+90
to
+91
| wikipedia.set_user_agent(self.user_agent) | ||
| wikipedia.set_lang(target_lang) |
Comment on lines
+84
to
+85
| target_lang = lang or self.lang | ||
| target_limit = limit or self.limit |
Comment on lines
+1
to
+9
| from unittest.mock import MagicMock, patch | ||
|
|
||
| from crewai_tools import WikipediaSearchTool | ||
| import pytest | ||
|
|
||
|
|
||
| @pytest.fixture | ||
| def tool(): | ||
| return WikipediaSearchTool() |
| f"Title: {title}\nNote: Error retrieving details: {e!s}" | ||
| ) | ||
|
|
||
| return "\n\n" + "-" * 80 + "\n\n".join(formatted_results) |
There was a problem hiding this comment.
Actionable comments posted: 4
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py`:
- Around line 38-58: Add concise docstrings to the public properties content and
summary on WikipediaPage and the methods search, page, summary, and get_content
on WikipediaClient. Document each input and return value, and explicitly
describe PageError or DisambiguationError behavior for methods that can raise
them, without changing runtime behavior.
- Around line 64-71: Validate and normalize the lang argument in
WikipediaSearchTool.__init__ before constructing api_url: lowercase it, accept
only a valid Wikipedia language-subdomain format, and reject URL delimiters or
other invalid characters. Raise an appropriate validation error for invalid
values, and add a regression test confirming values such as
“en@attacker.example#” are rejected before any request is created.
- Around line 290-297: Update the summary branch in the search-result loop to
call client.summary with the resolved page.title returned by client.page, while
preserving auto_suggest=False. Keep the full-content branch and existing body
formatting unchanged.
In `@lib/crewai-tools/tests/tools/test_wikipedia_search_tool.py`:
- Around line 143-153: Expand test_wikipedia_client_instance_isolation coverage
with mocked requests.get behavior tests for WikipediaClient.search, page,
summary, and get_content. Assert request outcomes for successful responses, API
error conversion, redirects, missing pages, and disambiguation parsing,
including a redirected title case; focus assertions on public behavior rather
than request-construction internals.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 3ec9a4e3-8ac3-44e0-b1af-616647363d3b
📒 Files selected for processing (2)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.pylib/crewai-tools/tests/tools/test_wikipedia_search_tool.py
There was a problem hiding this comment.
Actionable comments posted: 1
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py (1)
359-363: 🔒 Security & Privacy | 🟠 Major | ⚡ Quick winDo not log the raw search query.
search_queryis user-controlled and can contain sensitive data. The error log can retain it when the request fails. Log the exception type or a request identifier instead.Proposed fix
- logger.error(f"Wikipedia search failed for query '{search_query}': {e}") + logger.error("Wikipedia search failed: %s", type(e).__name__)🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py` around lines 359 - 363, Update the exception handler around client.search in WikipediaSearchTool to remove the raw user-controlled search_query from logger.error. Log the exception type or an appropriate request identifier while preserving the existing error return behavior and exception details returned to the caller.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@lib/crewai-tools/tests/tools/test_wikipedia_search_tool.py`:
- Around line 358-360: Strengthen the assertions in the Wikipedia search test
around tool._run by verifying the mocked client.summary call receives the
resolved title "Python (programming language)", rather than only checking the
returned text. Keep the existing result assertions and ensure the request-title
assertion distinguishes page.title from the original search query.
---
Outside diff comments:
In
`@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py`:
- Around line 359-363: Update the exception handler around client.search in
WikipediaSearchTool to remove the raw user-controlled search_query from
logger.error. Log the exception type or an appropriate request identifier while
preserving the existing error return behavior and exception details returned to
the caller.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: c255fbbb-2a56-4ed4-8c53-c7a080c46e17
📒 Files selected for processing (2)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.pylib/crewai-tools/tests/tools/test_wikipedia_search_tool.py
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 6 out of 8 changed files in this pull request and generated 5 comments.
Suppressed comments (4)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:154
auto_suggestis part of the public method signatures but isn’t used in eitherpage()orsummary(). This can confuse callers into thinking the behavior is supported. Consider (mandatory) either implementing the parameter’s behavior or removing it from the signature (if it’s kept only for compatibility, document explicitly that it’s unused/ignored).
def page(self, title: str, auto_suggest: bool = False) -> WikipediaPage:
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:227
auto_suggestis part of the public method signatures but isn’t used in eitherpage()orsummary(). This can confuse callers into thinking the behavior is supported. Consider (mandatory) either implementing the parameter’s behavior or removing it from the signature (if it’s kept only for compatibility, document explicitly that it’s unused/ignored).
def summary(self, title: str, auto_suggest: bool = False) -> str:
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:363
- Logging exceptions with formatted strings drops traceback context, which makes production debugging harder. Consider (optional) using
logger.exception(...)in theexceptblocks (or passingexc_info=True) so stack traces are retained; you can still keep the user-facing returned error strings as-is.
try:
search_results = client.search(search_query, results=target_limit)
except Exception as e:
logger.error(f"Wikipedia search failed for query '{search_query}': {e}")
return f"Error searching Wikipedia for '{search_query}': {e!s}"
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:395
- Logging exceptions with formatted strings drops traceback context, which makes production debugging harder. Consider (optional) using
logger.exception(...)in theexceptblocks (or passingexc_info=True) so stack traces are retained; you can still keep the user-facing returned error strings as-is.
logger.warning(
f"Failed to fetch details for Wikipedia page '{title}': {e}"
)
| from pydantic import BaseModel, ConfigDict, Field | ||
|
|
||
|
|
||
| logger = logging.getLogger(__name__) |
| WIKIPEDIA_AVAILABLE = True | ||
| except ImportError: | ||
| WIKIPEDIA_AVAILABLE = False | ||
|
|
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 6 out of 8 changed files in this pull request and generated no new comments.
Suppressed comments (3)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:23
- This tool currently requires the third-party
wikipediapackage (WIKIPEDIA_AVAILABLEchecks +package_dependencies=["wikipedia"]+ optional extra), but the implementation does not use thewikipedialibrary APIs (it usesrequestsagainst the MediaWiki API directly). This adds an extra dependency and a hard runtime gate that doesn’t appear necessary givenrequests/beautifulsoup4are already core dependencies.
WIKIPEDIA_AVAILABLE = importlib.util.find_spec("wikipedia") is not None
try:
from wikipedia.exceptions import ( # type: ignore[import-untyped]
DisambiguationError,
PageError,
WikipediaException,
)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:364
WikipediaClient(...)can raiseValueErrorfor an invalidlang(seeWikipediaClient.__init__), but_runconstructs the client outside thetryblock. That means an invalid language code will raise and potentially crash tool execution instead of returning a user-friendly error string like the other failure paths.
client: WikipediaClient = kwargs.get("client") or WikipediaClient(
lang=target_lang, user_agent=self.user_agent
)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.md:30
- The installation command in this tool README uses
uv add crewai-tools ..., but other tool READMEs in this repo consistently useuv add crewai[tools] .... Using the same pattern here avoids confusion and keeps the docs consistent.
uv add crewai-tools wikipedia
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 6 out of 8 changed files in this pull request and generated no new comments.
Suppressed comments (4)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:12
WIKIPEDIA_AVAILABLEis intended to gate optional dependencies, butbs4andrequestsare imported unconditionally at module import time. If either dependency is missing, importing this module will raiseImportErrorbefore_initialize_wikipedia()/_run()can emit the friendly error message, so the “missing dependencies” path can’t work as written.
from bs4 import BeautifulSoup, Tag
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field
import requests
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:357
WikipediaClient(...)construction happens outside thetry:block. If a caller passes an invalidlang(which raisesValueErrorinWikipediaClient.__init__), the tool will raise instead of returning a graceful error string.
client: WikipediaClient = kwargs.get("client") or WikipediaClient(
lang=target_lang, user_agent=self.user_agent
)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.md:31
- The installation instructions recommend installing the third-party
wikipediapackage, but the tool itself usesrequests+beautifulsoup4directly (and doesn’t importwikipedia). Since this PR adds awikipediaextra increwai-tools, it would be clearer/less error-prone to document installing via that extra (or explicitly listrequests/beautifulsoup4).
Install the `crewai-tools` package along with the `wikipedia` dependency:
```bash
# Using pip
pip install 'crewai[tools]' wikipedia
lib/crewai-tools/pyproject.toml:157
- This adds a
wikipediaoptional extra (wikipedia>=1.4.0), but the new tool implementation doesn’t import or use thewikipedialibrary anywhere (it calls the MediaWiki API viarequests/beautifulsoup4directly). This makes the extra/lockfile dependency look unused and potentially confusing for consumers.
wikipedia = [
"wikipedia>=1.4.0",
]
|
Note GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer. |
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py (1)
22-34: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winDocument the public exception contract.
Add docstrings for
WikipediaException,PageError, andDisambiguationError. Define when each exception occurs. Document thetitleandoptionsattributes onDisambiguationError.As per coding guidelines, “Document public APIs and complex logic in Python code.”
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py` around lines 22 - 34, Document the public exception contract by adding class docstrings to WikipediaException and PageError that describe when each is raised, and to DisambiguationError that describes its occurrence and its title and options attributes. Keep the existing inheritance, constructor behavior, and stored attribute names unchanged.Source: Coding guidelines
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py`:
- Around line 8-19: Make the Wikipedia dependencies lazy: remove the
module-level bs4 and requests imports, import requests inside
WikipediaClient._request(), and import BeautifulSoup and Tag only within the
disambiguation logic that uses them. Preserve WIKIPEDIA_AVAILABLE and the
documented dependency-error behavior in _initialize_wikipedia() and _run(), and
add module-load coverage in the WikipediaSearchTool tests for environments
without these optional packages.
---
Nitpick comments:
In
`@lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py`:
- Around line 22-34: Document the public exception contract by adding class
docstrings to WikipediaException and PageError that describe when each is
raised, and to DisambiguationError that describes its occurrence and its title
and options attributes. Keep the existing inheritance, constructor behavior, and
stored attribute names unchanged.
🪄 Autofix
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 3c66d270-4f31-4628-b64e-04d1c636ef99
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (7)
lib/crewai-tools/pyproject.tomllib/crewai-tools/src/crewai_tools/__init__.pylib/crewai-tools/src/crewai_tools/tools/__init__.pylib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.mdlib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/__init__.pylib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.pylib/crewai-tools/tests/tools/test_wikipedia_search_tool.py
🚧 Files skipped from review as they are similar to previous changes (4)
- lib/crewai-tools/src/crewai_tools/init.py
- lib/crewai-tools/pyproject.toml
- lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.md
- lib/crewai-tools/src/crewai_tools/tools/init.py
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 7 changed files in this pull request and generated 1 comment.
Suppressed comments (4)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:394
- This uses eager f-string interpolation in logging. Prefer parameterized logging (e.g.,
logger.warning(\"... %s\", ...)) to avoid unnecessary string formatting when the log level is disabled, and to keep logging consistent with the earlierlogger.errorusage.
logger.warning(
f"Failed to fetch details for Wikipedia page '{title}': {e}"
)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:222
- The fallback URL construction interpolates
page_titledirectly into the path; titles can include spaces and other characters that should be URL-encoded. Iffullurlis missing, this can generate invalid URLs. Consider URL-encoding the title when building the fallback (e.g., viaurllib.parse.quote).
page_title = str(page_info.get("title", title))
page_url = str(
page_info.get(
"fullurl",
f"https://{self.lang.lower()}.wikipedia.org/wiki/{page_title}",
)
)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:152
- The
auto_suggestparameter is exposed but not used inpage()(and similarly insummary()), which can mislead callers into thinking it changes behavior. Either implement the behavior, remove the parameter, or clearly document that it is currently ignored (and why) to avoid an ambiguous API.
def page(self, title: str, auto_suggest: bool = False) -> WikipediaPage:
lib/crewai-tools/tests/tools/test_wikipedia_search_tool.py:368
- Indexing into
call_args_list[3]makes this test fragile to harmless internal changes (e.g., adding an extra request). Prefer asserting based on matching a specific call (e.g., filtering calls byparams['prop'] == 'extracts'orparamscontaining'exintro') rather than relying on a fixed call index.
summary_call_params = mock_get.call_args_list[3].kwargs["params"]
Comment on lines
+118
to
+120
| response = requests.get( | ||
| self.api_url, params=params, headers=headers, timeout=10 | ||
| ) |
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 5 out of 7 changed files in this pull request and generated no new comments.
Suppressed comments (2)
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/README.md:31
- The installation instructions suggest installing
beautifulsoup4andrequestsseparately, butcrewai-toolsalready declares both as required dependencies (seelib/crewai-tools/pyproject.toml). Recommending them explicitly here is redundant and can confuse users about what they need to install.
Install the `crewai-tools` package along with the `beautifulsoup4` and `requests` dependencies:
```bash
# Using pip
pip install 'crewai[tools]' beautifulsoup4 requests
lib/crewai-tools/src/crewai_tools/tools/wikipedia_search_tool/wikipedia_search_tool.py:162
auto_suggestis documented as a supported parameter onWikipediaClient.page(), but it is never used in the implementation. Passingauto_suggest=Truecurrently has no effect, which is misleading for API consumers.
def page(self, title: str, auto_suggest: bool = False) -> WikipediaPage:
"""Retrieves page information and constructs a WikipediaPage instance.
Args:
title (str): Title of the Wikipedia page.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.