Add bocha search tool

[weijintaocode]

BochaSearchTool Documentation

Description

This tool is designed to perform intelligent web searches with AI-powered summaries and rich metadata extraction. It utilizes the Bocha AI Search API, a REST API that provides comprehensive search results with detailed summaries, site names, icons, and crawl timestamps.

Installation

To incorporate this tool into your project, follow the installation instructions below:

pip install 'crewai[tools]'

Example

The following example demonstrates how to initialize the tool.

from crewai_tools import BochaSearchTool

# Initialize the tool for internet searching capabilities
tool = BochaSearchTool()

Steps to Get Started

To effectively use the BochaSearchTool, follow these steps:

1. Package Installation: Confirm that the crewai[tools] package is installed in your Python environment.
2. API Key Acquisition: Acquire a API key here.
3. Environment Configuration: Store your obtained API key in an environment variable named BOCHA_API_KEY to facilitate its use by the tool.

Conclusion

By integrating the BochaSearchTool into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.

---

Note

Medium Risk
Introduces a new external-networking tool that calls a third-party API using an env-provided secret, so failures/timeouts and response-shape changes could affect runtime behavior.

Overview
Adds a new BochaSearchTool that performs web searches via the Bocha AI Search API, requiring BOCHA_API_KEY and returning formatted results including title/URL/summary/site metadata.

Includes user-facing documentation for installation, setup, and basic usage, and implements timeout/HTTP/connection/JSON error handling for the outbound request.

^{Written by Cursor Bugbot for commit 94058fe. This will update automatically on new commits. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 2 potential issues.

^{Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.}

This PR is being reviewed by Cursor Bugbot

Details

Your team is on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle for each member of your team.

To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.

[cursor]

API success check fails when code field absent

Medium Severity

The condition if data.get("code") != 200 incorrectly treats successful API responses as errors when the response JSON doesn't include a code field. If code is absent, data.get("code") returns None, and None != 200 evaluates to True, causing the tool to return an error message like "Bocha API error: Unknown error (code: N/A)" even for valid successful responses.

 

[cursor]

Unused imports clutter the module

Low Severity

Three imports are unused: datetime (line 1), ClassVar (line 3), and field_validator (line 6). These are imported but never referenced anywhere in the code. Only Any from typing and BaseModel, Field from pydantic are actually used.

 

[github-actions]

This PR is stale because it has been open for 45 days with no activity.