Skip to content
This repository was archived by the owner on Nov 10, 2025. It is now read-only.

Conversation

@VinciGit00
Copy link
Contributor

@VinciGit00 VinciGit00 commented Feb 4, 2025

Note

Adds a comprehensive crewai_tools suite with RAG core, AWS Bedrock integrations, diverse search/scrape/database tools, examples, tests, and CI workflows.

  • Tools Suite (crewai_tools):
    • RAG: Introduces rag/ core, chunkers, loaders (CSV/JSON/MDX/PDF/Web/GitHub/DBs), and rag_tool.
    • AWS Bedrock: Adds agents, browser session toolkit, code interpreter, knowledge base retriever, S3 reader/writer, and shared exceptions.
    • Adapters: Adds multiple adapters (rag_adapter, embedchain_adapter, mcp_adapter, enterprise_adapter, zapier_adapter, tool_collection).
    • Search/Scrape/Utilities Tools: Adds numerous tools (e.g., brave_search_tool, firecrawl_*, scrapegraph_*, serper_*, selenium_scraping_tool, website_search, csv/json/mdx/txt/pdf_search_tool, code_interpreter_tool, vision_tool).
    • Data/DB/Vector: Adds DB search tools (mysql, postgres, snowflake, singlestore) and vector tools (weaviate, qdrant, mongodb_vector_search_tool).
    • Platform/Automation: Adds crewai_platform_tools, generate_crewai_automation_tool, invoke_crewai_automation_tool, and parallel_tools.
  • Examples: Adds numerous runnable examples under examples/ for scraping, crawling, search, scheduling, and markdownify.
  • Tests: Adds comprehensive unit/integration tests across adapters, tools, and RAG loaders, plus cassettes for search tools.
  • CI/Docs: Adds GitHub workflows (generate-tool-specs.yml, tests.yml), docs (README.md, BUILDING_TOOLS.md), and tool spec generation (generate_tool_specs.py, tool.specs.json).

Written by Cursor Bugbot for commit 7e452ff. This will update automatically on new commits. Configure here.

beowolx and others added 30 commits January 28, 2025 10:46
- Re-add country (gl), location, and locale (hl) parameters to SerperDevTool class
- Update payload construction in _make_api_request to include localization params
- Add schema validation for localization parameters
- Update documentation and examples to demonstrate parameter usage

These parameters were accidentally removed in the previous enhancement PR and are crucial for:
- Getting region-specific search results (via country/gl)
- Targeting searches to specific cities (via location)
- Getting results in specific languages (via locale/hl)

BREAKING CHANGE: None - This restores previously available functionality
enable qdrant as vector search tool for crew agents
mplachta and others added 28 commits August 27, 2025 10:42
#430)

* feat: add InvokeCrewAIAutomationTool for external crew API integration

* feat: add InvokeCrewAIAutomationTool class for executing CrewAI tasks programmatically
* Add contextual AI tools with async support

* Fix package version issues and update README

* Rename contextual tools to contextualai and update contents

* Update tools init for contextualai tools

* feat: Resolved no module found error for nest_asyncio

* Updated nest_asyncio import

---------

Co-authored-by: QJ <[email protected]>
Co-authored-by: Qile-Jiang <[email protected]>
* Create tool for generating automations in Studio

This commit creates a tool to use CrewAI Enterprise API to generate
crews using CrewAI Studio.

* Replace CREWAI_BASE_URL with CREWAI_PLUS_URL

* Add missing /crewai_plus in URL
* refactor: fetch enterprise tool actions from platform

* chore: logging legacy token detected
* docs: add BUILDING_TOOLS.md

* feat(parallel): add ParallelSearchTool (Search API v1beta), tests, README; register exports; regenerate tool.specs.json

* test(parallel): replace URL substring assertion with hostname allowlist (CodeQL)
This commit updates tool prompts to explicitly highlight that some tools
can accept both local file paths and remote URLs.

The improved prompts ensure LLMs understand they may pass remote
resources.
* chore: add deprecation warning in CrewaiEnterpriseTools

* feat: add CrewAI Platform Tool

* feat: drop support to oldest env-var token
* fix: attempt to make embedchain optional

* fix: drop pydantic_settings dependency

* fix: ensure the package is importable without any extra dependency

After making embedchain option many packages were unstalled which caused errors in some tools due to failing import directives
- Remove embedchain adapter; add crewai rag adapter and update all search tools  
- Add loaders: pdf, youtube (video & channel), github, docs site, mysql, postgresql  
- Add configurable similarity threshold, limit params, and embedding_model support  
- Improve chromadb compatibility (sanitize metadata, convert columns, fix chunking)  
- Fix xml encoding, Python 3.10 issues, and youtube url spoofing  
- Update crewai dependency and instructions; refresh uv.lock  
- Update tests for new rag adapter and search params
…es (#455)

* chore: update project version to 0.73.0 and revise uv.lock dependencies

* chore: update chromadb dependency to version 1.1.0 and increment uv.lock revision

* revert

* chore: downgrade chromadb dependency to version 0.5.23

* drop
- Align ruff config and dev dependencies with crewAI  
- Remove pyright dependency
- Remove embedchain and resolve circular deps with ChromaDB  
- Adjust lockfile to match crewai requirements  
- Mock embeddings and vector DB in RAG tool tests
- Increment project version to 0.74.1
- Update crewai dependency to version 0.201.0
- Update chromadb dependency to version 1.1.0
- Adjust pydantic version to 2.11.9
- Clean up uv.lock by removing obsolete package entries
…467)

- Increment project version to 0.75.0
- Update crewai dependency to the latest version without a specific version constraint
- Update uv.lock to reflect changes in crewai version from 0.201.0 to 0.201.1
@VinciGit00 VinciGit00 closed this by deleting the head repository Sep 29, 2025
Copy link

@cursor cursor bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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.

),
]
package_dependencies: List[str] = ["mongdb"]

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Bug: Package Typo and Misconfigured Environment Variables

The MongoDBVectorSearchTool has a typo in its package_dependencies list, mongdb, which should be pymongo or mongodb. Also, its env_vars are incorrectly defined for Browserbase services instead of relevant MongoDB or OpenAI configurations, which could mislead users.

Fix in Cursor Fix in Web

@@ -48,6 +53,7 @@ class WeaviateVectorSearchTool(BaseTool):
...,
description="The API key for the Weaviate cluster",
)
package_dependencies: List[str] = ["weaviate-client"]
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Bug: Type Mismatch and Redundant Field Definition

The alpha field is typed as Optional[int] but defaults to 0.75 (a float), which is a type mismatch for hybrid search weighting. Also, package_dependencies is defined redundantly twice in the class.

Fix in Cursor Fix in Web

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.