Commit Graph

19 Commits

Author SHA1 Message Date
Lucas Gomide
72b3a8c70a feat: allow to provide the driver and options to be used by Selenium (#316) 2025-05-30 08:13:11 -04:00
Filip Michalsky
8ecc958e4c stagehand tool (#277)
* stagehand tool

* update import paths

* updates

* improve example

* add tests

* revert init

* imports

* add context manager

* update tests

* update example to run again

* update context manager docs

* add to pyproject.toml and run uv sync

* run uv sync

* update lazy import

* update test mock

* fixing tests

* attempt to fix tests
2025-05-10 09:53:20 -04:00
Lucas Gomide
fd4ef4f47a fix: Remove kwargs from all RagTools (#285)
* fix: remove kwargs from all (except mysql & pg) RagTools

The agent uses the tool description to decide what to propagate when a tool with **kwargs is found, but this often leads to failures during the tool invocation step.

This happens because the final description ends up like this:

```
CrewStructuredTool(name='Knowledge base', description='Tool Name: Knowledge base
Tool Arguments: {'query': {'description': None, 'type': 'str'}, 'kwargs': {'description': None, 'type': 'Any'}}
Tool Description: A knowledge base that can be used to answer questions.')
```

The agent then tries to infer and pass a kwargs parameter, which isn’t supported by the schema at all.

* feat: adding test to search tools

* feat: add db (chromadb folder) to .gitignore

* fix: fix github search integration

A few attributes were missing when calling the .add method: data_type and loader.

Also, update the query search according to the EmbedChain documentation, the query must include the type and repo keys

* fix: rollback YoutubeChannel paramenter

* chore: fix type hinting for CodeDocs search

* fix: ensure proper configuration when call `add`

According to the documentation, some search methods must be defined as either a loader or a data_type. This commit ensures that.

* build: add optional-dependencies for github and xml search

* test: mocking external requests from search_tool tests

* build: add pytest-recording as devDependencie
2025-05-05 14:15:50 -04:00
Lucas Gomide
edc9b44c47 Add secure Python Sandbox and Enhanced Logging in CodeInterpreterTool (#281)
* feat: add a safety sandbox to run Python code

This sandbox blocks a bunch of dangerous imports and built-in functions

* feat: add more logs and warning about code execution

* test: add tests to cover sandbox code execution

* docs: add Google-style docstrings and type hints to printer and code_interpreter

* chore: renaming globals and locals paramenters

---------

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>
2025-04-23 15:42:05 -04:00
Lucas Gomide
8cbdaeaff5 refactor(selenium): improve driver management and add headless mode (#268)
- Refactor Selenium scraping tool to use single driver instance
- Add headless mode configuration for Chrome
- Improve error handling with try/finally
- Simplify code structure and improve maintainability
2025-04-15 10:50:40 -04:00
Vini Brasil
257f4bf385 Test optional dependencies are not required in runtime (#260)
* Test optional dependencies are not required in runtime

* Add dynamic imports to S3 tools

* Setup CI
2025-04-08 13:20:11 -04:00
Luis Cardoso
3808f98c14 fix(serper-dev): restore search localization parameters
- 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
2025-01-28 10:46:40 +01:00
ChethanUK
9c4c4219cd Adding Snowflake search tool 2025-01-17 02:29:35 +05:30
João Moura
ed261892df Merge pull request #156 from pedropereira/feature/selenium-scraping-tool-can-return-html
Feat(SeleniumScrapingTool): Provide capability to return HTML
2024-12-27 22:02:58 -03:00
Tom Mahler
ba8f95964f added unit testing for multi-line output 2024-12-24 14:14:09 +02:00
Tom Mahler
64b98667a3 fixed code interpreter tests 2024-12-24 14:13:51 +02:00
Pedro Pereira
f11756387d chore: add tests for SeleniumScrapingTool 2024-12-19 21:06:51 +00:00
siddas27
e7e059d02a add rate limiting 2024-11-30 22:08:29 -06:00
siddas27
d168b8e245 add error handling 2024-11-30 21:36:28 -06:00
siddas27
6c242ef3bb add brave search tool 2024-11-30 14:04:06 -06:00
Eduardo Chiarotti
94e6651b55 feat: add code-interpreter tool to init and add unit tests 2024-06-20 20:43:19 -03:00
Gui Vieira
1c8d010601 Custom model config for RAG tools 2024-03-19 18:47:13 -03:00
João Moura
50bae27948 revamping crewai tool 2024-02-25 21:11:09 -03:00
João Moura
db5d371769 Quick tools reorganization 2024-02-15 14:02:42 -03:00