Compare commits

..

28 Commits

Author SHA1 Message Date
Brandon Hancock (bhancock_ai)
e6d33f626c Merge branch 'main' into brandon/eng-290-make-tool-inputs-actual-objects-and-not-strings 2025-01-10 17:14:18 -05:00
Brandon Hancock
b1960ecb4c Revert tool validation 2025-01-09 16:55:23 -05:00
Brandon Hancock
dfb2b4b47a add more tests back in 2025-01-09 16:47:53 -05:00
Brandon Hancock
b171e82990 Failing test 2025-01-09 16:39:57 -05:00
Brandon Hancock
d77902c537 drop llm 2025-01-09 16:35:31 -05:00
Brandon Hancock
90d610ed7e vcr 2 2025-01-09 16:32:57 -05:00
Brandon Hancock
9f8293349c improve function llm logic 2025-01-09 16:29:29 -05:00
Brandon Hancock
fb763885eb Fix tests 2025-01-09 16:25:20 -05:00
Brandon Hancock
389d5a9982 vcr 2025-01-09 16:17:14 -05:00
Brandon Hancock
91144a692a updating tests 2025-01-09 16:11:48 -05:00
Brandon Hancock
58a8c442da add back old tool validation 2025-01-09 16:09:04 -05:00
Brandon Hancock
0b70b3c8b4 add in more role tests 2025-01-09 16:04:48 -05:00
Brandon Hancock
8833ccc123 Trying to fix tests 2025-01-09 16:00:53 -05:00
Brandon Hancock
37ad9f9d9e Force test to pass 2025-01-09 15:14:17 -05:00
Brandon Hancock
3f20ef101c Trying to fix tests 2025-01-09 15:11:39 -05:00
Brandon Hancock
d4afe9fe66 add back in manager delegation tests 2025-01-09 14:44:07 -05:00
Brandon Hancock
acb0d7e056 add back in guardrails 2025-01-09 14:30:39 -05:00
Brandon Hancock
9fb98dbf01 trying to find what is timing out 2025-01-09 14:28:21 -05:00
Brandon Hancock
219af9baa8 Update cassette 2025-01-09 14:26:25 -05:00
Brandon Hancock
2b976e1f63 revert back to figure out why tests are timing out 2025-01-09 14:05:24 -05:00
Brandon Hancock
c653a2e691 add tests for tool validation 2025-01-09 13:28:36 -05:00
Brandon Hancock
6a4d3eb269 add back in support for add_image 2025-01-09 12:44:22 -05:00
Brandon Hancock
52133ebf99 improve prompting 2025-01-09 12:37:24 -05:00
Brandon Hancock
d6e7750965 Merge branch 'main' into brandon/eng-290-make-tool-inputs-actual-objects-and-not-strings 2025-01-09 12:19:46 -05:00
Brandon Hancock
6ad314af8c Fix crew_test issues with function calling 2025-01-09 11:11:21 -05:00
Brandon Hancock
0dc2582ce1 remove prints and unnecessary comments 2025-01-08 17:10:07 -05:00
Brandon Hancock
26053c9d1a Fix issues with parsing none/null 2025-01-08 17:03:45 -05:00
Brandon Hancock
2107512e84 Improving tool calling to pass dictionaries instead of strings 2025-01-08 15:22:55 -05:00

View File

@@ -150,20 +150,15 @@ There are two main ways for one to create a CrewAI tool:
```python Code
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
class MyToolInput(BaseModel):
"""Input schema for MyCustomTool."""
argument: str = Field(..., description="Description of the argument.")
class MyCustomTool(BaseTool):
name: str = "Name of my tool"
description: str = "What this tool does. It's vital for effective utilization."
args_schema: Type[BaseModel] = MyToolInput
description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
def _run(self, argument: str) -> str:
# Your tool's logic here
return "Tool's result"
# Implementation goes here
return "Result from custom tool"
```
### Utilizing the `tool` Decorator