Notifications
Clear all
Topic starter
Hi Dear Community!
I need some assistance in understanding how the ReAct Agent invokes tools.
When I utilize the OpenAI chat model (gpt-4o), the Agent sometimes fails to call a tool and instead attempts to output a final result, even when it's not yet complete.
For instance:
In this output, the model clearly indicates that the sabre_command tool should be executed. However, the tool is not called, and the agent attempts to parse it as JSON, subsequently failing with an error:
If I use an Anthropic chat model, everything functions correctly.
callin.io version: 1.74.0
Please assist!
Posted : 16/01/2025 2:01 pm
It seems your topic is missing some crucial details. Could you please provide the following information, if relevant?
- callin.io version:
- Database (default: SQLite):
- callin.io EXECUTIONS_PROCESS setting (default: own, main):
- Running callin.io via (Docker, npm, callin.io cloud, desktop app):
- Operating system:
Please share these details to help us understand your issue better.
Posted : 16/01/2025 2:01 pm
This thread was automatically closed 90 days following the last response. New replies are no longer permitted.
Posted : 16/04/2025 2:02 pm