Jose Luis López López

Results 4 issues of Jose Luis López López

**Environment, Container Image, Hardware** LocalAI version: 2.14.0 Container Image: localai/localai:v2.14.0-cublas-cuda12-ffmpeg nvidia CUDA 12, intel x86_64, Ubuntu 22.04 LTS. Linux makinota08 6.5.0-28-generic 29~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Apr 4 14:39:20 UTC 2...

bug
unconfirmed

The instruction required the agent to just "press return" after an input text. The workflow required to input a number in a text box as a step. The next step...

The agent is encountering an unexpected exception. The field json_response is null, and no verification of this field is made before using it. I suggest checking if json_response is null...

Hi!. The following line forbids the use of the vision enabled models under OLLAMA: https://github.com/Skyvern-AI/skyvern/blob/0184a0e70515e60c64350a792f284f50b6b8a47c/skyvern/forge/sdk/api/llm/config_registry.py#L836 I suggest that instead you create a parameter, like OLLAMA_SUPPORTS_VISION, or reuse the general parameter...