ui-tars integration (#2656)

This commit is contained in:
Wyatt Marshall
2025-06-13 01:23:39 -04:00
committed by GitHub
parent 47cf755d9c
commit 15d46aab82
18 changed files with 986 additions and 13 deletions

View File

@@ -24,6 +24,7 @@ This parameter defines the engine that powers the agent task.
- `skyvern-1.0`: performs really well for tasks with a simple goal, like filling a form, or searching for information on Google.
- `openai-cua`: uses OpenAI's CUA model.
- `anthropic-cua`: uses Anthropic's Claude Sonnet 3.7 model with the computer use tool.
- `ui-tars`: uses the UI-TARS model (Seed1.5-VL) via Doubao API for computer vision and GUI automation with multi-turn conversation support (https://seed.bytedance.com/zh/tech/seed1_5_vl).
### [Data Extraction Schema](/api-reference/api-reference/agent/run-task#request.body.data_extraction_schema)