mirror of
https://github.com/browser-use/browser-use.git
synced 2026-09-14 19:59:47 +08:00
MagMueller
6f8b0626b6
Browser Use Cloud does not serve `browser-use/bu-30b-a3b-preview`. The gateway still has the route (cloud `backend/llm_use/gateway/pricing.py` MODAL_MODELS, `service.py` _call_modal), but the Modal app behind it, `browser-use-llm-prod` in browser-use/deploy-llm, was last deployed on 2025-12-16 and every production call since returns upstream HTTP 503, which the gateway reports to the caller as a generic 500. The weights are public and in use: https://huggingface.co/browser-use/bu-30b-a3b-preview is a public repo with 2.34k downloads in the last month. So instead of dropping the model, say what it actually is - open weights you host yourself. - `examples/models/bu_oss.py` now starts from a vLLM server and talks to it through `ChatOpenAI`, so it needs no BROWSER_USE_API_KEY and does not depend on the dead Cloud route. - The `ChatBrowserUse` docstring says Cloud does not serve it. - The skills model table gains a self-hosting section with the vLLM command from the model card, and loses the priceless OSS row. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018oComYHNbeV4e21v22Bbdn
44 lines
1.1 KiB
Python
44 lines
1.1 KiB
Python
"""Run the open-weights Browser Use model on your own GPU.
|
|
|
|
`browser-use/bu-30b-a3b-preview` is published under
|
|
https://huggingface.co/browser-use/bu-30b-a3b-preview. It is open weights you host
|
|
yourself, not a model Browser Use Cloud serves for you, so it needs no
|
|
BROWSER_USE_API_KEY and has no per-token price.
|
|
|
|
Setup:
|
|
1. pip install vllm
|
|
2. vllm serve browser-use/bu-30b-a3b-preview --max-model-len 65536 --host 0.0.0.0 --port 8000
|
|
3. python examples/models/bu_oss.py
|
|
|
|
Point BU_OSS_BASE_URL at the server if it is not on localhost.
|
|
"""
|
|
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
from browser_use import Agent, ChatOpenAI
|
|
|
|
load_dotenv()
|
|
|
|
try:
|
|
from lmnr import Laminar
|
|
|
|
Laminar.initialize()
|
|
except ImportError:
|
|
pass
|
|
|
|
# Any OpenAI-compatible server works; vLLM is what the model card recommends.
|
|
llm = ChatOpenAI(
|
|
model='browser-use/bu-30b-a3b-preview',
|
|
base_url=os.getenv('BU_OSS_BASE_URL', 'http://localhost:8000/v1'),
|
|
api_key=os.getenv('BU_OSS_API_KEY', 'not-needed'),
|
|
)
|
|
|
|
agent = Agent(
|
|
task='Find the number of stars of browser-use and stagehand. Tell me which one has more stars :)',
|
|
llm=llm,
|
|
flash_mode=True,
|
|
)
|
|
agent.run_sync()
|