browser-use
How to change the LLM with myselt model, like 'deepseek-v3-241226'?
I have a llm names 'deepseek-v3-241226' with deepseek-v3. I edit the project and add the enum in deepseek.
Predefined model names for common providers
model_names = { "anthropic": ["claude-3-5-sonnet-20241022", "claude-3-5-sonnet-20240620", "claude-3-opus-20240229"], "openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo", "o3-mini"], "deepseek": ["deepseek-chat", "deepseek-reasoner", "deepseek-v3-241226"], "google": ["gemini-2.0-flash", "gemini-2.0-flash-thinking-exp", "gemini-1.5-flash-latest", "gemini-1.5-flash-8b-latest", "gemini-2.0-flash-thinking-exp-01-21", "gemini-2.0-pro-exp-02-05"], "ollama": ["qwen2.5:7b", "qwen2.5:14b", "qwen2.5:32b", "qwen2.5-coder:14b", "qwen2.5-coder:32b", "llama2:7b", "deepseek-r1:14b", "deepseek-r1:32b"], "azure_openai": ["gpt-4o", "gpt-4", "gpt-3.5-turbo"], "mistral": ["pixtral-large-latest", "mistral-large-latest", "mistral-small-latest", "ministral-8b-latest"], "alibaba": ["qwen-plus", "qwen-max", "qwen-turbo", "qwen-long"], "moonshot": ["moonshot-v1-32k-vision-preview", "moonshot-v1-8k-vision-preview"], }
then, I open 127.0.0.1:7788 and select llm provider with 'deepseek', model name with 'deepseek-v3-241226' , after runing agent, with error : INFO [src.agent.custom_agent] 开始调用模型 2025-03-24 17:31:35.902042 ERROR [agent] ❌ Result failed 1/3 times: 404 page not found Stacktrace: Traceback (most recent call last): File "D:\work\ai\web-ui\src\agent\custom_agent.py", line 350, in step raise e File "D:\work\ai\web-ui\src\agent\custom_agent.py", line 338, in step model_output = await self.get_next_action(input_messages) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\Administrator\AppData\Roaming\Python\Python313\site-packages\browser_use\utils.py", line 36, in wrapper result = await func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\work\ai\web-ui\src\agent\custom_agent.py", line 230, in get_next_action ai_message = self.llm.invoke(input_messages) File "C:\Users\Administrator\AppData\Roaming\Python\Python313\site-packages\langchain_core\language_models\chat_models.py", line 307, in invoke self.generate_prompt( ~~~~~~~~~~~~~~~~~~~~^ [self._convert_input(input)], ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<6 lines>... **kwargs,
how to add our LLM ? could anyone give me some suggusets?
My LLM is not the official Deepseek model. The API endpoint URL for invocation is of the format https://xxx.xxxxx.com/api/v3/chat/completions, and the model name is deepseek-v3-241226. How do I properly invoke it?
you can use the api key from the web(https://openrouter.ai/),the free api key ,
