根据conf.yaml.example 示例 配置ollama模型报错

[Albertyao1993]

根据conf.yaml.example 文件中，本地配置Ollama模型。run main.py 后，报错。请问是需要额外配置一个OPENAI_API_KEY 吗？
BASIC_MODEL: model: "ollama/qwen3:14b" base_url: "http://localhost:11434" # Local service address of Ollama, which can be started/viewed via ollama serve
> uv run main.py Traceback (most recent call last): File "/home/guoqiang/developments/deer-flow/main.py", line 14, in <module> from src.workflow import run_agent_workflow_async File "/home/guoqiang/developments/deer-flow/src/workflow.py", line 6, in <module> from src.graph import build_graph File "/home/guoqiang/developments/deer-flow/src/graph/__init__.py", line 4, in <module> from .builder import build_graph_with_memory, build_graph File "/home/guoqiang/developments/deer-flow/src/graph/builder.py", line 8, in <module> from .nodes import ( File "/home/guoqiang/developments/deer-flow/src/graph/nodes.py", line 14, in <module> from src.agents.agents import coder_agent, research_agent, create_agent File "/home/guoqiang/developments/deer-flow/src/agents/__init__.py", line 4, in <module> from .agents import research_agent, coder_agent File "/home/guoqiang/developments/deer-flow/src/agents/agents.py", line 13, in <module> from src.llms.llm import get_llm_by_type File "/home/guoqiang/developments/deer-flow/src/llms/llm.py", line 48, in <module> basic_llm = get_llm_by_type("basic") ^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/guoqiang/developments/deer-flow/src/llms/llm.py", line 42, in get_llm_by_type llm = _create_llm_use_conf(llm_type, conf) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/guoqiang/developments/deer-flow/src/llms/llm.py", line 27, in _create_llm_use_conf return ChatOpenAI(**llm_conf) ^^^^^^^^^^^^^^^^^^^^^^ File "/home/guoqiang/developments/deer-flow/.venv/lib/python3.12/site-packages/langchain_core/load/serializable.py", line 125, in __init__ super().__init__(*args, **kwargs) File "/home/guoqiang/developments/deer-flow/.venv/lib/python3.12/site-packages/pydantic/main.py", line 214, in __init__ validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/guoqiang/developments/deer-flow/.venv/lib/python3.12/site-packages/langchain_openai/chat_models/base.py", line 600, in validate_environment self.root_client = openai.OpenAI(**client_params, **sync_specific) # type: ignore[arg-type] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/guoqiang/developments/deer-flow/.venv/lib/python3.12/site-packages/openai/_client.py", line 114, in __init__ raise OpenAIError( openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

[naiheSH]

conf.yaml.example 把.example后缀删除，然后再运行

[Albertyao1993]

conf.yaml.example 把.example后缀删除，然后再运行

我是按照官方说明文档， cp了一份 conf.yaml 文件并且配置了ollama。然后报的需要设置openai_api_key的错误。

[naiheSH]

在conf.yaml需要配置豆包的key

conf.yaml.example 把.example后缀删除，然后再运行

我是按照官方说明文档， cp了一份 conf.yaml 文件并且配置了ollama。然后报的需要设置openai_api_key的错误。

[ai-srcflow]

这配置太拉了 压根一次性就成功不了 抄langmanus都抄不明白

[yin3331]

这样可以成功，最重要的是加个 /v1，还有模型名字前不要加ollama/
BASIC_MODEL:
model: "mistral-small3.1:24b"
api_key: fake
base_url: "http://localhost:11434/v1"