【求助帖】29-24.10.21-CrewAI-ollama本地模型调用报错 #274

New Issue

12422372205cs · 2024-10-23T12:47:11+08:00

12422372205cs commented

2024-10-23 12:47:11 +08:00

raise litellm.exceptions.BadRequestError( # type: ignore
litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=OllamaLLM
Params: {}
Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

ollama没有问题，单独测试是通过的，加在crewai项目中就报错

raise litellm.exceptions.BadRequestError( # type: ignore litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=OllamaLLM Params: {} Pass model as E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/starcoder',..)` Learn more: https://docs.litellm.ai/docs/providers - ollama没有问题，单独测试是通过的，加在crewai项目中就报错

12422372205cs commented

2024-10-23 19:35:05 +08:00

解决了
版本：crewai 0.74.2
通过查询crewai官网ollama使用方式更改如下：

from crewai import LLM
llm = LLM(
  base_url=f"http://{host}:{port}",
  model="ollama/llama3.1:latest",
)

解决了版本：crewai 0.74.2 通过查询crewai官网ollama使用方式更改如下： ``` from crewai import LLM llm = LLM( base_url=f"http://{host}:{port}", model="ollama/llama3.1:latest", ) ```

Sign in to join this conversation.