Installing llm-mistral but not setting an api key breaks llm models list
recollir opened this issue · comments
Installing llm-mistral but not setting an api key for it breaks llm models list. Not sure if this is due to how mistral works. Or if this should be reported to the llm repository. A workaround could be to ignore mistral when no api key set and just issue a warning for this when listing models.
❯ llm keys
No keys found
❯ llm plugins
[]
❯ llm models
OpenAI Chat: gpt-3.5-turbo (aliases: 3.5, chatgpt)
OpenAI Chat: gpt-3.5-turbo-16k (aliases: chatgpt-16k, 3.5-16k)
OpenAI Chat: gpt-4 (aliases: 4, gpt4)
OpenAI Chat: gpt-4-32k (aliases: 4-32k)
OpenAI Chat: gpt-4-1106-preview
OpenAI Chat: gpt-4-0125-preview
OpenAI Chat: gpt-4-turbo-preview (aliases: gpt-4-turbo, 4-turbo, 4t)
OpenAI Completion: gpt-3.5-turbo-instruct (aliases: 3.5-instruct, chatgpt-instruct)
❯ llm install llm-mistral
Collecting llm-mistral
...
...
Using cached llm_mistral-0.3-py3-none-any.whl (9.5 kB)
Installing collected packages: llm-mistral
Successfully installed llm-mistral-0.3
❯ llm models
Error: You must set the 'mistral' key or the LLM_MISTRAL_KEY environment variable.
Thanks, yeah this is a bug.
I tested this manually by deleting ~/Library/Application\ Support/io.datasette.llm/mistral_models.json and then removing my mistral key from the keys.json file.
🙏 Thank you.