How save the outputs from LLMs as it shown in the logs.

[innocent-charles]

Hello ! can anyone help me with how save the outputs of LLMs as it shown in the logs but a little better like json with entities and value extracted.

[rmitsch]

The output (i. e. prompts and responses) are available in Doc.user_data["llm_io"].

Unfortunately there is a mistake in the docs here at the moment:

Whether to save LLM I/O (prompts and responses) in the Doc._.llm_io custom attribute.

Doc._.llm_io should actually be Doc.user_data["llm_io"]. We'll fix the docs.

[innocent-charles]

Thanks much a lot @rmitsch