构建一个可以依赖聊天记录的个性化形象

[jrgong]

Thx, that helps!

@sam

10k tokens is workable

Just to clarify, are all the uploaded files injected into the system prompt? Or are they processed through the configured ai_embeddings_model first and then injected?

I am a bit confused about your recommended 10k token limit recommendation especially with the part below:

@sam

You can introduce large bodies of text into your custom AI bots that are absent from models training. (for example: internal training docs, internal reports)