LLM models often achieve better results when they have more specific information to work with. You can use annotations to add context to conversations and passages that wouldn't be available from the chat history.
For example, you could add annotations to more thoroughly describe the issue a passage solves or explain some terms that your organisation uses in an unusual way. The annotation is never visible to your chatbot users.
Annotations are only used by some LLM tasks. You must enable at least one task that can use annotations before you can annotate conversations or passages.
You can annotate:
- Conversations, which applies the context to all passages in that conversation.
- Passages, which applies the context only to that passage.
Both passage and conversation annotations can be used together.
Annotations appear in versions as a change to the passage or conversation that you annotated. Those passage or conversation changes must be published before the annotations can be used by your tasks. If you want to test your annotations before you publish them, you can:
- Run some sessions using TestBot.
- Add your new annotations to a CSV and run automated tests.