Creating and Importing LLM Chat Assets
Last updated
Last updated
It is not yet possible to import pre-existing chat conversations.
It is not yet possible to store conversations outside of iMerit's own private AWS S3 storage.
If you create a conversation now, it will be stored in an iMerit-owned private encrypted AWS S3 bucket.
Ango Hub allows you to annotate individual messages in LLM chat conversations by using the LLM Chat Labeling Editor. This page explains how to create LLM Chat assets.
There are two possible types of LLM Chat assets: "pre-existing" and "live" conversations.
Pre-existing conversations are conversations which already happened outside of the Ango Hub platform and you import them to be annotated. Currently, this feature is not yet available on the Ango Hub platform.
Live conversations start empty, and the annotator has a live conversation with your LLM directly from Ango Hub.
To create an empty conversation which will be populated live by the annotator, from your project, navigate to the Assets tab, then click on Add Data. A dialog will appear.
Click on LLM Asset Creator. A number of options will appear on the left-hand side of the screen.
This feature is not yet available: Storage Method. If you have previously integrated a storage method with Ango Hub, you may pick one here. The conversation will be saved in the storage and bucket chosen. If you do not pick a storage method, the chats will be saved in iMerit's own private and encrypted AWS S3 storage bucket.
Number of Conversations. Pick here the number of empty conversations you wish to create.
Click on Upload new conversations to create the empty conversations in your project.
