-
Notifications
You must be signed in to change notification settings - Fork 467
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Parametrized OpenAI Models #28813
Labels
Comments
john-thomas-dotcms
moved this from Next 1-3 Sprints
to Current Sprint Backlog
in dotCMS - Product Planning
Jun 20, 2024
victoralfaro-dotcms
moved this from Current Sprint Backlog
to In Progress
in dotCMS - Product Planning
Jul 15, 2024
victoralfaro-dotcms
changed the title
Move dotAI model parameters from Java code to dotAI App configuration
Parametrized OpenAI Models
Jul 18, 2024
This was referenced Jul 18, 2024
victoralfaro-dotcms
added a commit
that referenced
this issue
Jul 29, 2024
victoralfaro-dotcms
added a commit
that referenced
this issue
Jul 30, 2024
victoralfaro-dotcms
added a commit
that referenced
this issue
Jul 30, 2024
victoralfaro-dotcms
added a commit
that referenced
this issue
Jul 30, 2024
victoralfaro-dotcms
added a commit
that referenced
this issue
Jul 30, 2024
victoralfaro-dotcms
moved this from In Progress
to In Review
in dotCMS - Product Planning
Jul 30, 2024
github-merge-queue bot
pushed a commit
that referenced
this issue
Jul 30, 2024
…29236) Removing hardcoded OpenAI models at enum class OpenAIModel. Instead they are now part of the `dotAI.yml` application descriptor so the user can be the one who configures them not only one but multiple models for `text`, `image` and `embeddings`. The way to specify more than one is to provide a comma delimited list in the new dotAI App params. Sometimes we accept a model to use in the payload of our AI endpoints, for this matter we will validate that model and if it's invalid we will throw an exception. When is not present in the payload, then our backend will inject the current model. Which leads us to the question: How will the current model be determined? This is part of the work defined for #29284 (model fallback)
github-project-automation
bot
moved this from Done
to Internal QA
in dotCMS - Product Planning
Sep 3, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
Parent Issue
No response
User Story
Currently, the OpenAI models we support, and the parameters for those models (such as maximum tokens) are hard-coded in a Java file: https://github.com/dotCMS/core/blob/master/dotCMS/src/main/java/com/dotcms/ai/util/OpenAIModel.java
However, these models and parameters are not static. For example, OpenAI has added new models which are not in our list, and has already deprecated the gpt-3.5-turbo-16k model (and will decommission it completely in 3 months). But the only way we can change those for dotAI is with a Java code change (which will then also require backporting to 24.04 LTS).
We will have a more future-proof solution for this in dotAI phase 2. However, for now we need to:
Because of both our inability to support new OpenAI models, and the impending decommissioning of a model we support, this change is a high priority.
Acceptance Criteria
Proposed Objective
Reliability
Proposed Priority
Priority 2 - Important
External Links... Slack Conversations, Support Tickets, Figma Designs, etc.
No response
Assumptions & Initiation Needs
No response
Quality Assurance Notes & Workarounds
No response
Sub-Tasks & Estimates
No response
Tasks
The text was updated successfully, but these errors were encountered: