-
Notifications
You must be signed in to change notification settings - Fork 32
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
feat(api): Runs endpoints #583
Conversation
✅ Deploy Preview for leapfrogai-docs canceled.
|
f5e7dd9
to
ee2d89a
Compare
8290b9b
to
98ea343
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We have a circular import because we are depending on our own route.
src/leapfrogai_api/routers/openai/requests/create_thread_request.py
Outdated
Show resolved
Hide resolved
src/leapfrogai_api/routers/openai/requests/run_create_params_request.py
Outdated
Show resolved
Hide resolved
760d07b
to
306cbbe
Compare
…om:defenseunicorns/leapfrogai into 419-runs-endpoints-420-run-steps-endpoints
src/leapfrogai_api/routers/openai/requests/run_create_params_request_base.py
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is a big PR that has been the work of a lot of effort. There are several conversation items that will turn into issues in our backlog. Thanks everyone for their hard work in implementing this feature.
In the future, lets set the goal of maintaining smaller PRs and introducing more testing. I'm sure I could spend another couple working days looking through this PR but I believe it would be more efficient to merge this in now (since it is in a working state where we can iterate on it independently) and start working on adding improvements in separate PRs.
Thanks again for everyones hard work in developing, reviewing, and testing this PR.
Streaming and non-streaming versions of runs
Naive RAG implementation that allows generating responses using results pulled from the vector store
Closes #419