DO NOT MERGE. This is a test branch to demonstrate self-learning/optimization use cases. After the demonstration is complete, this PR can be closed.
The functionality of the 👍 and 👎 buttons are updated to update the thread checkpoint metadata score. The OpenGPTs backend calls the LangGraph API PATCH threads/<tid>/state endpoint to do the update.
Implementation
OpenGPTs backend: Add PATCH api/threads/<tid>/state endpoint to allow client to update thread checkpoint metadata score.
Update OpenGPTs UI feedback buttons to call the new API.
Convert the Assistant bot to a self-learning bot (i.e. uses FewShotExamples managed state).
Lint and format all backend and frontend files.
To Do
[x] Update langgraph-sdk after a new release is cut
[x] Test changes
[x] Create self-learning/optimization assistant
[x] Remove the "Self-Learning Assistant" from the frontend and backend. We'll use the regular assistant instead.
[x] Send score to both LangSmith and FewShotExamples
Next Steps
Implement custom graph that can "self learn/optimize". Branch off of this branch to make this change.
Summary
DO NOT MERGE. This is a test branch to demonstrate self-learning/optimization use cases. After the demonstration is complete, this PR can be closed.The functionality of the 👍 and 👎 buttons are updated to update the thread checkpoint metadata score. The OpenGPTs backend calls the LangGraph API
PATCH threads/<tid>/state
endpoint to do the update.Implementation
PATCH api/threads/<tid>/state
endpoint to allow client to update thread checkpoint metadata score.Assistant
bot to a self-learning bot (i.e. usesFewShotExamples
managed state).backend
andfrontend
files.To Do
langgraph-sdk
after a new release is cutfrontend
andbackend
. We'll use the regular assistant instead.Next Steps
Implement custom graph that can "self learn/optimize". Branch off of this branch to make this change.