-
Notifications
You must be signed in to change notification settings - Fork 52
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
wandbot v1.3 - There be changes ahead #85
Open
morganmcg1
wants to merge
121
commits into
main
Choose a base branch
from
make_wandbot_great_again
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Report is too large to display inline. Next stepsMark a package as acceptable riskTo ignore an alert, reply with a comment starting with
|
… calls, add tests for error propagation
…logging of openai messages
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
wandbot v1.3.0
Note that to trigger the final initalization after running
run.sh
, a request has to be made to the/startup
endpoint, as tiggering the heavy initialzations during app startup causes replit to timeout:New:
Testing
Updating the Evaluation Module
All LlamaIndex and RAGAS dependencies were removed from the evaluation code. The system prompt, model name and temperature remain the same.
Both implementations were evaluated to ensure that the new impelmentation perfectly matched the LlamaIndex version. Full evaluation details, code and results files are documented in this PR. Below are weave eval links for both implementations:
Full wandbot evals; LlamaIndex eval vs raw OpenAI
New (raw OpenAI) eval code as of commit 840427d - 72.7%, weave eval
wandbot v1.2 LlamaIndex eval code, 71.4% weave eval
The new code tends to evaluate slightly higher sometimes as the old LlamaIndex code wasn't fault tolerant of retries and errors and so would mark samples incorrect if there was an error/rate limit with the evaluator call itself.