feat: answer augments and auto-linter(#41) #43
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
Collaborator
mediumsizeworkingdog
commented
Nov 22, 2024
•
mediumsizeworkingdog
commented
- enabled generation of both question augmented and answer augmented tasks
- replaced sonnet with haiku for question and answer generation
- enabled token tracing to calculate cost of using non-openAI and non-claude models on langfuse
- removal of dead code and stylistic refactors
- constrained outputs to be of size 1100x1100 pixels
- fixed missing indentation in QA system prompts
- stored augment_type in redis so it can be queryied on Dojo before logging to wandb.
- added 24hr time-to-live for augment_type values on redis.
* feat: WIP - adding ability to augment on answers instead of question * chore: removed whitespace zzz * feat: added augmentation of answers * chore: remove dead code; edit comments * docs: renamed outdated vars * docs: more renaming of augmentation types * refactor: enable generation of multiple augment types * fix: ruff whitespace fixes * chore: removed unused LLMs from config * refactor: added token tracking for custom LLMs on langfuse * refactor: added 50/50 chance for picking augment type * refactor: renamed Worker class to WorkerManager * chore: comment unused code * refactor: change random.choice() -> random.choices() for augment selection
* fix: missing indents in QA system prompts * fix: instructions outside of XML tag
* refactor: stored augment_type in redis * refactor: add 24hr expiration to augment_type in redis
jarvis8x7b
reviewed
Dec 2, 2024
Comment on lines
+44
to
+47
| "total_cost": None, | ||
| "total": None, | ||
| "input_cost": None, | ||
| "output_cost": None, |
There was a problem hiding this comment.
btw would this still log the cost correctly on the dashboard?
* chore: style changes * feat: init linter files * feat: add syntax error prompting and LLM calls * feat: enabled automatic linting of generated js code to catch syntax errors * chore: commit eslint config files * feat: added docker install + config for auto-linter
mediumsizeworkingdog
changed the title
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.