Return CSV instead of JSON for token efficiency #33
Conversation
This file contains hidden or 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
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Outdated suggestions cannot be applied.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.
We've been returning JSON back to the LLMs which is inefficient for token usage. We now convert all of the JSON API responses to CSV and flatten any nested objects. We also account for cases where the Polygon API response structure varies (e.g. it's often a JSON object with a
resultsattribute but sometimes the data fields are top level without being nested under that key).Tests have been added to ensure the JSON to CSV conversion is robust and accurate. This PR also now runs tests for each PR and bumps a few of the dependencies.