codeforboston / codeforboston/maple

Backfill Job for Bill Summaries/Topics

Open
#1,882 1 comment 0 reactions 1 assignee Claimed by @chiroptical View on GitHub
backend Ready for Development tech debt
Dominant language
TypeScript
Stars
56
Forks
175
Avg merge
2d 5h
Merged PRs (30d)
13

Description

## Problem

Since the initial bulk load of LLM summaries/topics for bills, a number of new bills were added to the system before our pipeline to auto-generate summaries and topics for new bills went live. Given that we want all bills to have LLM summaries/topics, we need to write a backfill script to go back and process any bills missing the `summary`/`topics` fields in Firestore.

## Success Criteria
- [ ] Create a new python script that connects to Firestore, iterates over bills in the `generalCourts/194/bills` collection that *don't* currently have a `summary` or `topics`, run those bills through the existing python LLM functions that generate summaries/tags (linked below), and update the existing bill in Firestore with the new `summary`/`topics`

## Additional Notes
- Existing Python function that generates summaries: [`get_summaries_and_tags_api_function` ](https://github.com/codeforboston/maple/blob/c2e6047bde6b14078dbd4e1262ba51db7c87300a/llm/llm_functions.py#L329)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.