Calling `llm embed` with the same content but different --store settings does not update the table
Open
Nobody has claimed this yet.
bug
embeddings
- Dominant language
- Python
- Stars
- 12.5k
- Forks
- 998
- Avg merge
- 3d 13h
- Merged PRs (30d)
- 10
Description
Just noticed this:
paginate-json 'https://api.github.com/repos/simonw/llm/issues?state=all&filter=all' > issues.json
cat issues.json | jq '[.[] | {id, title, body}]' | llm embed-multi llm-issues -
That worked and populated my llm-issues collection with 215 records. But then I realized I should have passed --store to store the content too. So I ran this:
cat issues.json | jq '[.[] | {id, title, body}]' | llm embed-multi llm-issues - --store
But the content column was not populated, because the code noticed that the content_hash had not changed.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the issue with the two shown llm embed-multi llm-issues - commands, first without and then with --store. Trace the handling of content_hash and --store; done means rerunning with changed store settings populates the content column for existing records.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli, database
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100