simonw / simonw/llm

Foreign characters stored in content with embeddings malformed

Open
#283 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
12.5k
Forks
998
Avg merge
3d 13h
Merged PRs (30d)
10

Description

Hi -

I create embeddings for some UTF-8 plain text files.

In the embeddings.db sqlite database foreign characters are not right. For example

æ becomes æ
ø becomes ø

and so on.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the issue with UTF-8 plain-text files containing characters such as æ and ø, then trace how their content is written to embeddings.db. No source file or test is named; done means the stored content preserves the original characters instead of becoming mojibake.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, sqlite
Domain
ai, databases
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.