lintsinghua / lintsinghua/DeepAudit
嵌入模型的维度全部使用的是预设的值影响实际运行效果
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7k
- Forks
- 850
- PR merge metrics
- No merged PRs in 30d
Description
在选择OpenAI兼容后端时，测试维度为4096，但是保存后为768
https://github.com/lintsinghua/DeepAudit/blob/09444458b12653f484db1cf4b883af930809afdd/backend/app/services/rag/embeddings.py#L48-L70
在代码里看到都是根据提供商预设模型和维度，应该是使用测试结果获取维度长度
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
Start with backend/app/services/rag/embeddings.py at lines 48–70 and trace how the OpenAI-compatible backend’s tested embedding dimension is handled when the model is saved. Reproduce the case where testing reports 4096 but persistence uses 768; done means the saved dimension matches the test result rather than a provider preset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- backend, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100