spring-projects / spring-projects/spring-ai
Suggested modifications to MilvusVectorStore
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 9.5k
- Forks
- 2.9k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 6
Description
I sincerely hope that the org.springframework.ai.vectorstore.milvus.MilvusVectorStore#doSimilaritySearch function can accept externally passed float[] embeddings.
This is because, to reduce costs, the embeddings corresponding to the query might have already been cached before performing RAG retrieval.
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
Locate org.springframework.ai.vectorstore.milvus.MilvusVectorStore#doSimilaritySearch and trace how the query embedding is currently obtained before Milvus retrieval. Determine the API change needed to accept an externally supplied float[] embeddings, then verify that cached embeddings can be used without generating them again and cover the behavior with the relevant vector-store tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, spring
- Domain
- ai, databases
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100