spring-projects / spring-projects/spring-ai
VertexAI vector store
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 9.5k
- Forks
- 2.9k
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 5
Description
I'm new to both Spring AI and VertexAI so forgive me in advance if I've misunderstood something. When looking in the documentation of Spring AI, I see that you support many embedding models and vector stores. However, I can only see that VertexAI can be used as an embedding model to generate my embeddings, but I cannot find a VectorStore implementation for VertexAI (at least not in the documentation). My understanding is that VertexAI can also be used as a vector store, at least according to Gemini:
Vertex AI can be used as a vector store. Its Embedding API provides a managed service for storing, indexing, and retrieving embeddings. This makes it a convenient and efficient option for various applications that require vector similarity search.
Would it make sense to also support VertexAI as a VectorStore implementation in the future in the Spring AI project?
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 the Spring AI documentation and the existing embedding-model and VectorStore integrations to determine how Vertex AI is currently represented. Confirm which Vertex AI storage or vector-search service is intended, then define the integration scope and documentation needed for support; the issue names no repository files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- google-cloud, java, spring
- Domain
- ai, backend, databases
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100