Check out the examples to see code using chromem-go for retrieval augmented generation (RAG) on a Wikipedia dataset using Ollama, and semantic search on an arXiv dataset using OpenAI: github.com/philippgille...

Let me know what you think! Looking forward to any kind of feedback 🙂

Yes, there are a lot of vector DBs already (Pinecone, Qdrant, Milvus), or classic DBs with vector support (PostgreSQL with pgvector) but not embeddable.

Chroma and Weaviate are embeddable but not in Go. SQLite has the sqlite-vss extension but using it in Go requires CGO.

Minimal code example for chromem-go

New side project I worked on in the past weeks:

An embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence. Can create the embeddings for you via OpenAI, local Ollama and others.
github.com/philippgille/chromem-go