Own your embeddings: Weaviate + Ollama local vector search config that never leaves your network
philipvollet · x · 2026-09-15
Philip Vollet suggests going open source and owning your data: Weaviate OSS embeds on import and at query time, and with a local model neither hop leaves your network. He shares the exact text2vecollama config pointing at host.docker.internal:11434 with the snowflake-arctic-embed model. Quoted context: turbopuffer's native embeddings GA announcement and its 'stop thinking about embeddings' writeup.
More from Infra
- NVIDIA Posts $96.2B Quarter: An AI Finance Model Separates Real Earnings From Future Promises — nikola_mr64990 · 2026-09-15
- AI's $1.1T data-center bet: productivity must grow 2.7x by 2030 to break even — nordicinst · 2026-09-15
- Chatbot injects 252k-token prompt every turn instead of RAG, dev asks to be talked out of it — louay_Sallakho · 2026-09-15
- MinIO: open-source S3-compatible object store with zero egress fees — thisguyknowsai · 2026-09-15
- Go-LLM repo details running Flash-Next on dual RTX 3090 via vLLM, with honest benchmarks — Motor_Ad16 · 2026-09-15
- Before porting code to GPU, measure memory transfer time — data movement is the real bottleneck — Franc0Fernand0 · 2026-09-15