@llama_index
A use case that we’ve heard repeatedly from users is time-based retrieval for RAG systems. ⏱️ We’re excited to integrate with @TimescaleDB - not just a vector db, but also: ✅ time-based filters ✅ much faster/cheaper storage than pgvector Full blog 📗: https://t.co/vu7PD9zyEt https://t.co/ZErPPlgGo5