#qdrant

The latest AI and developer news about #qdrant, with the original source and a short summary.

Qdrant tests Perplexity’s PDF embeddings: 21× smaller compressed vectors, with originals still stored

1-bit TurboQuant compression reduces vector size from 856 KB to 40 KB per page while retaining 96.5% of float32 retrieval scores.

·2026.10.17 11:00

PickEmbedFlow Released to Eliminate Downtime During Embedding Model Swaps

Researchers have released EmbedFlow, an open-source tool that enables instant switching between embedding models by leveraging existing indexes without backfilling.

·2026.09.08 11:00

Qdrant x LangChain: Achieving Final Performance

Integrating Qdrant with LangChain maximizes the performance and resource efficiency of RAG applications.

·2·2026.08.26 23:00

Building a Personal-Memory RAG with Ollama

Built a memory RAG that lets you query all your personal data using Ollama and qwen2.5:7b.

·2·2026.04.15 22:00

Webinar Recap: How Cars24 Automated 3 Million Minutes of Sales Calls with Voice AI

Cars24 automated 25% of sales calls with multilingual multi-agent Voice AI.

·1·2026.04.10 14:00

[Company Spotlight] Qdrant Vector Database

High-performance vector database **Qdrant** has launched a **Replit** template to help developers implement RAG and streamline onboarding.

·1·2024.01.12 02:00