Entity-graph retrieval on top of Qdrant: Personalized PageRank + convergence scoring, zero LLM calls at query time, +5.9 pts recall@10 on full HotpotQA.
Multi-hop questions break vector search. Here is a graph layer for Qdrant that fixes them.
Related
Building Event-Driven AI Agents: Replacing Polling Loops with Redis Streams and Idempotent Workers
How to architect low-latency, reactive AI workflows that eliminate rate limits, slash compute overhead, and guarantee reliable execution under load
Claude API vs OpenAI API: A Developer's Comparison 2026
This is a developer-focused Claude API vs OpenAI API comparison of the two most widely used large...
What is a DAG? Arborescence (Part 2)
Part 1: Arborescence (General Definition) there may be inaccuracies or simplifications in...