# Agentic medical diagnosis system with layered vector retrieval powered by Weaviate

**URL:** <https://forum.weaviate.io/t/agentic-medical-diagnosis-system-with-layered-vector-retrieval-powered-by-weaviate/22597>\
**Category:** Showcase\
**Created:** [August 5, 2026, 9:15am UTC](https://forum.weaviate.io/t/agentic-medical-diagnosis-system-with-layered-vector-retrieval-powered-by-weaviate/22597 "2026-08-05T09:15:50Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![varun500](https://avatars.discourse-cdn.com/v4/letter/v/dec6dc/32.png) [@varun500](https://forum.weaviate.io/u/varun500)\
**Post date:** [August 5, 2026, 9:15am UTC](https://forum.weaviate.io/t/agentic-medical-diagnosis-system-with-layered-vector-retrieval-powered-by-weaviate/22597/1 "2026-08-05T09:15:50Z")

</div>

Agentic medical diagnosis system with layered vector retrieval powered by Weaviate

I’ve built Agentic GraphRAG for Medical Diagnosis ([GitHub - avnlp/agentic-med-diag: Agentic Graph RAG for Medical diagnosis and Clinical QA. Combines LangGraph-orchestrated multi-hop reasoning with parallel graph, vector, community, and text-to-Cypher retrieval with an agentic plan–research–verify loop for evidence-grounded answers on MedQA, MedXpertQA, MedCaseReasoning and MMLU-Pro. · GitHub](https://github.com/avnlp/agentic-med-diag)) , an end-to-end system combining LangGraph orchestration with multi-strategy vector search, hybrid retrieval (dense + BM25), and an agentic plan–research–verify loop for evidence-grounded clinical QA.

Stack: Weaviate for vector search and semantic indexing, Neo4j knowledge graphs, GLiNER/GLiREL extractors, LangGraph pipelines

Knowledge Graph Construction

- Schema-driven extraction with 13 entity types and 25 clinically-grounded relation types
- Three-extractor fusion (GLiNER, GLiREL, LLM) with configurable merge strategies
- Deterministic + LLM-powered entity resolution for deduplication
- Hierarchical Leiden community detection with auto-generated clinical summaries

Layered Retrieval Architecture

- Four vector collections (entity, relation, chunk, community report)
- Multiple atomic methods: hybrid search, fulltext, BFS graph traversal, and text-to-Cypher graph querying
- Pluggable rerankers (RRF, cross-encoder, MMR)
- Data-driven recipes for composing retrieval strategies

Agentic Plan–Research–Verify Loop

- Planner decomposes clinical questions into focused sub-questions
- Parallel researchers execute multi-strategy retrieval with citations
- Verifier assesses coverage and gates synthesis on sufficiency
- Gracefully converges on missing information across iterations

The stack is battle-tested: Neo4j + Weaviate/Qdrant for storage, LangGraph for orchestration, DeepAgents for multi-agent coordination, and BAML for type-safe LLM schema injection. Tested on MedQA, MedXpertQA, MedCaseReasoning, and MMLU-Pro benchmarks.
