PathRAG
https://github.com/BUPT-GAMMA/PathRAG
Retrieves key relational paths from knowledge graph; flow-based pruning + reliability scoring; path-based prompting. Outperforms baselines on six datasets. arxiv Feb 2025.
At a glance
- Type
- Path-pruned graph retrieval
- Tier
- T4
- Section
- Retrieval-as-memory hybrids
- Created
- 2025-02
- Latest release
- no releases
- License
- Unlicensed
- GitHub
- 356★ Python
- Pricing
- searched not found
- Funding
- not applicable — not commercial
Taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- read-only
- unit
- chunk
- governance
- inspectable
- conflict
- n/a
When to use
Optimised for: retrieval quality / accuracy on long-context QA
Anti-fit: most are research papers; production fitness varies by maintainer
Pros & cons
Pros
Path-based retrieval through KG for multi-hop questions.
Cons
Preprint; path-quality bounds answer quality.
Claims & capabilities
Path-pruned graph retrieval — outperforms baselines on six datasets via flow-based pruning + reliability scoring; 45 cites; 356 stars on GitHub.
Technical surface
- API surface
- not applicable — research paper
- Backend storage
- not applicable — research paper
- Deployment
- searched not found
- Embedding model
- not applicable — research paper
- Multi-tenancy
- not applicable — research paper
- MCP
- not applicable — research paper, no deployed product
- A2A
- not applicable — research paper, no deployed product
- OpenTelemetry
- not applicable — research paper, no deployed product
Similar systems
Other retrieval-as-memory hybrids in the catalog, ranked by inbound references.
- GraphRAG (Microsoft) T1
Modular graph-based RAG. Leiden community detection over knowledge graph; community summaries at multiple levels. DRIFT Search hybrid (Oct 2024).
- RETRO T3
DeepMind. Retrieval-Enhanced Transformer with chunked cross-attention over a 2T-token retrieval database. Frozen BERT retriever + differentiable encoder.
- Atlas T3
Meta AI. Jointly fine-tunes retriever + LM for few-shot tasks.
- RAPTOR T3
Stanford recursive-summarisation tree over the corpus — clusters and summarises documents into a hierarchical index; retrieves at multiple levels. ICLR 2024.
- Self-RAG T4
Trains an LLM end-to-end to emit reflection tokens that decide whether to retrieve, assess passage relevance, and critique output quality — all within a single model.
- HippoRAG / HippoRAG2 T3
Hippocampus-inspired RAG. LLMs + knowledge graphs + Personalized PageRank to mimic neocortex/hippocampus roles. NeurIPS 2024.
Related systems
References (1)
- GraphRAG (Microsoft) cites — S2 isInfluential citation