{"slug": "llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval", "title": "LlamaIndex integration for SynapCores (RAG, GraphRAG, and hybrid retrieval)", "summary": "SynapCores released official LlamaIndex integration packages for its AI-native SQL engine, enabling RAG, GraphRAG, and hybrid retrieval in a single self-hosted binary. The packages replace multiple databases like Postgres, pgvector, Neo4j, and Redis, with a hybrid retriever combining vector, graph, and SQL planned for v0.2.0.", "body_md": "Official LlamaIndex integration packages for [SynapCores](https://synapcores.com) — the AI-native SQL engine.\n\nReplace Postgres + pgvector + Neo4j + Redis with one self-hosted binary. RAG, GraphRAG, agent memory, and SQL in a single deployable engine.\n\n```\n# Vector store (RAG)\npip install llama-index llama-index-vector-stores-synapcores\n\n# Property graph store (GraphRAG)\npip install llama-index llama-index-graph-stores-synapcores\npython\nfrom llama_index.core import VectorStoreIndex\nfrom llama_index.vector_stores.synapcores import SynapCoresVectorStore\n\nvector_store = SynapCoresVectorStore(\n    uri=\"http://localhost:8080\",\n    table_name=\"llama_nodes\",\n    embedding_dim=1536,\n)\n\nindex = VectorStoreIndex.from_documents(docs, storage_context=...)\nresponse = index.as_query_engine().query(\"What is in the docs?\")\n```\n\n| Package | Class | Status |\n|---|---|---|\n`llama-index-vector-stores-synapcores` |\n\n`SynapCoresVectorStore`\n\n`llama-index-graph-stores-synapcores`\n\n`SynapCoresPropertyGraphStore`\n\nA hybrid retriever — `SynapCoresHybridRetriever`\n\ncombining vector + graph + SQL in a single retrieval call — is on the v0.2.0 roadmap.\n\n`synapcores/community:v1.7.0.2-ce`\n\nor newer (needs HNSW DDL,`->>`\n\nJSON arrow, Cypher)- Default HTTP gateway on\n`:8080`\n\n[SRD.md](/SynapCores/synapcores-llamaindex/blob/master/SRD.md)— design + implementation notes[docker/docker-compose.yml](/SynapCores/synapcores-llamaindex/blob/master/docker/docker-compose.yml)— local engine for tests\n\nMIT.", "url": "https://wpnews.pro/news/llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval", "canonical_source": "https://github.com/SynapCores/synapcores-llamaindex", "published_at": "2026-06-26 15:50:56+00:00", "updated_at": "2026-06-26 16:05:03.378892+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-infrastructure", "generative-ai", "large-language-models"], "entities": ["SynapCores", "LlamaIndex", "Postgres", "Neo4j", "Redis"], "alternates": {"html": "https://wpnews.pro/news/llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval", "markdown": "https://wpnews.pro/news/llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval.md", "text": "https://wpnews.pro/news/llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval.txt", "jsonld": "https://wpnews.pro/news/llamaindex-integration-for-synapcores-rag-graphrag-and-hybrid-retrieval.jsonld"}}