LlamaIndex integration for SynapCores (RAG, GraphRAG, and hybrid retrieval)

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.

Official LlamaIndex integration packages for SynapCores https://synapcores.com — the AI-native SQL engine. Replace Postgres + pgvector + Neo4j + Redis with one self-hosted binary. RAG, GraphRAG, agent memory, and SQL in a single deployable engine. Vector store RAG pip install llama-index llama-index-vector-stores-synapcores Property graph store GraphRAG pip install llama-index llama-index-graph-stores-synapcores python from llama index.core import VectorStoreIndex from llama index.vector stores.synapcores import SynapCoresVectorStore vector store = SynapCoresVectorStore uri="http://localhost:8080", table name="llama nodes", embedding dim=1536, index = VectorStoreIndex.from documents docs, storage context=... response = index.as query engine .query "What is in the docs?" | Package | Class | Status | |---|---|---| llama-index-vector-stores-synapcores | SynapCoresVectorStore llama-index-graph-stores-synapcores SynapCoresPropertyGraphStore A hybrid retriever — SynapCoresHybridRetriever combining vector + graph + SQL in a single retrieval call — is on the v0.2.0 roadmap. synapcores/community:v1.7.0.2-ce or newer needs HNSW DDL, - JSON arrow, Cypher - Default HTTP gateway on :8080 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 MIT.