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

Official LlamaIndex integration packages for SynapCores — 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.

pip install llama-index llama-index-vector-stores-synapcores

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?")

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— design + implementation notesdocker/docker-compose.yml— local engine for tests

MIT.