Back to Home
asami icon

rag-system

Verified Safe

by asami

Overview

A hybrid semantic-vector retrieval engine that integrates structured knowledge graphs and embedding models for advanced RAG (Retrieval Augmented Generation) capabilities for AI agents.

Installation

Run Command
docker compose -f docker-compose.demo.yml up -d

Environment Variables

  • FUSEKI_URL
  • SIE_EMBEDDING_MODE
  • SIE_EMBEDDING_ENDPOINT
  • OPENAI_API_KEY
  • SIE_VECTORDB_ENDPOINT
  • SIESERVER_PORT
  • SIE_VECTORDB_ROUTER_MODE
  • SIE_CONFIG_MODE
  • SERVER_MODE
  • SIE_WORKSPACE_DIR
  • MCP_WS_URL
  • SIE_MCP_MERGE_MANIFEST
  • SIE_GRAPHDB_ENDPOINT
  • SIE_VECTORDB_BACKEND
  • SIE_EMBEDDING_MODEL
  • EMBEDDING_MODEL

Security Notes

The system downloads and initializes external ontology files (`site.jsonld`, `.ttl` files) from `www.simplemodeling.org` during `init-fuseki.sh` execution, which introduces a supply chain risk. The Python `chroma_server.py` loads embedding models based on `EMBEDDING_MODEL` environment variable, also presenting a supply chain risk if models are sourced from untrusted locations. The custom `SimpleHttpClient` in Scala, while functional, might not be as thoroughly vetted as widely used HTTP client libraries, potentially leading to unforeseen HTTP-related vulnerabilities. Input to SPARQL queries is URL-encoded, which mitigates direct injection, but the overall reliance on external content for initialization merits caution.

Similar Servers

Stats

Interest Score0
Security Score6
Cost ClassMedium
Avg Tokens300
Stars0
Forks0
Last Update2026-01-05

Tags

Semantic SearchKnowledge GraphRDFSKOSSmartDoxOntologySemantic RAGMCPAI Agents