RAG Firewall – retrieval-time guardrails for LangChain/LlamaIndex
RAG Firewall – retrieval-time guardrails for LangChain/LlamaIndex
RAG pipelines are great, but they can still retrieve "toxic" chunks: – prompt injection attempts – leaked API keys/secrets – stale or conflicting content – unapproved external URLs We built an open-source "retrieval firewall" that scans chunks before they reach the LLM: – denies injection & secrets – flags/reranks PII, encoded blobs, untrusted URLs – audit log (JSONL) of all decisions – drop-in wrappers for LangChain and LlamaIndex retrievers Install: pip install rag-firewall Repo: https://github.com/taladari/rag-firewall Curious if others here handle retrieval-time risks, or just ingest/output filtering. Would love feedback and red-team payloads.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
The Firewall for Humanity.
A Prompt-Injection Firewall for AI Agents and RAG Pipelines
sn00p – poc app firewall
Built firewall for LLMs after prompt injection bypass GPT-4s guardrails
Vectorless RAG
PageIndex – Vectorless RAG
Preprocess maximises RAG performances
The onchain firewall that stops 99% of hacks in real-time
A Firewall for AI agents with auditing
Trajeckt, a Firewall for AI Agents