A common problem with a familiar shape: a process can dial outbound to the internet, but nothing on the internet can dial it back. Your dev server on a laptop. A service in a private VPC. A homelab app behind your router. A container in a pod with no ingress. Same shape every time — outbound works, inbound doesn't. rift is a small Go binary I built to solve that. Run it as a server on a VPS you ow
A Haystack pipeline can be perfectly wired and still unsafe. The retriever returns documents. Every component did its job. But if untrusted text moved through the pipeline as ordinary context, the trust boundary was lost. That is the problem this post is about. Not bad Python. A valid component connection only says: this value fits the next component It does not say: this value is safe to influen
Posted by the RagLeap team — building RagLeap, a private-server AI business platform When we started building RagLeap, the easiest path was obvious: spin up an API, connect to OpenAI, store everything in a managed cloud database, and ship fast. The Problem Nobody Talks About You upload your documents, customer data, order history It works. But ask yourself: where is your data right now? What Our U
I like servers. Not in a "let me spend Saturday hand-tuning nginx" way. More in a "this $6 VPS is sitting right here and could probably run half my side projects" way. The weird part is that deploying to one still feels more complicated than it should. For a lot of small and medium web apps, the app itself is not the hard part. The annoying part is everything around it: building the app getting it
Comparison: Haystack 2.0 vs. RAGatouille 0.3 for Building High-Accuracy RAG Pipelines for Developer Docs Retrieval-Augmented Generation (RAG) has become the standard for building LLM-powered tools that answer questions using private or domain-specific data. For developer documentation (dev docs) — which includes technical jargon, versioned APIs, code snippets, and structured reference material —