Logistics RAG Engine · 2026
Streaming RAG platform for logistics
An end-to-end streaming RAG application connecting a React frontend to a self-hosted vLLM inference engine.
- Role
- AI and Frontend Lead, Adilas Tech
- Year
- 2026
- Stack
- FastAPI, vLLM, Qdrant, React, SignalR, GPT-4o
At Adilas Tech I lead AI development on a logistics platform whose core is an end-to-end streaming RAG application. Operators ask questions in plain language and get grounded answers drawn from the platform's own data, streamed into the interface as they generate.
I architected the full path: a React frontend connected over SignalR to a high-throughput FastAPI inference service running vLLM, with asynchronous retrieval against a Qdrant vector store. The streaming protocol was designed so the frontend renders tokens the moment they exist, keeping perceived latency low even on long answers.
The platform runs a hybrid model strategy that I validated and implemented: a routing layer decides per query whether a self-hosted model can answer or whether the request should escalate to GPT-4o. That keeps costs predictable without capping quality on hard queries.
> key_details
- SignalR streaming protocol from FastAPI and vLLM to a React client
- Asynchronous RAG retrieval over a Qdrant vector store
- Hybrid routing between self-hosted models and GPT-4o per query
- Core patterns established for concurrent token generation