Ask questions about EU railway interoperability rules (TSIs). Answers cite the exact passage; out-of-scope questions are refused.
Translation pending
OtherPython · HTMLGitHub @cardohsoOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
GitHub star growth between the latest completed 8-hour observations
MSIME (Water Cedar Input Method) is an open-source Chinese input method for Windows, macOS, Linux, Android, iOS, and HarmonyOS, supporting full pinyin, double pinyin, and Wubi, with translation displayed next to candidate words. View download, user guide, and FAQ.
AI translation
Status Trio is a native macOS menu bar application that integrates Wi-Fi, battery, and volume into a single compact, configurable menu bar icon. It allows for various custom appearance configurations.
AI translation
The free, open-source Arc replacement for macOS. Spaces, pinned tabs, split view and Arc's shortcuts, with your Arc sidebar imported in one go.
LeanBitLab - Crafting bloat-free, efficient, privacy-focused open source experiences for Android and Linux.
RAG assistant over EU railway TSI regulations, with citations and an evaluation gate in CI
Loading the full README.
Read the full README ↗A question-answering assistant over EU railway interoperability law: the Interoperability Directive and six Technical Specifications for Interoperability (TSIs). Every answer cites the exact passage it comes from, and the assistant refuses when its sources don't cover the question. An evaluation harness runs on GitHub Actions and fails the build when answer quality, grounding or refusal behaviour drops below fixed thresholds.
Live demo: https://rail-rag.calmcliff-0073b8b6.switzerlandnorth.azurecontainerapps.io
Demo video (90 s): https://youtu.be/CVuVkNnhasc
Used by: rail-compliance-agent, a tool-using agent that runs this assistant's retrieval as one of its tools to check a train design spec against the PRM TSI, and is evaluated on its tool use (it pins this repo at one commit).
The demo scales to zero when idle, so the first request after a pause is slower: 6.7 s, measured once after 12 minutes idle (1.0 s once warm).
Stack: Python 3.12 · LangGraph · FastAPI · Azure AI Search hybrid search, BM25 + vectors (with a local Qdrant fallback) · ONNX bge-small-en-v1.5 embeddings · Gemini (generator) · gpt-oss-120b via Groq (judge) · RAGAS · Langfuse · Docker · Azure Container Apps · GitHub Actions. Runs on free tiers plus a few cents of Azure for Students credit: €0.18 in the first 3 days, mostly setup traffic. No paid plan or card is involved.
Measured on the 20-question golden set (eval/golden_set.jsonl), from GitHub Actions run 38838060201 at commit 097bfba, the commit the live demo runs. This is the gated run for dense-only retrieval; hybrid retrieval is measured below. The raw numbers are in eval/results/latest.json.
| Metric | How it's measured | Value | Gate |
|---|---|---|---|
| Faithfulness | RAGAS; judge gpt-oss-120b (a different model family from the generator) | 1.00 | ≥ 0.80 |
| Answer relevancy | RAGAS | 0.90 | ≥ 0.70 |
| Context precision | rank-weighted, against gold passage ids | 0.94 | ≥ 0.50 |
| Context recall | against gold passage ids | 0.89 | ≥ 0.70 |
| Grounding | answers cite only the documents the question is about | 1.00 | ≥ 0.90 |
| Answerable questions answered | 16 answerable questions | 0.94 (15/16) | ≥ 0.80 |
| Unanswerable questions refused | 4 out-of-scope / near-domain questions | 1.00 (4/4) | ≥ 0.75 |
Latency per question on free tiers: median 2.5 s when answered and 1.8 s when refused. The slowest answer took 73.8 s, all of it spent backing off from a free-tier rate limit.
Read these numbers with care:
q13 asks how long the Commission has to decide on a request not to apply a TSI. Its answer ("four months … deemed to have been accepted", Directive Art. 7) shares few words with the question, and dense retrieval ranked other "Commission decision" articles higher. Hybrid retrieval adds BM25 keyword search and fuses both rankings with Reciprocal Rank Fusion (RRF), in Azure AI Search and in the Qdrant fallback.
Retrieval only: the same 20 saved queries, deterministic, no LLM (eval/results/retrieval.json, python -m rail_rag.evaluation.retrieval --stores qdrant,azure):
| Dense | Hybrid | |
|---|---|---|
| Retrieval recall@8, Qdrant | 0.91 (15/16 gold in top 8) | 1.00 (16/16) |
| Retrieval recall@8, Azure AI Search | 0.91 (15/16) | 1.00 (16/16) |
| q13 gold passage rank | not in top 8 | 6 (both stores) |
| Refusal-floor decisions changed | none of 20 |
End to end, judge-free: one local run of the full pipeline in hybrid mode, compared with the dense CI run above (eval/results/hybrid-local-judge-free.json):
| Metric | Dense (CI) | Hybrid (local) | Δ |
|---|---|---|---|
| Answerable questions answered | 0.94 (15/16) | 1.00 (16/16) | +1 question (q13) |
| Context precision | 0.94 | 1.00 | +0.06 |
| Context recall | 0.89 | 0.95 | +0.06 |
| Retrieval recall@8 | 0.91 | 1.00 | +0.09 |
| Grounding | 1.00 | 1.00 | 0 |
| Unanswerable questions refused | 1.00 | 1.00 | 0 |
This is the beginning of the README. Read the rest at the original. Read the full README ↗
