Sentence Similarity
sentence-transformers
English
Arabic
aviation
gacar
saudi-arabia
retrieval
rag
bilingual
embeddings
Instructions to use flygaca/CaptAdel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use flygaca/CaptAdel with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("flygaca/CaptAdel") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Add status: in development model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,43 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- ar
|
| 6 |
+
tags:
|
| 7 |
+
- aviation
|
| 8 |
+
- gacar
|
| 9 |
+
- saudi-arabia
|
| 10 |
+
- retrieval
|
| 11 |
+
- rag
|
| 12 |
+
- bilingual
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# CaptAdel — Fly GACA
|
| 16 |
+
|
| 17 |
+
Status: in development. This repository is the future home of the **GACAR retrieval embedding model** that powers Captain Adel, Fly GACA's independent, educational AI flight instructor for Saudi civil aviation. Model weights are not published here yet.
|
| 18 |
+
|
| 19 |
+
## What Captain Adel is
|
| 20 |
+
|
| 21 |
+
Captain Adel is a retrieval-augmented assistant: it answers GACAR questions from a curated corpus with the relevant Part cited, and refuses rather than guess when it can't ground an answer. Its answers come from retrieval over source regulations — not from a model that has memorised them. This repo will hold the retrieval piece: a bilingual (Arabic / English) embedding model fine-tuned to find the right regulation for a query.
|
| 22 |
+
|
| 23 |
+
It is a retrieval component, not a knowledge store. It does not "know" or generate regulations.
|
| 24 |
+
|
| 25 |
+
## Unofficial & educational
|
| 26 |
+
|
| 27 |
+
Fly GACA is independent and not affiliated with, endorsed by, or operated by the General Authority of Civil Aviation (GACA). Nothing here is official, legal advice, or for operational use. The authoritative source for any regulation is always GACA — https://gaca.gov.sa. Captain Adel does not provide real-time weather, NOTAMs, clearances, or airworthiness/medical decisions.
|
| 28 |
+
|
| 29 |
+
## Intended use (once weights are published)
|
| 30 |
+
|
| 31 |
+
- ✅ Embedding GACAR / aviation text and queries for semantic retrieval (EN/AR)
|
| 32 |
+
- - ✅ Powering the Fly GACA RAG pipeline
|
| 33 |
+
- - ❌ Not a source of truth for regulations · ❌ not official · ❌ not for operational decisions
|
| 34 |
+
|
| 35 |
+
- ## Evaluation
|
| 36 |
+
|
| 37 |
+
- Evaluated with the Fly GACA retrieval harness (recall@k, MRR, nDCG) against a held-out bilingual query set; numbers reported here when the model ships.
|
| 38 |
+
- ## Links
|
| 39 |
+
- Project: https://flygaca.com
|
| 40 |
+
- - Source: https://github.com/FlyGACA/flygaca
|
| 41 |
+
- - Contact: hello@flygaca.com
|
| 42 |
+
|
| 43 |
+
- © Fly GACA · Independent of GACA · Made in the Kingdom · صُنع في السعودية
|