はじめに Redis、キャッシュの理解を目的に、ポケモン図鑑を作りました！ その過程で気づいたことや困ったことを紹介します。 ↓今回作成したアプリのリポジトリ 作ったもの ポケモン図鑑 1000匹のポケモンを検索、表示することができます！ 技術スタック R...

High-performance Rust TUI Pokedex & Evolution Analyzer. Fetches PokeAPI data asynchronously, parses complex branch trees, and renders pixel-art sprites. - Huseynteymurzade28/pokeductor

An open RESTful API for Pokémon data

PokéAPI is superb — but one Pokémon detail is 290 KB, the list is name+url pairs (every grid tutorial ships an N+1 Promise.all), and list search is silently ignored. Extract 30 compact records via their own GraphQL beta, import as db.json, and get substring search, 3.4 KB 20-card grids via ?select=, sorting, their exact count/results envelope, real writes, and failure drills. Free, no signup.

YouTube video by Kirk M.

_This is a submission for Weekend Challenge: Passion Edition_ ## ❔ What I Built These two last weeks, my team mates started to to use Claude Code together with they yearly review : 📓 Versionner et builder l'eBook de son Entretien Annuel d'Evaluation sur Git(Hub) adriens adriens adriens Follow Mar 25 '24 ## 📓 Versionner et builder l'eBook de son Entretien Annuel d'Evaluation sur Git(Hub) #markdown #pandoc #ebook #ai 2 reactions 11 comments 6 min read **to discover which Pokemon they are... and why**. I found that really really fun... and started to wonder > if I could automate that with only onPrem resources, with embeddings, ML... only with a simple laptop without GPU, a simple core i5 and 8 Gib. And of course, only with pure Open Source software ❣️ What you'll discover below is how I started to prototype it and make it happen. ## 🍿 Demo ## 🤗 Code The whole code source is available as a HF Space, see rastadidi/resume-to-pokemon for more... or to play wth it 🤓 ## 🧰 How I Built It To achieve this first prototype I : 1. **Used the data** I already prepared with my registry.jsonresume.org/adriens 2. **Bundled dataset (built once).** `build_dataset.py` fetches every species from the PokeAPI — name, types, base stats, sprite, genus and English Pokedex flavor text. For each Pokemon it also derives a **professional-archetype profile** from its types and stat spread (e.g. a Steel type → _"a disciplined, precise, robust engineer of structured systems"_), so career resumes and monster biology meet in the same trait vocabulary. Description + profile are embedded with BAAI/bge-m3 and committed as `data/pokemon.json` + `data/embeddings.npy` — so the app makes **no PokeAPI calls at runtime**. 3. **Resume → phrases.** Sections that carry semantic signal — `basics.summary`, `skills`, `work`/`volunteer`, `projects`, `interests` — are each turned into a short phrase and embedded with the same model. (Administrative sections like education, certificates and languages are skipped.) 4. **Retrieve → rerank.** Cosine similarity over the embeddings retrieves a shortlist of the closest Pokemon; a cross-encoder (BAAI/bge-reranker-v2-m3) then re-scores the (resume, Pokemon) pairs jointly for much sharper precision than cosine alone. The tool explains _why_ by quoting the matched resume phrase and the Pokemon's own profile + Pokedex text. 5. **Ranking + relative fit.** Pokemon are ranked by a blend of the rerank match and their base stats (adjustable). Because a broad resume matches many Pokemon similarly, raw scores cluster tightly and are unreadable — so the reported score is a **relative fit** : rerank scores are standardized across the shortlist and spread through a sigmoid, so the top clearly stands out (~100%) and the tail drops off. It's a fit _relative to the candidate pool_ , not an absolute probability. The two best-fitting **types** are derived from the same shortlist, so they always agree with the ranked Pokemon. 6. **Calibrated confidence.** Instead of a raw similarity number, a read-out reports how far the top match _stands out from the field_ (a z-score over the shortlist), flagging decisive vs. diffuse, multi-type profiles. Type scores and the ranked Pokemon are derived from the _same_ reranked shortlist, so the "best-fit typing" always agrees with the cards.