# Jiarui-0410/multimodal-product-discovery

> Full-stack multimodal product retrieval and personalized reranking: CLIP and FAISS fetch candidates, while Spring Boot and PostgreSQL store profiles and rerank results.

- Magnitude: 4.3 out of 10 — Early signal
- Stars: 75 total · +0 stars today, ≈ 62 by evening
- Star trust: star growth looks organic
- Category: Backend & databases · Language: Python · License: MIT · Created: 2026-09-26 · Last push: 2026-09-26
- GitHub: https://github.com/Jiarui-0410/multimodal-product-discovery · Page: https://gitnova.dev/en/r/Jiarui-0410/multimodal-product-discovery

## Useful for

- Run text or image product search through the Streamlit UI and Spring Boot API
- Build personalized recommendations from a user's view, click, and purchase history
- Evaluate retrieval quality with Precision@K, Recall@K, and NDCG@K via the evaluation endpoint

## Why it’s here

- 0 stars so far today, about 62 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 75 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #178.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1
- Issues and pull requests: 0
- Watchers: 2
- Average over the last week: 69 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 6

## Stars per day, last 8 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-27: 0, 0, 0, 0, 0, 0, 76, 0

## Spotted in now

- Top new repositories this week: #178

## More in this category

1. **hydra-db/hydradb** — 5.4 · Breakout · Backend & databases · Rust · +0 stars today, ≈ 647 by evening
   HydraDB is a distributed graph database written in Rust that stores the graph durably on S3-compatible object storage, with separate data nodes and indexers. It supports OpenCypher queries, GraphBLAS traversal, Neo4j Bolt 5.x drivers, and…
   Full card: https://gitnova.dev/en/r/hydra-db/hydradb.md
2. **nodejs/node** — 3.1 · Steady · Backend & databases · JavaScript · +0 stars today, ≈ 28 by evening
   Open-source, cross-platform JavaScript runtime environment used to build server-side applications, CLI tools and build tooling. Governed by the OpenJS Foundation, it ships Current, LTS and Nightly releases.
   Full card: https://gitnova.dev/en/r/nodejs/node.md
3. **tokio-rs/toasty** — 2.7 · Breakout · Backend & databases · Rust · +0 stars today, ≈ 14 by evening
   An async ORM for Rust from the tokio team: models are defined as structs with a derive macro, supporting SQLite/Turso, PostgreSQL, MySQL and DynamoDB. It does not hide the target database's capabilities and generates queries around its…
   Full card: https://gitnova.dev/en/r/tokio-rs/toasty.md
4. **tokio-rs/tokio** — 2.6 · Steady · Backend & databases · Rust · +0 stars today, ≈ 5 by evening
   An asynchronous runtime for Rust providing non-blocking I/O, a task scheduler, timers, and network sockets. Used to build reliable concurrent applications and network services in Rust.
   Full card: https://gitnova.dev/en/r/tokio-rs/tokio.md
5. **supabase/supabase** — 2.6 · Cooling · Backend & databases · TypeScript · +0 stars today, ≈ 20 by evening
   Postgres development platform: hosted database with auth, auto-generated REST/GraphQL APIs, realtime subscriptions, file storage and edge functions. An open-source Firebase alternative.
   Full card: https://gitnova.dev/en/r/supabase/supabase.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-27 02:22 UTC, updated every 30 minutes.