0 views collected around this technical thread.
Fast.ai's Kwaipilot team unveiled OASIS, a 1.3B‑parameter code‑embedding model that, using only 5 million tokens, outperforms larger OpenAI embeddings across CodeSearchNet, CoSQA and AdvTest benchmarks, thanks to repository‑level program analysis, synthetic data generation, and a fused loss function.
The article presents Alchemy, a comprehensive code quality analysis platform that integrates static analysis, unit‑test rule scanning, duplicate‑code detection, custom rule checks, and code search into GitLab CI/CD pipelines, addressing common DevOps challenges and improving backend development efficiency.
This article introduces how to build a global code search system called 'Qianxun' from scratch, covering its background, architecture, core technologies, and future prospects.
This tutorial shows developers how to use GitHub's advanced search syntax and filters—such as name, README, description, stars, forks, language, and push date—to quickly locate relevant, actively maintained open‑source repositories for learning and practice.
This article explains why and when to scan product code for vulnerabilities, describes static source‑code and binary scanning methods, introduces deep code‑search techniques and a real‑time Sphinx‑based indexing architecture, and shows how these practices can significantly raise overall product quality.
The article explains how static source‑code scanning, binary analysis, and advanced code‑search technologies—including incremental indexing, deduplication, real‑time Sphinx indexing, and BM25 ranking—can be combined to detect and remediate product‑level vulnerabilities early, thereby significantly raising software quality and reducing risk.
In an interview, Gitee’s chief architect Chen Xin explains why Elasticsearch was chosen for code search, outlines how combining search with NLP can both aid semantic understanding and enrich repository queries, and shares his views on the platform’s fast‑evolving ecosystem and upcoming community meetup.
The article explains why and when to scan product code for vulnerabilities, describes static source‑code and binary scanning methods, introduces deep code‑search techniques, outlines the system architecture and incremental indexing pipeline, and shows how these practices can substantially raise overall product quality.