I scanned Langfuse. It observes its own LLM calls through its own platform.
Langfuse is an open-source observability platform that tracks its own LLM calls. It utilizes LangChain for features like prompt testing and evaluations, ensuring that internal usage generates production traces. The architecture allows the team to identify issues before customers do, enhancing the platform's reliability.
- ▪Langfuse uses LangChain to power features such as a playground for testing prompts and LLM evaluations.
- ▪The platform processes its own LLM calls through a callback handler, allowing for self-observation.
- ▪Langfuse integrates with six different LLM providers through a unified interface.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3951700) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } Ryan Smith Posted on May 28 I scanned Langfuse. It observes its own LLM calls through its own platform. #opensource #ai #webdev #typescript Scanning Open Source (3 Part Series) 1 I scanned Dub's codebase. It's not a link shortener. 2 I scanned Inbox Zero. It has a comprehensive prompt injection defense system. 3 I scanned Langfuse. It observes its own LLM calls through its own platform. Post 3 of "Scanning Open Source." So far: Dub hides a fraud engine.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
