Handling LLM API Rate Limits: Retries and Backoff
Your LLM backend returns 429s the moment traffic bursts. How to retry with backoff and jitter, respect Retry-After, and pace fan-out to stay under the limit.
Your LLM backend returns 429s the moment traffic bursts. How to retry with backoff and jitter, respect Retry-After, and pace fan-out to stay under the limit.
One blocking call in a FastAPI route stalls every other request, including live SSE streams. Here is how the event loop breaks, and how to keep it free.
Retrieval puts the right chunk at rank 8, but the generator only reads the top few. How a cross-encoder reranker reorders RAG candidates, and where it fails.
How to chunk documents for a RAG pipeline: why fixed-size splitting fails, structure-aware splitting, size and overlap tradeoffs, and the failure modes.
Stream LLM output token by token from a FastAPI backend with Server-Sent Events: working code, the EventSource client, proxy buffering, and failure modes.
How to keep a RAG index fresh without full rebuilds: detect changed files with checksums, re-embed only what changed, and handle deletions safely.
AI-powered document creation platform pairing Claude with a live .docx / .pptx / .pdf / .xlsx preview. Chat on the left, documents render live on the right, each user gets their own isolated E2B sandbox.
Secured 2nd place at the Argusa AI Challenge 2025 by building ARGRAG, a RAG system for complex enterprise document corpora with multi-modal analysis, metadata intelligence, and real-time performance.
Developing, Operating and extending on WMCore + Unified, so CMS Monte Carlo and reconstruction workloads stay healthy across the WLCG sites.
Partnering with MIT to build an LLM-powered RAG copilot for CMS computing operations.
A Gemini-powered tool that turns abstract ideas and complex concepts into visually appealing mindmaps. FastAPI backend, Streamlit frontend.