RAG systems have a recall problem, not a hallucination one
engineering llm machine_learning"As an AI language model, your RAG pipeline sucks and I'm pretty sure there's information you're not giving me..."
Blogs
Obsidian Templater Workflow for Chinese Language Learning
taiwan 中文 obsidianPairing Obisian with Taiwan's Open Source dictionary for vocabulary acquisition and practice
Semantic Router: GPT-4o API video sampling via semantic chunking
llm semantic_routerA sampling strategy for the GPT-4o API 2-4 frames per second requirement
Setup a Remote NVIDIA AI Workbench Node using EC2
nvidia devopsHow to run GPU-accelerated ML workloads with ease using NVIDIA's AI Workbench and a CUDA-enabled EC2 instance.
Semantic Router: Postprocessing LLM output using Semantic Splitters
llm semantic_routerTrim extraneous LLM output automatically. No regex, no string parsing.
Bogdan's Taipei Spots
taiwan lifeWhat I like to do in and around Taipei
Semantic Router: Steer local LLMs for decision-making and more
llm semantic_routerUse LLM and agent input semantic meaning as a superfast decision layer for your applications
Formal Grammars for Large Language Models
llmGet useful, structured output from even the smallest of LLMs
Quick classification of Taiwan's Indigenous Weapons Programmes
taiwan militaryThe unveiling of Taiwan's Hai Kun-class submarine is flexing the country's military-industrial muscles
Deploying HuggingFace models on NVIDIA-enabled EKS nodes
engineering devopsUse battle-tested container orchestration for your GPU-enabled inference workloads, with baked-in telemetry from Prometheus
1 of 2
Next Page