The Volcano Engine Developer Community, Volcano Engine's TOD community, connects the platform with developers, offering cutting-edge tech content and diverse events, nurturing a vibrant developer culture, and co-building an open-source ecosystem.
This guide walks you through installing OpenClaw, configuring a Feishu chatbot, adding the Seedance video‑generation skill, and using it to create text‑to‑video or image‑to‑video content, including detailed steps, required permissions, code snippets, and supported AI models.
This guide walks you through preparing a Windows environment, installing Node.js, Git, and OpenClaw, configuring the OpenClaw JSON file, setting up Feishu bot permissions, installing and starting the gateway, and enabling browser relay and cron tasks for AI‑driven automation.
This article explains how Volcano Engine's veDB leverages compute‑storage separation, Kubernetes operators, and declarative operations to achieve extreme deployment density, seamless scaling, and high‑availability for millions of database instances, while addressing the challenges of traditional VM‑based deployments.
This article explains the challenges of accurate RED metric collection in high‑traffic microservices, compares head‑based and tail‑based sampling, and details Volcano Engine APMPlus's multi‑level, hash‑routed tail sampling design, performance optimizations, and real‑world evaluation results.
VeDB, ByteDance's cloud‑native distributed database, combines a four‑layer monitoring architecture, AI‑driven root‑cause analysis, full‑SQL insight, and second‑level metric collection to dramatically shorten MTTR, improve reliability, and support massive, high‑concurrency workloads across diverse production scenarios.
This article explains how high‑dimensional vectors enable semantic AI search, compares exact and approximate nearest‑neighbor algorithms, examines the challenges of large‑scale vector storage, and evaluates AWS S3 Vectors' architecture, pricing, and hybrid solutions for cost‑effective, high‑performance retrieval.
veDB‑Search extends MySQL compatibility to enable AI‑driven hybrid retrieval—combining vector, full‑text, and scalar searches—through a single SQL statement, simplifying architecture, boosting performance, and supporting in‑database embedding for seamless "search everything" capabilities.
This article examines ByteDance's Jeddak AgentArmor framework, detailing the systemic risks of intent misinterpretation and constraint violations in AI agents, the full‑lifecycle threat model, dual probabilistic trust and policy mechanisms, and real‑world validation cases that demonstrate its effectiveness.
This article explains how integrating the disk‑based DiskANN index with the ultra‑compact RaBitQ quantization dramatically boosts Milvus's vector search performance and cuts costs, delivering over five times higher QPS and more than 90% cost reduction for billion‑scale AI workloads.
CollabLLM tackles the limitations of large language models in everyday multi‑turn dialogues by introducing a user‑centric, multi‑turn training framework that leverages simulated interactions, multi‑round reward modeling, and veRL toolchain support, achieving superior performance over single‑turn baselines.
