BestHub
Sign in
Tagged articles
8 articles
Page 1 of 1
Baidu Tech Salon
Baidu Tech Salon
Feb 26, 2025 · Artificial Intelligence

Graph‑Engine‑Driven Workflow for Building Intelligent Agents

The article presents a graph‑engine‑driven workflow platform that lets developers assemble, orchestrate, and execute intelligent LLM‑based agents with low‑code visual design, fine‑grained path control, hierarchical sub‑flows, and event‑driven hooks, addressing perception, reasoning, planning, and scalability challenges while surpassing existing frameworks.

Data DecouplingIntelligent agentsLLM
0 likes · 19 min read
Graph‑Engine‑Driven Workflow for Building Intelligent Agents
Baidu Geek Talk
Baidu Geek Talk
Feb 24, 2025 · Artificial Intelligence

Using a Graph Engine to Drive Workflow for Intelligent Agents

By leveraging mature graph‑engine technology, the article shows how visual, low‑code workflow orchestration can give intelligent LLM‑based agents fine‑grained path control, reusable functions, hierarchical sub‑flows, and robust error handling, turning complex business tasks into modular, scalable processes adopted by hundreds of thousands of developers.

AI agentsLLMgraph engine
0 likes · 18 min read
Using a Graph Engine to Drive Workflow for Intelligent Agents
Baidu Tech Salon
Baidu Tech Salon
Oct 15, 2024 · Industry Insights

How Baidu Revamped Visual Search: From PHP to Golang and Graph Engine

This article details Baidu's visual search architecture evolution, covering the shift from a PHP/HHVM stack to Golang with the GDP framework, the adoption of the ExGraph graph engine, comprehensive system redesign, and stability infrastructure built to support rapid product iteration and AI model integration.

Backend DevelopmentGolangarchitecture
0 likes · 14 min read
How Baidu Revamped Visual Search: From PHP to Golang and Graph Engine
Baidu Geek Talk
Baidu Geek Talk
Dec 13, 2023 · Backend Development

How Baidu Revamped Its Search Display Service: From PHP to Go and Graph Engines

This article details Baidu's search display service evolution, outlining its original C and PHP/HHVM implementation, the three major challenges of high development difficulty, limited architecture capability, and low reusability, and presents a comprehensive solution using a graph execution engine, common operators, and a phased migration to Go.

BackendGoSearch
0 likes · 15 min read
How Baidu Revamped Its Search Display Service: From PHP to Go and Graph Engines
High Availability Architecture
High Availability Architecture
Dec 28, 2021 · Backend Development

Design and Practice of the Nimbus Low‑Code Platform for Search Middleware

This article examines the challenges faced by Baidu's search middleware in high‑frequency iteration and complex backend development, and presents the design, implementation, and benefits of the Nimbus low‑code platform—including a graph engine, unified development environment, visual operator composition, automated testing, and intelligent capacity management—to accelerate product innovation while reducing development effort.

DevOpscapacity managementgraph engine
0 likes · 16 min read
Design and Practice of the Nimbus Low‑Code Platform for Search Middleware
Baidu Geek Talk
Baidu Geek Talk
Dec 27, 2021 · R&D Management

Nimbus: Baidu Search Platform's Low-Code Platform Practice and Exploration

Baidu’s Nimbus low‑code platform empowers its Search Platform to meet rapid requirement iterations and growing innovation demands by using a graph‑engine‑driven, visual operator orchestration that offers one‑click cloud environments, sandboxed debugging, automated testing, and intelligent capacity management, delivering significant cost savings and efficiency across more than 200 business systems.

Baidu search platformDAG orchestrationNimbus
0 likes · 16 min read
Nimbus: Baidu Search Platform's Low-Code Platform Practice and Exploration
Youku Technology
Youku Technology
Jul 9, 2020 · Artificial Intelligence

Multi-level Multi-modal Search Engine and Graph Engine for Billion-scale Video Content

An advanced multi‑level, multi‑modal search and graph engine for Youku processes text, voice, image and video queries across hierarchical video elements, using combined vector and inverted indexes to merge cross‑level and cross‑modal results, while a distributed knowledge‑graph layer enables multimodal graph traversal for billion‑scale video retrieval.

AIgraph enginelarge-scale indexing
0 likes · 12 min read
Multi-level Multi-modal Search Engine and Graph Engine for Billion-scale Video Content
DataFunTalk
DataFunTalk
Jul 8, 2020 · Artificial Intelligence

Multi‑Level Multi‑Modal Search Engine and Graph Engine for Video Content at Youku

The article presents a detailed technical overview of Youku's video search system, covering multi‑modal inputs, multi‑level element indexing, face search, cross‑level and cross‑modal retrieval, and the design and applications of a multimodal graph engine with knowledge‑graph integration.

AIKnowledge Graphface search
0 likes · 12 min read
Multi‑Level Multi‑Modal Search Engine and Graph Engine for Video Content at Youku