OpenSearch for GenAI Storage: AgentScope Studio Practice
summary
Describes moving AgentScope Studio’s storage from PostgreSQL to OpenSearch to handle massive unstructured GenAI and agent data (prompts, responses, tool calls). Explains using OpenSearch’s full-text search plus vector capabilities for rapid keyword queries and semantic retrieval, and covers implementing vectorization for logs to improve debugging and optimization of LLM workflows.
AI-written summary · about
related talks
25mKeynote: OpenSearch in the Agentic Era
28mUse OpenSearch as Your Vector Search Database To Optimize GenAI Accuracy!
36mBuilding Next-gen Search With OpenSearch
40mBuilding Intelligent Search Systems With Agentic RAG and OpenSearch
26mOpenSearch: Conversations with Context
55mVector Search Made Simple: Getting Started with OpenSearch for AI Applications
47mBoosting AI With OpenSearch: Vector Stores, Similarity Search, and Retrieval-Augme...
43mOpenSearch Flow and Agent Frameworks: Easy AI