PPL tool Prerequisite Step 1: Create a connector for a model Step 2: Register and deploy the model Step 3: Register a flow agent that will run the PPLTool Step 4: Run the agent...
Neural Sparse Search tool Step 1: Register and deploy a sparse encoding model Step 2: Ingest data into an index Step 3: Register a flow agent that will run the NeuralSparseSearch...
AI 缓存 功能说明 配置说明 配置示例 AI 缓存 功能说明 AI 缓存插件实现了将 LLM 响应进行抽取并缓存的功能,对于向 LLM API 高频请求相同问题的场景可以显著降低响应时延并节省成本。默认配置方式可以直接用于 openai 协议的结果缓存,同时支持流式和非流式响应的缓存。 需要数据面的proxy wasm版本大于等于0.2....
Build your own chatbot Prerequisite Step 1: Configure a knowledge base Step 2: Prepare an LLM Step 3: Create an agent with the default prompt Create an agent Test the agent Tes...
Understanding the implications of beta previews Possible dangers of using a beta feature How to enable feature previews ️‼️ HEADS UP! Feature previews are not stable . Please...
Examples Semantic Search LLM Pipelines Workflows Model Training Scale Architecture Releases Applications Examples See below for a comprehensive series of example not...
Examples Semantic Search LLM Pipelines Workflows Model Training Scale Architecture Releases Applications Examples See below for a comprehensive series of example not...