tenfingers/fabric-docs-rlat

Microsoft Fabric Docs — rlat知识模型是一个基于Microsoft Fabric文档的预构建知识模型，专为检索增强的编码助手和LLM上下文注入而设计。目标用户为在Microsoft Fabric上构建数据湖、管道和数据仓库的数据工程师和Fabric用户。数据集提供两种版本：远程版本在首次查询时从GitHub获取数据并本地缓存，捆绑版本则完全自包含，支持离线使用。数据集包含来自Microsoft Fabric文档的语义段落，使用BGE-large-en-v1.5编码器进行编码，并采用特定的压缩和量化技术。README还提供了使用说明、示例查询、数据来源、许可详情和引用信息。

The Microsoft Fabric Docs — rlat knowledge model is a prebuilt knowledge model based on Microsoft Fabric documentation, designed for retrieval-augmented coding assistants and LLM context injection. The target audience includes data engineers and Fabric users building lakehouses, pipelines, and warehouses on Microsoft Fabric. The dataset offers two variants: a remote version that fetches data from GitHub on the first query and caches it locally, and a bundled version that is fully self-contained for offline use. The dataset includes semantic passages from Microsoft Fabric documentation, encoded using the BGE-large-en-v1.5 encoder with specific compression and quantization techniques. The README also provides usage instructions, sample queries, corpus provenance, licensing details, and citation information.