What problem does it solve?
Developers working with LlamaIndex often need accurate, documentation-backed answers about RAG pipelines, indexes, retrievers, agents, and integrations without browsing hundreds of online pages. This Skill bundles 455 official LlamaIndex Python framework documents with a local search tool so answers are grounded in real documentation with cited sources.
Core Features & Use Cases
- Offline Full-Text Search: A zero-dependency Python script searches the bundled Markdown corpus by keywords, class names, or package names, with directory-prefix filtering.
- Documentation-Grounded Answers: Responses cite the exact offline document paths used, and version-sensitive claims are flagged against the snapshot boundary.
- Source Code Fallback: When the offline snapshot is insufficient, the workflow cross-checks the official GitHub repository and clearly labels source-derived conclusions.
- Use Case: Ask how to persist a VectorStoreIndex to disk, and receive a working code example with the correct package imports plus references to the exact documentation pages consulted.
Quick Start
Use the llama-index-wiki skill to explain how to build a local RAG pipeline with Ollama and HuggingFace embeddings, citing the relevant documentation.