Module Guides
First, check out our module guide on Indexes for in-depth guides for each index (vector index, summary index, knowledge graph index). Each index corresponds to a default query engine for that index.
Then check out the rest of the sections below.
Structured & Semi-Structured Data
Section titled “Structured & Semi-Structured Data”- Text-to-SQL
- JSON Query Engine
- Pandas Query Engine
- Polars Query Engine
- JSONalyze Query Engine
- Knowledge Graph Query Engine
- KG RAG Retriever
- Multi-Docment Auto Retrieval
Advanced
Section titled “Advanced”- Router Query Engine
- Retriever Router Query Engine
- Joint QA Summary Engine
- Sub-Question Query Engine
- MultiStep Query Engine
- SQL Router
- SQL Auto-Vector
- SQL Join Query Engien
- PGVector SQL Query Engien
- DuckDB Query Engine
- Retry Query Engine
- Citation Query Engine
- Recursive Table Retriever
- Tesla 10q Example
- Ensemble Query Engine
Advanced: Towards Multi Document Querying/Analysis
Section titled “Advanced: Towards Multi Document Querying/Analysis”This specific subsection showcases modules that help with querying multiple documents.
Experimental
Section titled “Experimental”Note for AI agents: this documentation is built for programmatic access.
- Overview of all docs: https://developers.llamaindex.ai/llms.txt
- Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md
- Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters.
- A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/python/shared/mcp/