# LlamaIndex Documentation

> LlamaIndex is the company behind LlamaParse, the document parsing platform for AI agents: Parse, Extract, Classify, Split and Index as one API. The LlamaIndex Framework is its original open-source Python toolkit for RAG and agents, and LiteParse is its open-source local document parser.

## Instructions for AI agents

- API base URL: `https://api.cloud.llamaindex.ai` (EU region: `https://api.cloud.eu.llamaindex.ai`). Authenticate with `Authorization: Bearer $LLAMA_CLOUD_API_KEY`.
- API keys: https://cloud.llamaindex.ai (dashboard, free to start). Setup guide: https://developers.llamaindex.ai/llamaparse/general/api_key/
- SDKs: Python `pip install llama-cloud` (`from llama_cloud import LlamaCloud`), TypeScript `npm install @llamaindex/llama-cloud`, Go `go get github.com/run-llama/llama-parse-go`, Java `ai.llamaindex:llama-cloud`, CLI `go install github.com/run-llama/llama-parse-cli/cmd/llp@latest`. Reference: https://developers.llamaindex.ai/reference/
- Start here: https://developers.llamaindex.ai/llamaparse/quickstart/ then the product pages under https://developers.llamaindex.ai/llamaparse/
- MCP servers: the LlamaParse platform at `https://mcp.llamaindex.ai/mcp` (needs an API key) and this documentation at `https://developers.llamaindex.ai/mcp`. Setup: https://developers.llamaindex.ai/for-agents/
- Skills and plugins for Claude Code and Codex: https://developers.llamaindex.ai/llamaparse/for-agents/skills/
- Prefer the current SDKs above over the deprecated `llama-parse` and `llama-cloud-services` packages.

## Accessing Documentation Programmatically

All documentation pages are available as raw Markdown by appending `index.md` to the page URL. For example, the page at `https://developers.llamaindex.ai/llamaparse/parse/getting_started/` has its Markdown source at `https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md`.

The site also exposes REST API endpoints for searching and browsing documentation:

- **Search**: `GET https://developers.llamaindex.ai/api/search?q=<query>&limit=10&section=<section>&full-content=true` — Full-text BM25 search across all docs. `section` and `full-content` are optional.
- **Grep**: `GET https://developers.llamaindex.ai/api/grep?q=<regex>&context=0&case-sensitive=false&max-results=100` — Regex pattern matching across documentation content.
- **Read**: `GET https://developers.llamaindex.ai/api/read?path=<doc-path>&startLine=0&endLine=500` — Retrieve content of a specific documentation page (e.g. `path=/llamaparse/parse/getting_started/`). Returns the first 500 lines by default. Use `startLine` and `endLine` to paginate through longer documents.
- **List**: `GET https://developers.llamaindex.ai/api/list?section=<section>&path=<path>&depth=2` — Browse the documentation tree structure. All parameters are optional.

All API endpoints return JSON with CORS enabled (`Access-Control-Allow-Origin: *`).

## LlamaParse
- [LlamaClassify Examples](https://developers.llamaindex.ai/llamaparse/classify/examples/): Collection of examples demonstrating how to use the LlamaClassify for document classification.
- [Overview of Classify](https://developers.llamaindex.ai/llamaparse/classify/): Learn what the Classification API is, how rules work, and how to run classifications using the client SDK.
- [Connectors](https://developers.llamaindex.ai/llamaparse/connectors/): How LlamaCloud connectors sync files from Google Drive, SharePoint, S3, and Confluence into a project folder, and how connections, synced folders, and sync schedules fit together.
- [Index Examples](https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/examples/): Collection of examples demonstrating how to use Index for building RAG applications.
- [Data Sinks](https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/integrations/data_sinks/): Data sinks are the vector databases where a LlamaCloud Index stores processed document embeddings; pick the fully managed option or connect your own.
- [Data Sources](https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/integrations/data_sources/): Overview of data source integrations for Index for connecting and retrieving data for RAG use cases.
- [Embedding Models](https://developers.llamaindex.ai/llamaparse/deprecated/cloud-index/integrations/embedding_models/): Embedding models convert a LlamaCloud Index processed documents into vectors; choose from supported providers such as OpenAI, Azure, Bedrock, Cohere, Gemini, and HuggingFace.
- [LlamaSheets Examples](https://developers.llamaindex.ai/llamaparse/deprecated/sheets/examples/): Collection of examples demonstrating how to use the LlamaSheets API for spreadsheet understanding.
- [Getting Started](https://developers.llamaindex.ai/llamaparse/deprecated/sheets/): Introduction to LlamaSheets, an API for extracting regions and tables from spreadsheets.
- [LlamaExtract Examples](https://developers.llamaindex.ai/llamaparse/extract/examples/): Collection of examples demonstrating how to use the LlamaExtract Python SDK for document extraction.
- [Overview of Extract](https://developers.llamaindex.ai/llamaparse/extract/): Use Extract on the LlamaParse platform from LlamaIndex to get structured data from unstructured documents through the web UI, Python SDK, and REST API.
- [LlamaExtract Examples](https://developers.llamaindex.ai/llamaparse/extract/v1/examples/): Collection of examples demonstrating how to use the LlamaExtract Python SDK for document extraction.
- [Getting Started](https://developers.llamaindex.ai/llamaparse/extract/v1/getting_started/): Introduction to LlamaExtract, a tool for extracting structured data from unstructured documents, available as a web UI, Python SDK, and REST API.
- [Enterprise Readiness](https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/): Security, compliance, deployment, and support options for using LlamaParse Platform in enterprise applications.
- [LlamaParse documentation](https://developers.llamaindex.ai/llamaparse/): LlamaParse is the document processing platform from LlamaIndex. Parse converts PDFs, scans and Office files to markdown or JSON; Extract returns JSON in your schema; Classify, Split and Index cover sorting, segmenting and retrieval. One API key, with SDKs for Python, TypeScript, Go and Java.
- [Parse Examples](https://developers.llamaindex.ai/llamaparse/parse/examples/): Runnable example tutorials demonstrating Parse for common document workflows — first parse, chart extraction, financial table extraction, enriched forms output, custom prompts, batch processing, spreadsheets, and TypeScript/Node.js integration.
- [Overview of Parse](https://developers.llamaindex.ai/llamaparse/parse/): Parse is the document parsing product on the LlamaParse platform from LlamaIndex, built for LLM pipelines—layout-aware OCR that turns PDFs, scans, tables, and charts into clean markdown, text, or JSON.
- [Parse Examples (v1 Migration)](https://developers.llamaindex.ai/llamaparse/parse/v1/examples/): Find current Parse v2 examples for prompts, spreadsheets, and async folder processing, plus the migration guide for existing v1 integrations.
- [Self-Hosting & BYOC (Bring Your Own Cloud)](https://developers.llamaindex.ai/llamaparse/self_hosting/): Deploy LlamaCloud in your own cloud infrastructure with full self-hosting and BYOC support. Run LlamaParse, LlamaExtract, and the complete LlamaCloud platform on Kubernetes using Helm charts — on AWS, Azure, or GCP.
- [Split Examples](https://developers.llamaindex.ai/llamaparse/split/examples/): Collection of examples demonstrating how to use the Split API for document segmentation.
- [Overview of Split](https://developers.llamaindex.ai/llamaparse/split/): Introduction to the Split API, a tool for automatically segmenting concatenated PDFs into logical document sections based on content categories.
- [Overview of Verify](https://developers.llamaindex.ai/llamaparse/verify/): Verify reviews PDFs, documents, and images for signs of local tampering or synthetic fabrication and presents the evidence for further investigation.

## Python LlamaAgents & Workflows
- [Introduction](https://developers.llamaindex.ai/python/llamaagents/workflows/)

## Python Framework
- [Frequently Asked Questions](https://developers.llamaindex.ai/python/framework/community/faq/)
- [Llama Packs 🦙📦](https://developers.llamaindex.ai/python/framework/community/llama_packs/)
- [LlamaIndex Framework, by the makers of LlamaParse](https://developers.llamaindex.ai/python/framework/): LlamaIndex is the company behind LlamaParse, the document parsing platform for AI agents. The LlamaIndex framework is our original open-source toolkit for RAG and agents.
- [LlamaParse (formerly LlamaCloud)](https://developers.llamaindex.ai/python/framework/llama_cloud/)
- [Agents](https://developers.llamaindex.ai/python/framework/module_guides/deploying/agents/)
- [Chat Engine](https://developers.llamaindex.ai/python/framework/module_guides/deploying/chat_engines/)
- [Query Engine](https://developers.llamaindex.ai/python/framework/module_guides/deploying/query_engine/)
- [Evaluating](https://developers.llamaindex.ai/python/framework/module_guides/evaluating/)
- [Component Guides](https://developers.llamaindex.ai/python/framework/module_guides/)
- [Indexing](https://developers.llamaindex.ai/python/framework/module_guides/indexing/)
- [Data Connectors](https://developers.llamaindex.ai/python/framework/module_guides/loading/connector/)
- [Documents / Nodes](https://developers.llamaindex.ai/python/framework/module_guides/loading/documents_and_nodes/)
- [Loading Data](https://developers.llamaindex.ai/python/framework/module_guides/loading/)
- [Ingestion Pipeline](https://developers.llamaindex.ai/python/framework/module_guides/loading/ingestion_pipeline/)
- [Node Parser Usage Pattern](https://developers.llamaindex.ai/python/framework/module_guides/loading/node_parsers/)
- [Model Context Protocol (MCP)](https://developers.llamaindex.ai/python/framework/module_guides/mcp/)
- [Models](https://developers.llamaindex.ai/python/framework/module_guides/models/)
- [Prompts](https://developers.llamaindex.ai/python/framework/module_guides/models/prompts/)
- [Callbacks](https://developers.llamaindex.ai/python/framework/module_guides/observability/callbacks/)
- [Observability](https://developers.llamaindex.ai/python/framework/module_guides/observability/)
- [Querying](https://developers.llamaindex.ai/python/framework/module_guides/querying/)
- [Node Postprocessor](https://developers.llamaindex.ai/python/framework/module_guides/querying/node_postprocessors/)
- [Response Synthesizer](https://developers.llamaindex.ai/python/framework/module_guides/querying/response_synthesizers/)
- [Retriever](https://developers.llamaindex.ai/python/framework/module_guides/querying/retriever/)
- [Routers](https://developers.llamaindex.ai/python/framework/module_guides/querying/router/)
- [Structured Outputs](https://developers.llamaindex.ai/python/framework/module_guides/querying/structured_outputs/)
- [Storing](https://developers.llamaindex.ai/python/framework/module_guides/storing/)
- [Building an agent](https://developers.llamaindex.ai/python/framework/understanding/agent/)
- [Cost Analysis](https://developers.llamaindex.ai/python/framework/understanding/evaluating/cost_analysis/)
- [Introduction to Structured Data Extraction](https://developers.llamaindex.ai/python/framework/understanding/extraction/)
- [Building an LLM application](https://developers.llamaindex.ai/python/framework/understanding/)
- [Full-Stack Web Application](https://developers.llamaindex.ai/python/framework/understanding/putting_it_all_together/apps/)
- [Putting It All Together](https://developers.llamaindex.ai/python/framework/understanding/putting_it_all_together/)
- [Q&A patterns](https://developers.llamaindex.ai/python/framework/understanding/putting_it_all_together/q_and_a/)
- [Structured Data](https://developers.llamaindex.ai/python/framework/understanding/putting_it_all_together/structured_data/)
- [Introduction to RAG](https://developers.llamaindex.ai/python/framework/understanding/rag/)
- [Indexing](https://developers.llamaindex.ai/python/framework/understanding/rag/indexing/)
- [Loading Data (Ingestion)](https://developers.llamaindex.ai/python/framework/understanding/rag/loading/)
- [Querying](https://developers.llamaindex.ai/python/framework/understanding/rag/querying/)
- [Storing](https://developers.llamaindex.ai/python/framework/understanding/rag/storing/)
- [Use Cases](https://developers.llamaindex.ai/python/framework/use_cases/)

## For AI Agents
- [Using LlamaIndex with AI Agents](https://developers.llamaindex.ai/for-agents/): A map of the MCP servers, agent skills, plugins, and workflow nodes you can use to give an AI agent LlamaIndex capabilities.
- [MCP Documentation Search](https://developers.llamaindex.ai/for-agents/mcp/): Connect to our hosted MCP server to search LlamaIndex documentation