LlamaParse (formerly LlamaCloud)
LlamaParse is the hosted document platform from the LlamaIndex team: Parse (agentic OCR), Extract (structured data in your schema), Classify, Split and Index (managed ingestion and retrieval). It gives you production-quality data for your LLM application and plugs into this framework as readers, indexes and retrievers.
It was previously called LlamaCloud. The llama-cloud package, the LlamaCloud client and the LLAMA_CLOUD_API_KEY variable keep their names; the older llama-parse and llama-cloud-services packages are deprecated in favour of llama-cloud 2.x.
Resources
Section titled “Resources”- LlamaParse documentation
- Sign up for LlamaParse to get an API key
- Parse, Extract, Classify, Split and Index docs
- Using LlamaParse from this framework
LlamaCloudIndex, the integration for the earlier version of Index
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/for-agents/mcp/
- Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/