LlamaIndex
Data framework connecting language models to private documents
LlamaIndex is profiled here as a LLM tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
LlamaIndex is an open-source data framework for connecting language models to private data, started by Jerry Liu in late 2022 as GPT Index. It covers the retrieval pipeline end to end, from loading and parsing through chunking, indexing, and querying, with event-driven agent workflows layered on top. LlamaCloud, the commercial service, adds managed parsing and extraction for complex enterprise documents. Jerry Liu started the project to give a language model access to his personal notes, and the company now serves enterprise document workloads through LlamaCloud.
Key Capabilities:
Document loaders and integrations through the LlamaHub registry
Index and query engine abstractions for RAG pipelines
Event-driven Workflows for multi-step agents
LlamaParse for layout-aware and table-aware document parsing
LlamaExtract for schema-based structured data extraction
Python and TypeScript libraries under MIT licensing
Alternative tools
- Pydantic AI
Type-safe agent framework from the Pydantic team
- LangGraph
Stateful graph orchestration for production AI agents
- Jina AI
Search foundation models and web reading APIs
- Haystack
Composable pipeline framework for RAG and agent systems
- LiteLLM
Open-source gateway that speaks every LLM API
- OpenRouter
One API for hundreds of language models