Edge Rewrite
restyle Source code View original
// HTMLRewriter · presentation

This page was redesigned at the edge.

Cloudflare fetched the original article and streamed it through HTMLRewriter to apply an entirely new visual system without rebuilding the source page.

Jump to content

LlamaIndex

Add links
From Wikipedia, the free encyclopedia
LlamaIndex
TypePrivate
IndustryArtificial intelligence
Enterprise software
FoundedApril 1, 2023; 3 years ago (2023-04-01)
FoundersJerry Liu
Simon Suo
HeadquartersSan Francisco, California, U.S.
Websitewww.llamaindex.ai

LlamaIndex is an American artificial intelligence company headquartered in San Francisco, California.[1] LlamaIndex specializes in agentic optical character recognition (OCR) and document intelligence infrastructure, developing tools and frameworks that enable large language models (LLMs) to ingest, index, and query structured and unstructured data sources.[2][3]

History

[edit]

LlamaIndex traces its origins to a side project begun in late 2022 by Jerry Liu, then a machine learning engineering manager at AI safety startup Robust Intelligence and formerly a research scientist at Uber's autonomous vehicle division. While experimenting with OpenAI's GPT-3 model, due to its inability to work reliably with private or proprietary data and its narrow 4,096-token context window,[4][5]

Liu built a small indexing utility and published it to GitHub in November 2022, under the name GPT Tree Index.[1][5][6] Within a few months, it had accumulated over 16,000 GitHub stars, 200,000 monthly downloads, and a Discord server of roughly 6,000 developers which convinced Liu to turn it into a company.[6] Simon Suo, a former Uber colleague who later worked at autonomous-driving startup Waabi, joined LlamaIndex as co-founder.[4][7]

The company was formally incorporated in April 2023 and the project was rebranded LlamaIndex.[8] In June 2023, the company announced an $8.5 million seed round led by Greylock Partners, with participation from Jack Altman, Lenny Rachitsky, and Charles Xie.[4] The following year, a survey published by InfoWorld described LlamaIndex as an orchestration provider that helps connect large language models (LLMs) to private data sources. The survey noted that LlamaIndex was primarily focused on data ingestion, indexing, and retrieval.[9]

In March 2025, LlamaIndex, together with Cisco, LangChain, Glean, and Galileo, participated in the launch of AGNTCY, an open-source initiative intended to support interoperability and collaboration among AI agents.[10] In the same month, LlamaIndex announced a $19 million Series A funding round, bringing its total disclosed funding to approximately $27.5 million.[11][12] Investors have included Databricks and KPMG, which made a minority equity investment as part of a commercial partnership.[13][14][15] LlamaIndex simultaneously launched LlamaCloud, a managed cloud service based on the LlamaIndex framework.[1] LlamaIndex published LlamaParse, an agentic OCR uses a multi-agent pipeline combining computer vision, specialized VLMs, and LLM-based reasoning to handle document layouts, tables, charts, and handwriting that may be difficult for conventional OCR systems to handle.[1][16][17]

In October 2025, IBM released an open-source Python connector enabling IBM Db2 to serve as a vector store within LlamaIndex workflows.[18]

In March 2026, LlamaIndex released LiteParse, an open-source, TypeScript-native parsing library designed for local, offline execution. LiteParse runs entirely on the user's machine with no external API dependencies or Python requirements.[19][20] Later, LiteParse was re-launched as a Rust project with native TypeScript and Python bindings, in addition to adding markdown output.[19][20] In April 2026, LlamaIndex introduced ParseBench, a benchmark for evaluating document-parsing systems on enterprise documents.[21]

Open-source framework

[edit]

The original open-source LlamaIndex framework was developed as a Python library, in addition to its OCR products, for building retrieval-augmented generation (RAG) applications and AI agents.[3][22][8][23] The framework provides data connectors, index structures, query engines, and agent orchestration primitives. LlamaIndex introduced the Workflows abstraction, an event-driven system for creating multi-step agent pipelines with durable state, enabling long-running document processing tasks to persist across sessions.[18] The open-source libraries are commercially licensed without restriction.[24]

Publications

[edit]

LlamaIndex has been a subject of several scientific research papers, including:

  • Zirnstein, Bruno (2023). "Extended context for InstructGPT with LlamaIndex". doi:10.13140/RG.2.2.17701.31204. Retrieved 2026-07-09.
  • Braunschweiler, Norbert; Doddipatla, Rama; Keizer, Simon; Stoyanchev, Svetlana (2023). "Evaluating Large Language Models for Document-grounded Response Generation in Information-Seeking Dialogues". arXiv:2309.11838 [cs.CL].
  • Chandrasekhar, Achuth; Chan, Jonathan; Ogoke, Francis; Ajenifujah, Olabode; Barati Farimani, Amir (2024). "AMGPT: A large language model for contextual querying in additive manufacturing". Additive Manufacturing Letters. 11 100232. doi:10.1016/j.addlet.2024.100232. Retrieved 2026-07-09.
  • Korean Institute of Smart Media; Jo, Minjeong; Lee, Junghoon (2025-04-30). "Patient record-combined emergency rescue guide built upon LlamaIndex". Korean Institute of Smart Media. 14 (4): 87–97. doi:10.30693/SMJ.2025.14.4.87. Retrieved 2026-07-09.
  • Vithanage, Dinithi; Yu, Ping; Xie, Qianqian; Xu, Hua; Wang, Lei; Deng, Chao (2025). "A comprehensive evaluation of large language models for information extraction from unstructured electronic health records in residential aged care". Computers in Biology and Medicine. 197 (Pt A) 111013. doi:10.1016/j.compbiomed.2025.111013. PMID 40886641. Retrieved 2026-07-09.

References

[edit]
  1. 1 2 3 4 Wiggers, Kyle (2025-03-04). "LlamaIndex launches a cloud service for building unstructured data agents". TechCrunch. Retrieved 2026-07-09.
  2. ↑ "The scaffolding era is over. LlamaIndex says context is the new moat". Venturebeat. 2026-07-09. Archived from the original on 2026-05-06. Retrieved 2026-06-06.
  3. 1 2 "What is LlamaIndex?". IBM. 2024-08-21. Retrieved 2026-07-09.
  4. 1 2 3 Kyle Wiggers (2023-06-06). "LlamaIndex adds private data to large language models". TechCrunch. Retrieved 2026-07-09.
  5. 1 2 Liu, Jerry (2026-05-28). "RAG Is A Hack - with Jerry Liu from LlamaIndex". www.latent.space. Retrieved 2026-07-09.
  6. 1 2 "The Data Framework for LLMs". Greylock. 6 June 2023. Retrieved 2026-07-09.
  7. ↑ Eleatiche (2025-11-12). "LlamaIndex – Orchestrating Knowledge in the Age of Cognitive Capitalism". Eleatiche. Retrieved 2026-07-09.
  8. 1 2 "What Is LlamaIndex? A Guide to Building Context-Aware AI | DigitalOcean". www.digitalocean.com. 2026-03-12. Retrieved 2026-07-09.
  9. ↑ Martin Heller (2024-12-09). "Surveying the LLM application framework landscape". InfoWorld. Retrieved 2026-07-09.
  10. ↑ Rodriguez, Jesus (2025-03-12). "The Sequence Engineering #508: AGNTCY, the Agentic Framework that Brought LangChain and LlamaIndex Together". TheSequence. Retrieved 2026-06-02.
  11. ↑ Bluemner, Paul (2025-03-05). "LlamaIndex Raises $19M Series A". citybiz. Retrieved 2026-06-02.
  12. ↑ "LlamaIndex closes $19M in funding to supercharge enterprise-grade knowledge agents". KMWorld. 2025-03-04. Retrieved 2026-07-09.
  13. ↑ "KPMG LLP Makes Minority Equity Investment in LlamaIndex". KPMG. Retrieved 2026-07-09.
  14. ↑ "Databricks and KPMG Invest in AI Document Processing Platform | IDM Magazine". idm.net.au. Retrieved 2026-07-09.
  15. ↑ "Jerry Liu — LlamaIndex". Databricks Data + AI Summit. Retrieved 2026-07-09.
  16. ↑ Plumb, Taryn (2024-07-10). "How LlamaIndex is ushering in the future of RAG for enterprises". VentureBeat. Archived from the original on 2025-07-24. Retrieved 2026-06-01.
  17. ↑ "LlamaCloud and LlamaParse".
  18. 1 2 "Announcing the IBM Db2 Vector Store integration for LlamaIndex". IBM. 2025-10-22. Retrieved 2026-07-09.
  19. 1 2 "LlamaIndex Releases LiteParse: A CLI and TypeScript-Native Library for Spatial PDF Parsing in AI Agent Workflows". MarkTechPost. 2026-03-19. Retrieved 2026-07-09.
  20. 1 2 "run-llama/liteparse". LlamaIndex. 2026-07-09. Retrieved 2026-07-09.
  21. ↑ Zhang, Boyang; Acosta, Sebastián G.; Carlson, Preston; Bron, Sacha; Doulcet, Pierre-Loïc; Ospina, Daniel B.; Suo, Simon (2026). "ParseBench: A Document Parsing Benchmark for AI Agents". arXiv:2604.08538 [cs.CV].
  22. ↑ "LlamaIndex goes beyond RAG so agents can make complex decisions". Venturebeat.
  23. ↑ Ferrer, Josep. "Building a RAG Application Using LlamaIndex". KDnuggets. Retrieved 2026-06-02.
  24. ↑ run-llama. "llama_index/LICENSE at main · run-llama/llama_index". GitHub. Retrieved 2026-06-06.
[edit]
Retrieved from "https://en.wikipedia.org/w/index.php?title=LlamaIndex&oldid=1365015549"