What it does
A data framework for connecting LLMs to external data sources, primarily through Retrieval Augmented Generation (RAG) pipelines. Handles document ingestion, indexing, vector storage, and retrieval — the backbone of knowledge-grounded AI applications.
Security relevance
RAG pipelines are a primary vector for data exfiltration (LLM06) and injection attacks. LlamaIndex manages the pipeline that retrieves context and feeds it to the LLM — meaning it controls what data the model sees. Poisoning the index, manipulating retrieval, or extracting sensitive chunks are all real attack vectors.
When to use it
Study when assessing RAG-based AI applications. Using LlamaIndex to build requires data pipeline design, vector store selection, index configuration, and ongoing maintenance. Expert-level framework that underpins most enterprise RAG deployments.
OWASP coverage
Risks addressed — mapped to both OWASP Top 10 standards. 1 in LLM, 1 in Agentic.
The raw record
What Yuntona stores. Single source of truth — fork it on GitHub.
name: LlamaIndex slug: llamaindex type: Mixed category: AI Development Tools url: https://www.llamaindex.ai reviewed: 2026-04 added: 2026-04 updated: 2026-04 risks: llm: [LLM06] asi: [ASI06] complexity: Expert Required pricing: — audience: Builder lifecycle: [develop] tags: [Data, Framework, RAG]