Skip to content
LlamaIndex Framework
Open Source Community
FAQ

Vector Database

  1. Do I need to use a vector database?
  2. What’s the difference between the vector databases?

LlamaIndex provides a in-memory vector database allowing you to run it locally, when you have a large amount of documents vector databases provides more features and better scalability and less memory constraints depending of your hardware.


2. What’s the difference between the vector databases?
Section titled β€œ2. What’s the difference between the vector databases?”

To check the difference between the vector databases, you can check at Vector Store Options & Feature Support.


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 β€” e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ β€” 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 β€” the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node β€” is mapped at https://developers.llamaindex.ai/for-agents/