Data Sinks
Data sinks are the vector databases where a LlamaCloud Index stores processed document embeddings; pick the fully managed option or connect your own.
Data Sinks
Section titled “Data Sinks”Once your input documents have been processed, they’re ready to be sent to their final destination: a vector database.
If you don’t want to set up and host a vector database, we offer a full-managed option in which we host the vector database for you. Alternatively, you can host your own vector database and connect it to Index:
Once the vector database is setup, they will be store using a Embedding Model of choice and will be ready to be used in your RAG use case ➡️
For the time being, the term “Data Sink” means a vector database. However, this definition of a Data Sink may expand in the future.
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/python/shared/mcp/