# What is Document Store? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Data Infrastructure  
> **Canonical Citation:** [https://spidits.com/ai-glossary/document-store](https://spidits.com/ai-glossary/document-store)

## Definition
A Document Store is a database designed to store, retrieve, and manage document-oriented information, typically formatted as JSON, XML, or PDF structures. In RAG architectures, it holds the raw text associated with vector embeddings.

## Architectural Mechanics & Deep Dive
A document store is a type of non-relational database designed to store, retrieve, and manage semi-structured data, typically in formats like JSON, XML, or BSON. In AI retrieval and RAG architectures, document stores act as the primary repository for raw text documents, metadata, and citation sources, working in tandem with vector databases to retrieve and display source text back to users.

## Industry Applications & Real-World Use Cases
RAG pipelines, knowledge management backends, and unstructured content retrieval.

## Frequently Asked Questions

### Why does a RAG system need both a vector database and a document store?
The vector database searches for the matching IDs using mathematical embeddings. The document store retrieves the actual readable text associated with those IDs to feed to the LLM.

### Give examples of databases acting as document stores.
MongoDB, Elasticsearch, and PostgreSQL JSONB columns.

## Related Terminology
- [vector-database](https://spidits.com/ai-glossary/vector-database)
- [rag](https://spidits.com/ai-glossary/rag)
- [semantic-search](https://spidits.com/ai-glossary/semantic-search)

---
*From the SPIDITS AI Knowledge Base (336+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*