# Chunking, search indexes and retrievers in Data 360

*Agentforce Specialist Study Guide · Data 360 Fundamentals · Last updated October 15, 2026 · https://www.certifyforce.com/study-guide/agentforce-specialist/data-360-fundamentals/chunking-search-indexes-and-retrievers-in-data-360*

How Data 360 makes unstructured content retrievable: chunking and vectorization, vector, hybrid and enriched search indexes, data-space scoping, and individual and ensemble retrievers with filters, versions, citations and the Retriever Playground.

- Certification: Salesforce Agentforce Specialist
- Exam section: Data 360 Fundamentals
- Study guide: https://www.certifyforce.com/study-guide/agentforce-specialist

**Official exam objective:**

> Explain foundational concepts of Data 360 such as chunking, indexing, and retrievers.

## What the exam expects

- Explain how unstructured content becomes searchable: ingestion, mapping, chunking, vectorization and the search index.
- Choose a vector or hybrid search index, and decide when enrichment or image processing is worth it.
- Configure an individual retriever: filters and filter logic, returned fields and result count, versions, citations, and the Retriever Playground.
- Decide when an ensemble retriever is needed and know its limits.
- Describe the run-time sequence: retrieve, augment the prompt, generate.

Key terms: **chunk** is a semantically meaningful passage of a document; **vector embedding** is a numeric representation of a chunk's meaning; **search index** stores chunked, vectorized content for one data model object; **individual retriever** searches one index for one use case; **ensemble retriever** runs several individual retrievers and reranks the combined results.

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Search index scope | Defined in a data space, associated with one DMO | [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5), [Example: Agentic RAG with Advanced Data 360 Setup](https://help.salesforce.com/s/articleView?id=ai.generative_ai_rag_example.htm&language=en_US&type=5) |
| Index types | Vector, hybrid and enriched; enriched chunks are turned on when creating a vector or hybrid index | [Get to Know Search Index Types in Data 360](https://trailhead.salesforce.com/content/learn/modules/search-index-types-data-cloud-quick-look/get-to-know-search-index-types-in-data-cloud) |
| Enrichment cost | Consumes Flex Credits | [Get to Know Search Index Types in Data 360](https://trailhead.salesforce.com/content/learn/modules/search-index-types-data-cloud-quick-look/get-to-know-search-index-types-in-data-cloud) |
| Filter limit | Ten filter conditions per individual retriever | [Retriever Filters Reference](https://help.salesforce.com/s/articleView?id=data.c360_a_retriever_filter_reference.htm&language=en_US&type=5) |
| Versions | Each save creates a version; one active at a time | [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5) |
| Citations | Enabled per individual retriever in AI Models | [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5) |
| Visual content | Enable image processing on the unstructured DMO search index | [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5) |
| Activation | An activated retriever is available to Prompt Builder users | [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5) |

## Check yourself

- Why does a hybrid index return a document containing an exact part number that a vector index missed?
- When is an ensemble retriever the right choice?
- Which three chunks does an enriched index generate per passage?
- Why is content chunked before indexing?

## Sources

- [Retrieve Data](https://help.salesforce.com/s/articleView?id=data.c360_a_ai_retriever_about.htm&language=en_US&type=5)
- [Get to Know Search Index Types in Data 360](https://trailhead.salesforce.com/content/learn/modules/search-index-types-data-cloud-quick-look/get-to-know-search-index-types-in-data-cloud)
- [Use Search for AI, Automation, and Analytics](https://help.salesforce.com/s/articleView?id=data.c360_a_search_index_ground_ai.htm&language=en_US&type=5)
- [Vector Search](https://help.salesforce.com/s/articleView?id=sf.c360_a_search_index_vector_index.htm&language=en_US&type=5)
- [Retriever Filters Reference](https://help.salesforce.com/s/articleView?id=data.c360_a_retriever_filter_reference.htm&language=en_US&type=5)
- [Example: Agentic RAG with Advanced Data 360 Setup](https://help.salesforce.com/s/articleView?id=ai.generative_ai_rag_example.htm&language=en_US&type=5)
- [Enhance Agents with Business Knowledge Using RAG](https://trailhead.salesforce.com/content/learn/modules/retrieval-augmented-generation-quick-look/augment-prompts-with-relevant-knowledge)
- [Enhance AI Performance with Real-World Data Insights](https://trailhead.salesforce.com/content/learn/modules/agentforce-data-library-basics/upgrade-ai-with-real-world-data)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 32 linked practice questions, and unlimited timed mock exams are included with the Agentforce Specialist pack (USD $19): https://www.certifyforce.com/practice-exams