Indexing controls how your organization's documents and other knowledge are broken down and stored so the Enterprise Search agent can retrieve them. This screen mirrors the AI Agent editor's Indexing settings exactly.

Overview

Indexing organizes and structures information to accelerate lookup and retrieval. You set the storage and embedding model, a Default Strategy for parsing and chunking, optional per-format overrides, graph-based indexing, and chunk-level enrichment. Changing indexing settings re-indexes all knowledge already added. The section saves automatically.

Storage and embedding model

The Storage group holds the basics:

• Knowledge Store — the vector store for indexed data. Open Search is the store, and the field is fixed.

• Embedding Model — converts organized data into vector points to match against a user's query. It defaults to your workspace's default embedding model; pick another from the catalog if needed.

• Retention Period — how long to keep your knowledge stored.

Parsing

Under the Default Strategy, the Parsing step decides how raw files are read. Choose a Parsing Method:

• Application — use an external application to parse the file.

• Agentic — use a vision LLM for parsing.

• Automation — use a custom workflow for parsing.

Use Application for standard documents, Agentic for complex or visual layouts a vision model reads better, and Automation when you have a custom parsing pipeline. At runtime, the default application parser is the platform's built-in document reader; if a strategy's parser is missing or misconfigured, indexing falls back to the built-in reader rather than failing. Word documents and presentations are converted to PDF before parsing, and images extracted from documents can be described by a vision model and indexed alongside the text.

Chunking

The Chunking step splits parsed text into retrievable pieces. Pick a Chunking algorithm — Recursive Character Text Splitter, Token Text Splitter (the default), Character Text Splitter, Language aware Text Splitter, Code Text Splitter, or Semantic Text Splitter — then set Max chunk size (default 512) and Chunk overlap, the number of characters shared between adjacent chunks. Some algorithms add options: the recursive splitter takes a Delimiter, the Semantic Text Splitter uses an embedding model plus a Threshold type, and the Code Text Splitter takes a programming Language. Turn on Use Summarizing Model to create concise summaries of longer text chunks.

Images, audio, and tables

Which settings win

Indexing settings can exist at several levels, and the most specific one wins. For parsing and chunking strategies, a per-source Mimetype override beats the agent's or knowledge set's per-format strategies, which beat the global workspace per-format strategies; if nothing matches the file's type, the Default Strategy applies, and absent any configuration the platform default is used. The embedding model resolves the same way — knowledge source, then knowledge set, then agent, then the workspace's default. Because embedding models with different vector dimensions use separate indexes, changing the embedding model re-embeds everything.

Per-format strategies, graph-based indexing, and enrichment

Three options extend the default strategy:

• New Indexing Strategy — add a strategy that applies only to specific file types, so, say, PDFs and spreadsheets index differently.

• Enable Graph-Based Indexing — automatically extract entities and relationships from added knowledge to build a connected knowledge graph, supporting relationship-aware retrieval.

• Enrichment Strategies — add metadata to each chunk to support accurate and context-driven retrieval, computed via Manual Value, LLM Powered generation, or an Automation.

Choosing Automation opens a three-step wizard: Select Automation, Map Input Schema (mapping the source schema to the automation's input fields), and Map Output Schema (mapping the automation's returned fields to the enrichment schema). Enrichment runs during indexing as each chunk is processed — the computed fields are stored on the chunk and can be used for metadata filtering at retrieval time and shown in citations. If PII masking is configured, sensitive values are redacted from chunks at this stage too, before anything is embedded or stored.

If the embedding model's connection is missing

Indexing runs through the models you select, and each model draws its credentials from a connection. If that connection is deleted, deactivated, or replaced, indexing can't reach the model and the source fails to index. Fix it from the Model Library — the model shows a state like Connection Missing, Inactive Connection, or Connection Unavailable — use Switch Connection to point it at a working connection, then re-index.