RAG Settings

RAG stands for Retrieval Augmented Generation. In plain terms: DataDios reads through a data source, turns what it finds into a searchable index, and then lets the AI look things up in that index before it answers you. The AI answers from your own data instead of guessing.

You turn this on per data source, and you turn it on yourself — nothing is indexed until you ask for it.

Which sources support it

The RAG settings tab only appears for source types that support indexing. Today that is:

Kind of source	Types
Databases	Databricks Database, MySQL, Oracle, PostgreSQL, SQL Server, Snowflake
Warehouse / query engines	Trino Engine
Files and folders	Amazon S3, Azure Blob, Folder
Knowledge bases	Confluence, GitHub Wiki, Google Drive, SharePoint
Code	GitHub
Issue trackers	Jira, ServiceNow
CRM	Salesforce Cloud
Governance	Collibra, Collibra DQ
Logs	Logs

If you do not see the tab on a source, that source type does not support RAG yet.

What gets indexed from a database

This is the part worth reading before you enable it, because databases behave differently from files.

For a database or warehouse source, DataDios indexes the shape of your tables, not the rows inside them. A table contributes its name and its column names. The values in the table are never sent to the embedding model and never stored in the index.

That is deliberate. It means you can index a production warehouse without customer data leaving it, and it keeps the index small — a table costs you one short entry however many rows it holds.

It also means the AI can answer "which table holds order totals?" but not "what was order 12345?". For questions about actual values, use AI Studio, which queries the source directly.

Every database source indexes schema only

This is enforced in the connector, for all seven database and warehouse types that support RAG: Databricks, MySQL, Oracle, PostgreSQL, SQL Server, Snowflake and Trino Engine. Even if you tick RAG Data for Selected Objects, table rows are still not indexed and the setting has no effect. Indexing contents applies to file, knowledge base, issue and code sources.

For Databricks specifically, the indexed entry holds the catalog, schema, table and column names. Primary and foreign keys are not included, because Unity Catalog treats them as informational and DataDios does not collect them.

Before you start

You need two things:

1. An embedding model data source. An embedding model is what turns text into the numbers that make meaning-based search possible. Add one under Data Sources first — any Gen AI Models source that can create embeddings, such as an OpenAI, Gemini, Cohere, Hugging Face or Ollama model. Claude does not; it has no embeddings API, so the picker here doesn't offer it.
2. Somewhere to keep the index. DataDios ships with its own built-in store and uses it by default, so there is nothing to set up. It is the only option offered today.

Turn it on

1. Go to Data Sources and find the source you want to index.
2. Open Edit connection on that source.
3. Select the RAG settings tab. The tab only appears when you are editing an existing source, not while creating one.
4. Choose your embedding data source and embedding model. Both are required.
5. Leave the rest at its defaults unless you have a reason to change it — see the table below.
6. Click Enable.

DataDios then starts an indexing job in the background. The panel shows a progress card with the last job and, if you set up automatic syncing, the next run time. You can close the dialog; the job keeps running.

To change a setting later, come back to the same tab and click Update. Update no longer changes the embedding data source or model once RAG has been enabled — both fields become read-only at that point, because a knowledge base's vectors stay tied to whatever built them. To stop indexing, click Disable. Disabling does not lift the lock: it only pauses indexing, so the source and model stay exactly as they were if you enable this knowledge base again later. To use a different embedding source or model, create the knowledge base under a new data source name instead.

A knowledge base that already had RAG enabled before this locking existed is fixed to its source and model by the upgrade. If the upgrade couldn't match one safely, it stops working until a DataDios administrator restores it: searching it, syncing it or re-enabling it is refused with "This knowledge base couldn't be matched to its embedding source during the upgrade; ask your DataDios administrator to restore it." See Manage → Integrations.

If two people enable RAG on the same data source at the same moment, one of them gets "RAG is already being enabled for this data source. Check its status in a moment." Nothing is lost: wait for the other enable to finish, then check the panel.

The settings

Setting	What it does	Default
Embedding data source	Which model turns your content into searchable numbers	your own AI · embeddings source, or the tenant default if you bound it yourself; otherwise blank, so choose one
Embedding model	Which model from that source	the model that goes with that source; otherwise blank, so choose one
Chunk size	How much text goes into one searchable piece, in tokens. DataDios estimates 1.3 tokens per word, so 1000 tokens is roughly 770 words	1000
Chunk overlap	How much each piece repeats from the one before, so a sentence split across two pieces is still findable	200
Chunking strategy	How the text is cut up. auto picks a sensible method from the file type; you can also choose tokens, sentences, paragraphs, pages, lines, semantic, code or recursive	auto
RAG Metadata for All Objects	Index the shape of every object — table and column names	on
RAG Data for Selected Objects	Also index the contents. Has no effect on any database source (see above)	off
Ingest Scope	With contents turned on, whether to cover the whole source or just objects you pick	Partial Selection
Auto Sync Interval	Re-index on a schedule: Daily, Weekly or Monthly. Leave it blank to keep auto sync off	off

Embedding data source and model are filled in only from an AI · embeddings setting you bound yourself: your own setting, or the tenant default if you are the administrator who set it — see Manage → Integrations. A tenant default someone else bound is not filled in, because that source belongs to them, so choose one of your own. Either way you can pick something else before you enable RAG here. Once RAG is enabled, changing that setting only affects knowledge bases you enable afterwards; this one keeps whatever it already resolved to.

Chunk size and overlap only matter for sources whose contents are indexed — files, wiki pages, issues and code. For a database source, each table's entry is short and these settings make no practical difference.

Where the index is used

Once a source is indexed, an agent workflow can use it as its RAG Datasource to supply extra context during analysis. The Agents module is not part of the new interface yet — see Agent workflows.

If something goes wrong

• The tab is not there. Either the source type does not support RAG (see the table above), or you are creating a source rather than editing one. Save it first, then edit it.
• No embedding models to choose from. You have not added a Gen AI model data source yet, or the one you added has no embedding model configured.
• "Select an embedding datasource." You clicked Enable with the embedding data source blank. It is blank when you have no AI · embeddings setting of your own and the tenant default, if there is one, was bound by someone else. Choose one of your own embedding sources here, or set Your own setting in Manage → Integrations. Nothing was saved. (Through the API, an enable with no source and nothing bound returns "Knowledge base RAG needs an embedding source. A tenant admin can set AI · embeddings in Manage > Integrations.")
• The job finishes but the search finds nothing. For a database source, check that RAG Metadata for All Objects is on. If you were expecting to search row values, that is not what database indexing does — see above.