Data Sources (RAG)

Data sources are the foundation for retrieval-augmented generation (RAG) in MeinGPT. Content from connected sources is indexed and made available to your assistants as knowledge. You can also pick a data source directly in a chat when you only want to look something up once. A normal chat without an assistant also searches every data source the person is allowed to use on its own – see Data sources in normal chats.

Add a data source

Open Settings → Data sources and click Add data source:

You connect each of these sources directly under Settings → Data Sources, with no hardware of your own.

Cloud data source at a glance

For most teams, the cloud-based data source is the right choice.

Cloud data pools share one storage budget per workspace: by default 300 GB of raw imported data, combined across all of the workspace's cloud data pools. Once the budget is used up, no new content is indexed until space frees up again - for example by removing files you no longer need. As an admin, you can see current usage under Settings → Data sources.

SharePoint Connector vs. data source: which one when?

If you want to use SharePoint data in MeinGPT, you have two options: the native Microsoft 365 Connector, or a data source with SharePoint as a source. Both have their strengths.

Rule of thumb:

• Microsoft 365 Connector for most SharePoint use cases. Especially when each user should only see what they are allowed to see in SharePoint itself.
• Data source when you want to index large stocks centrally, mix multiple sources, or build a central knowledge base without individual permissions.

Configuration & recommendations

Narrow the data scope

There is no hard data limit. But the more data a data source covers, the more irrelevant hits compete with the relevant ones. Recommendation:

• When you connect a SharePoint/OneDrive folder, all subfolders are included automatically - you don't need to add subfolders as their own data source
• Connect 500 to 1,000 relevant files per data source in a targeted way, not the entire SharePoint
• Prefer multiple specialized data sources over one huge one, for example "HR policies", "Product specifications", "Sales material"
• The more focused a data source, the better the results

Write the short description carefully

The short description of a data source is not just documentation. The model uses it to decide whether a data source is relevant for a given request. A poor description leads to data sources not being searched even when they should be.

Good: "Contains all internal HR policies, process descriptions, and onboarding documents."

Less good: "HR documents."

Data sources in normal chats

A normal chat – without an assistant and without a selected source – can search every data source the person is allowed to use. The model decides per question whether to search. If it finds nothing relevant, it says so in the answer. You control this as follows:

• Access: A data source that is not shared with a person is not searched in their chats. Share data sources only with the teams that need them instead of the whole workspace. Exception for workspace admins: an admin's chat searches all data sources in the workspace, including ones not shared with that admin. To check whether a share works, test with an account without the admin role.
• Short description: The model relies on it to judge whether a source fits the question. State precisely which topics the source covers and which it does not.
• Assistant without knowledge: A chat that runs with an assistant only searches the data sources assigned to that assistant under Knowledge. If the assistant has none, the chat searches none. This is how you avoid the automatic search for a chat.
• Default Assistant: If a Default Assistant is set under Settings → AI & features → Chat, it is preselected in new chats and the chat only searches its data sources. If it reads No default assistant, a new chat starts without an assistant and searches every data source the person is allowed to use. If you deselect the assistant in the chat, for example by picking a plain model, it is a chat without an assistant again.

Data source search cannot be switched off workspace-wide under Connectors.

Reference the tool in the system prompt

In assistant instructions, it pays to reference data sources explicitly. For example: "Start every conversation by retrieving relevant information from the connected data source." This makes data source usage more reliable.

Symptom: the assistant ignores a linked data pool. If an assistant answers from general knowledge instead of the data pool even though the pool is correctly synced and linked, a missing reference in the system prompt is the most common cause — not a misconfiguration of the data pool itself. Check first whether the instructions explicitly mention the data pool before investigating sync status or permissions.

Going deeper

Advanced: Customer-Managed Outpost (On-Premise)

If you want to run your own on-premise knowledge infrastructure, for example for regulated industries or special security requirements, you can run your own Outpost. Source files and the search index remain stored there; there is no permanent central copy. For a request, however, the Outpost transmits exactly what you released per folder on the Outpost: extracted text and metadata, or a copy of the original file as well. There is no second setting for this in the MeinGPT web console. Temporary sandbox processing is described under Search & Answers.

• Choose network model: On-Premise Connections
• Set up an Outpost: Set up an Outpost
• Local folders and their release level: A folder on this machine

Other sources

Besides the six Cloud sources above and manually uploaded files, there are folders and network drives only an Outpost can read. The full overview with the Cloud-vs-Outpost distinction: Data sources.

Custom Data Preparation Pipelines

For the dedicated pattern with S3 handover for third-party systems, see:

• Custom Data Preparation Pipelines

Related pages

• Code Sandbox: stage 3 of file processing, structured table analysis
• Microsoft 365 Connector: direct SharePoint, Outlook, and Teams access
• Team management: access control per data source
• Data Sources: full list of source types