Search & Answers

How MeinGPT searches a data pool, what shows up in an answer, and how deep the AI goes into an individual file when needed. Setup and configuration of a data source: Data Sources & RAG.

How search works

Customer knowledge bases are often large. Hundreds or thousands of gigabytes of Word, PDF, and other files are not unusual. Sending every search query through every file would be far too slow. That is why a search index is built up front. It works similar to Google, just for your internal documents.

The initial indexing can take hours to days, depending on the data volume. Word, PDF, and similar formats are binary, so the text has to be extracted first. This one-time effort pays off in fast search results afterwards.

You do not have to wait for all of it. The index is built in two stages: keyword search first, semantic search second. A file is therefore searchable as soon as its keyword index is ready — semantic search follows in the background, file by file. You can see how far each stage has got under Indexing progress.

Search characteristics:

• Keyword search: Finds exactly the terms you type — case numbers, article numbers, proper names. It is built first and is always available.
• Semantic: Documents are converted into mathematical representations (called embeddings) that capture meaning, not just individual words. Can be turned off per data source.
• Sorted by relevance: Hits are ranked by content fit, not by frequency of a search term. A document that thematically matches the question can rank higher than one with the exact keyword.
• Number of results: By default, the ten most relevant sources are returned. The number is configurable in the settings.
• Filename search: Besides content, you can also search specifically by filename, for example "Show me file XY".

Search settings per data pool

Each data pool has four settings that decide how it is searched (open the data pool → Overview tab):

• Semantic search — additionally finds what matches in meaning but is worded differently. On by default. Turning it off is worth it when you search for exact terms anyway and the corpus is large: indexing then finishes far sooner and costs less.
• Passages per answer — how many passages may go into a single answer (default 10, range 1 to 100).
• Deep search (experimental) — hands retrieval to a dedicated search agent that runs several queries, broadening or narrowing them as needed, instead of a single direct search call. Cloud data pools only, and additionally requires deep search to be enabled for your organization.
• Improve result order — currently has no effect. The switch stores a value that is not evaluated in any search path. Leave it off.

These settings apply per data pool, not per assistant — they take effect the same way whether the pool is used directly in a chat or through an assistant.

Which value to set when, with recommendations per document type: Data pool search settings.

Indexing progress

At the top of a data source's detail page, Indexing shows one bar per stage:

• Keyword search — how many files are already searchable. Once the first files appear here, the data source is usable.
• Semantic search — how far the embeddings have caught up. If semantic search is off for this source, that is stated here instead of a bar.

Below that you can see how many files did not make it into the index: failed and skipped ones, each with its reason — such as "no text in the file", "password protected" or "too large for the configured limits". Files whose extension is not on the list of file formats are not counted here: the sync never picks them up in the first place.

For a cloud data source, this area also shows four figures: File upload (how many files the CloudVault has taken in), Searchable (how many files are currently searchable), Chunks (how many indexed text passages exist), and Last sync (the time and status of the most recent sync run). These four numbers come from two status checks against the CloudVault, not four independent ones: File upload and Chunks come from one check, Searchable and Last sync from the other. If a check fails, both numbers it covers show "Unknown" together. If all four show "Unknown" at the same time, the same underlying cause as the "Indexing status unavailable" message below has usually affected the whole area. If the platform cannot query the progress right now, the section shows the message "Indexing status unavailable" instead — for a cloud data source (CloudVault) because the CloudVault did not answer this status check, for an Outpost data source because the Outpost is offline or unreachable.

Citations in answers

Answers from a data source include numbered citations as clickable badges next to the text. Clicking one opens a preview with the title, location, and an excerpt of the original document - and, depending on the data source's release level, an option to open or download the original file.

Release level: what leaves a source

How much is available behind a citation is decided by a setting on the data source — not on the assistant. You find it under Settings → Data sources: click the source, open the Admin tab, setting "What employees get from this source".

Only Original files unlocks opening and downloading the original file from a citation — and lets the assistant load an original file into the chat or the Code Sandbox when needed.

A cloud data source inherits the Cloud Vault's level by default; the selector shows which one that currently is (at present Original files). You only need a level of its own when one source should release less than the rest. For an Outpost data source the level is set exclusively in the Outpost app, where Text only is the preset; the platform only displays the reported value.

Knowledge Map

Every cloud data source has its own Knowledge Map tab (open the data source → Knowledge Map). It shows how the documents in this pool are actually used - not manually curated, but computed from real searches over the last 30 days:

• Folder activity: The folders the assistant returns to most often.
• Knowledge map graph: A network of the documents most frequently retrieved together. Clicking a document shows its retrieval count and connected documents.

How MeinGPT works with files (3-stage model)

Not every request needs the same processing depth. MeinGPT decides per request how deep it has to go. There are three stages:

You do not have to configure anything manually. More about the sandbox: Code Sandbox.

On-premise data sources carry one extra restriction at stage 3:

Next up

Release level: what employees get from a source

Separately from who may use a data source at all (Access control), the release level determines which form of the content that source provides - for Cloud data sources as well as Outpost ones. Open the data source under Settings → Data sources → What employees get from this source:

• Text only - only text leaves this source: the content of the relevant documents, not the files themselves. Citations in chat answers still show the title, location and excerpt - but no option to open or download the original file appears.
• Original files - the file itself, in addition to the text. Users can open or download it from a citation.

A Cloud data source inherits its level from the associated Cloud Vault by default; each data source can override that. For an Outpost data source this field is read-only - the level is set only in the Outpost app, on the folder itself (Outpost).