Edmund Documentation
/USER MANUAL

Data sources

Connect an operational database as a data source: add it under the organization's Data sources, pick the database type your feature flags allow, fill in the connection details, and add a description that sharpens query accuracy.

Administrator Last reviewed July 2026

A data source is a live connection to an operational database — stock, spare parts, fault history — so Edmund can answer from current and historical values, not just uploaded manuals. A project’s knowledge can also include documents, PLC programs and maintenance journals; the database is the part that stays connected live rather than being uploaded.

Databases are managed for the whole organization under Data sources (Datové zdroje in the left navigation) and assigned to the projects that should query them.

Warning

Connecting a database is an administrator task. Everyone can see which sources a project uses, but only an Administrator can add or change a connection.

Add a data source

  1. In Organization settings, open Data sources (Datové zdroje). The overview lists every connected database and whether its connection is live — Spojení navázáno means the connection is established.

  2. Click Add data source (Přidat zdroj dat).

  3. Pick the database type. Which types appear depends on your organization’s feature flags — PostgreSQL, Microsoft SQL Server, Oracle Database, InfluxDB or Snowflake.

  4. Fill in the connection details — Connection name (Název spojení), Host URL (URL hostitele), Database name (Název databáze), and the Username (Uživatelské jméno) and Password (Heslo) of a read-only account — then choose Next (Další).

  5. In the wizard’s second step, Project assignment (Přiřazení projektu), pick the project (or projects) that should query the source, and save. Each project’s settings page shows its assigned sources under Data sources (Zdroje dat).

A real connected source — a Snowflake warehouse, with the connection established.
Pick the database type when adding a data source.

Add a description

Each database can carry a Database description (Popis databáze) — a field on the connection form, also reachable later by clicking the database in the data-source overview. It’s optional, but a well-written description markedly improves query accuracy — describe what the tables hold and how they relate, so Edmund knows where to look.

Tip

Spend the time on the description. It’s the single biggest lever on how well Edmund reads your database.

Connect with a read-only account

Warning

Connect with a database account that only needs to read the data Edmund should see. Read-only access is the safe practice — it keeps queries from ever changing your data.

How database answers look

An answer drawn from a connected database, returned as a table of matching rows.

A database answer comes back as a results table plus a short summary, pulled live at query time — not as Source links, which belong to document and journal answers. See Reading answers & citations.

And when a table isn’t enough, ask for a chart — Edmund draws it from the query result right in the chat, with Exportovat PNG (Export PNG) to take it away:

A real database answer charted in chat — fault frequency by rank with the cumulative share, drawn from the connected warehouse.