Skip to main content
The CSV, QVD and Power BI (.pbix) connectors expose data files as SQL tables. You point each connection at file paths or glob patterns, and every matching file becomes one or more tables the agent can query with SQL, join, and aggregate.
Use these when the file is a dataset. If you want the agent to search and read documents — PDFs, Word files, mixed folders — use Files and Directories instead, which exposes files as a searchable catalog rather than as tables.

​
How it works

Both connectors run on DuckDB inside Bag of words. Paths are resolved on the backend host, exactly like the Files and Directories connector, so a local folder or an already-mounted SMB/NFS share both work. There are no credential fields — access is whatever the operating system grants the backend process.
  • CSV is read natively by DuckDB. There is no conversion or cache: each resolved file is exposed directly as a table at connect time. One file, one table.
  • QVD is a proprietary binary format, so each file is converted to a columnar cache on the backend the first time it is indexed, then queried with SQL from there.
  • Power BI (.pbix) files carry an embedded semantic model, so one file yields several tables — the model’s tables, not one table per file.
Glob patterns are expanded at connect time, so adding a file that matches an existing pattern makes it available on the next index without editing the connection.

​
Before you start

  • The files exist on the Bag of words backend host and are readable by the process that runs it.
  • For a network share, mount it with the OS first. If Bag of words runs in a container, the mount must be visible inside the container.
  • Give each file a stable, meaningful filename — the filename becomes the table name the agent sees.

​
CSV

Go to Data Sources → Add data source → CSV. The settings apply to every file in the connection. If some of your CSVs are semicolon-delimited and others comma-delimited, or they use different encodings, create a separate connection per group.

​
Authentication

A single mode, No Authentication (none), at system scope. Nothing to enter.

​
QVD

The QVD connector is part of the Enterprise Edition.
Go to Data Sources → Add data source → Qlik (QVD). QVD files carry their own field names and types, so there is nothing to configure beyond the paths.
Indexing a large QVD set takes longer than CSV, because each file is converted before it can be queried. The conversion is cached, so subsequent indexing only touches files that changed.

​
Authentication

A single mode, No Authentication (none), at system scope. Nothing to enter.

​
Power BI (.pbix)

Go to Data Sources → Add data source → Power BI (.pbix). Each .pbix file contains an embedded semantic model, and every table in that model becomes a queryable table. Unlike CSV and QVD, one file therefore contributes many tables rather than one.
The data you query is the data that was last refreshed into the file, not live data from the Power BI service. A .pbix is a point-in-time snapshot: it is as current as whoever last saved it. Connect Power BI or Power BI Report Server instead when you need the live semantic model.

​
Authentication

A single mode, No Authentication (none), at system scope. Nothing to enter — access is whatever the operating system grants the backend process.

​
Troubleshooting

The glob matched nothing. Check that the path is absolute and correct from the backend host’s point of view — a path that works on your laptop is not necessarily the path inside the container.
Auto-detection picked the wrong delimiter. Set delimiter explicitly on the connection.
The file has no header row but has_header is on, or vice versa. Toggle has_header.
Set encoding to match the file — latin-1 is the usual fix for exports from older Windows tools.
That is expected. The connector reads the data saved inside the file at its last refresh. Re-save the file after refreshing it in Power BI Desktop, or connect the live Power BI semantic model instead.