> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lilfella.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Files and documents

> Supported formats, table naming, document search, and rescanning.

Tables become queryable sources. Documents remain searchable text read directly from the selected workspace; Fella does not create an embedding index.

## Supported formats

| Kind             | Extensions                                          | Shipped behavior                                                                                  |
| ---------------- | --------------------------------------------------- | ------------------------------------------------------------------------------------------------- |
| Delimited tables | `.csv`, `.tsv`, `.tab`                              | Loaded into SQLite; comma, semicolon, tab, or pipe delimiters can be detected from the first line |
| JSON tables      | `.json`, `.ndjson`, `.jsonl`                        | A JSON object, an array of objects, or object-per-line records becomes a table                    |
| Spreadsheets     | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`                   | Each non-empty readable sheet becomes a table                                                     |
| Documents        | `.pdf`, `.txt`, `.text`, `.md`, `.markdown`, `.log` | PDF text is extracted; text files are read directly                                               |
| Optional table   | `.parquet`, `.pq`                                   | Recognized, but usable only in a build compiled with the `duckdb` feature                         |

PDF extraction handles text-layer PDFs. Scanned or photographed documents need OCR before Fella can read them.

## Messy values

The ingestors infer integer, float, boolean, date, and text shapes. They can parse written amounts such as `$1,200.50`, treat blank-like values as missing in numeric columns, normalize unambiguous named-month dates, skip preamble rows, and drop a trailing total row. Caveats are supplied to the agent through table inspection and can appear in evidence.

## Tables and names

Use `/files` to see which table a file became. Use `/schema <name>` for its row count, column names, types, and null percentages. During an agent run, `inspect_table` can additionally return distinct counts, min/max values, ingest notes, and sample rows.

```text filename="table names" theme={null}
Bank Statement 2024.csv -> bank_statement_2024
123 transactions.json   -> t_123_transactions
report.csv + report.json -> report and report_2
```

## Documents are direct reads

`grep_files` searches catalogued document text with a case-insensitive regular expression and returns file/line matches. `read_file` accepts one or several document names. Each document is capped at 12,000 characters and a multi-document call is capped at 16,000 characters.

<Warning>
  PDF support reads selectable text only. Image-only scans return a no-text warning; Fella does not perform OCR.
</Warning>

## Rescan after changes

```text filename="fella command" theme={null}
/reindex
/files
```

`/reindex` refreshes the catalog. `/files` shows loaded sources and noticed files that could not be used. A root `.fellaignore` can exclude names and workspace-relative path prefixes.

<Note>
  `fella.md` at the workspace root is context, not a document source. Fella skips it during the data scan and injects it separately into the model prompt.
</Note>

## Related in the docs

| If you need...                   | Go to                                                                    |
| -------------------------------- | ------------------------------------------------------------------------ |
| Open or exclude a workspace path | [Open a folder](/developer-platform/using-fella/open-folder)             |
| Teach Fella file conventions     | [Context and memory](/developer-platform/using-fella/context-and-memory) |
| Run a direct query               | [Commands and shortcuts](/developer-platform/using-fella/commands)       |

<CardGroup cols={2}>
  <Card title="Open a folder" icon="folder-open" href="/developer-platform/using-fella/open-folder">
    Set the workspace boundary and understand scanning.
  </Card>

  <Card title="Ask questions" icon="message-circle-question" href="/developer-platform/using-fella/asking-questions">
    Match a question to tables, documents, or analysis tools.
  </Card>
</CardGroup>