Files
LocalAI/docs/content/features/simple-office.md
T
mudler-agentandEttore Di Giacinto 16acc8926b feat(addons): simplify Office and discover Tables (#13029)
* feat(tables): list accessible databases

Let agents discover existing databases through the host gateway.
Keep listing actor-scoped and separate from executable tools.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test(tables): verify database listing authority

Exercise model discovery through the real owner and carrier.
Check shared access, revocation, denial and resource limits.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(tables): bundle database search guidance

Teach agents to discover existing databases before querying records.
Package and verify the skill with the Tables add-on.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test(tables): cover packaged chat skill gates

Load the real receipt-verified Tables instructions through the temporary
Studio workspace. Check the index and load refusal after runtime, chat
switch and saved-agent grant changes.

This fixture starts at the receipt and broker boundary; packaging tests
cover artifact construction and integrity separately.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(office): parse Markdown and CSV inputs

Convert bounded text inputs into document and workbook structures.
Render supported Markdown formatting without fetching external content.
Preserve spreadsheet fields as strings rather than inferring formulas.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(office): preserve list markers, breaks and PDF page margins

Cover actual DOCX breaks and tabs, explicit zero list starts, empty list rejection, and PDF margin/pagination regressions.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(office): guard Markdown parsing work

Check cancellation and nesting during parser callbacks.
Validate table dimensions before padded table allocation.
Keep parser state isolated to each conversion.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(office): recognize tables before applying limits

Leave mismatched table-like paragraphs as ordinary Markdown.
Keep oversized real tables bounded before allocation.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(office): simplify document creation inputs

Accept Markdown for DOCX and PDF, and CSV for single-sheet XLSX files.
Replace nested creation schemas to reduce model tool grammar complexity.
Keep existing read, edit and PowerPoint behavior and internal office IDs.

Present the add-on as Simple Office and document the compatibility change.
Keep same-style Markdown fragments editable in generated DOCX files.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(ci): align add-on fixtures and test inventories

Tables fixtures must carry the skill their manifest declares. Preserve
its bytes in package tests and mark only binaries executable in UI
fixtures. Assert that installation keeps the shipped skill intact.

Register the new Tables tests and the connector case from master in
exact suite inventories. Include the new database read in tool counts.

Run Office regressions through Ginkgo and check reader close errors.
Keep all document assertions and the existing CI gates intact.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: nib:gpt-6.1-sol

* fix(ci): restore Office and packaging checks

Keep the generated Office label consistent with Simple Office. Install
Poppler for the PDF layout regressions on Linux and macOS.

Separate successful runtime setup from the 300 ms deadline under test.
Keep the timeout, cancellation, stop and admission assertions intact.

Refresh the packaging inventory from all 209 executed cases, retaining
repeated platform checks and the Office and Tables skill checks.

Assisted-by: nib:gpt-6.1-sol
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-11-02 12:48:08 +01:00

71 lines
3.5 KiB
Markdown

---
title: "Simple Office"
weight: 35
---
Simple Office is a lightweight add-on for basic Word, Excel, PowerPoint and
PDF file work in chats, without requiring Sandbox. Install `office` from the
add-on library. Its internal ID, tool names, settings and resource references
remain `office`; the visible name is **Simple Office**. Sandbox workflows remain
independent. There is no automatic fallback, routing or provider preference change.
## Create documents with Markdown
`create-docx` and `create-pdf` require string fields `path` and `markdown`.
Optional `title` is string metadata only; it does not add a visible heading.
```json
{"path":"/reports/summary.docx","markdown":"# Summary\n\nA **bold** paragraph.\n\n- First\n- Second","title":"Report"}
```
Use a `.pdf` path with `create-pdf`. Both formats support headings, paragraphs,
bullet and numbered lists, bold/italic emphasis, and simple rectangular tables.
Inline and fenced code are literal text, never executed. Links show visible
labels without fetching their targets. Raw HTML, images and unsupported
constructs are rejected with an error. No network fetching, file inclusion,
macros, shell commands or external converters are used.
Limits are 2000 document blocks, 100 items per list, 20 table columns and
500 body rows per table. The full JSON argument budget is 1 MiB; parsing is
bounded internally. PDF retains its built-in-font Latin-1 restrictions;
unsupported characters are refused before saving. No fonts or Unicode support
are added by this change.
## Create a single-sheet workbook with CSV
`create-xlsx` requires string fields `path` and `csv`; optional string `sheet`
defaults to `Sheet1`, and optional string `title` is workbook metadata.
```json
{"path":"/reports/status.xlsx","csv":"Worker,Status\n00123,Healthy\n","sheet":"Status"}
```
CSV uses commas and standard quoting, including escaped quotes and multiline
quoted cells, with LF or CRLF line endings. There is no delimiter guessing.
Exactly one sheet is created. The first row is ordinary data, with no implicit
header styling. Every nonempty field is stored as a string: leading zeros and
values beginning with `=`, `+`, `-` or `@` are preserved, not inferred as numbers
or formulas. Empty cells stay blank at their original coordinates. Use
`edit-xlsx` afterwards for explicit numeric cells, formulas or additional sheets;
its existing behavior has not changed.
Malformed quoting, ragged rows, only-empty content and invalid sheet names are
refused. Limits are 5000 rows, 200 columns and 100000 grid cells, including empty
fields, within the full 1 MiB JSON argument budget.
## Compatibility change
The three creation tools no longer accept the old `blocks` (DOCX/PDF) or
`sheets` (XLSX) structures. Update callers to `markdown` or `csv` respectively.
All advertised arguments of these three tools are strings; there is no alternate
structured-array creation contract. Read/edit tools and `create-pptx` are unchanged.
Multiple-sheet creation is not supported by `create-xlsx`.
All paths are inside the caller's authorized workspace, not arbitrary host paths
or content URLs. Chat folder and read-only access rules still apply. Failed
parsing or rendering saves no new file. Existing files are never overwritten by
creation: a conflict saves the new result to a sibling path and reports it.
Cancellation, authorization, extension checks and atomic workspace storage remain
in force. These simplified catalog schemas are not evidence of live model tool
selection or of general native grammar-parser correctness.