From 6ec841871e9ecf9e440de0530655fcbf87ffac04 Mon Sep 17 00:00:00 2001 From: Issei Nakamura Date: Sat, 15 Aug 2026 06:09:49 +0000 Subject: [PATCH] docs(artifacts): document enable_spreadsheet_parsing in LoadArtifactsTool Document the `enable_spreadsheet_parsing` parameter added to `LoadArtifactsTool` in adk-python: https://github.com/google/adk-python/commit/370027a770b413ab7991afa3395dbf8be1eb89e5 - Keep the standard `LoadArtifactsTool()` example in the main Python snippet for the default behavior. - Add a dedicated "Parsing spreadsheet artifacts (Python only)" section explaining that spreadsheet files (.xlsx, .xls) cannot be read inline by default and can be parsed into Markdown tables by enabling `enable_spreadsheet_parsing=True`. - Document behavior details: rendering each sheet as a separate Markdown table and capping output at the first 100 rows per sheet to prevent context window exhaustion. --- docs/artifacts/index.md | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/docs/artifacts/index.md b/docs/artifacts/index.md index ca24ed1896..874ba0fce8 100644 --- a/docs/artifacts/index.md +++ b/docs/artifacts/index.md @@ -895,6 +895,22 @@ artifact in a later turn. and customize its request instructions before loading the selected artifact contents. + **Parsing spreadsheet artifacts (Python only):** + + By default, spreadsheet files (`.xlsx`, `.xls`) cannot be read inline by the + model. In Python, you can set `enable_spreadsheet_parsing=True` to parse + them into Markdown tables: + + ```python + tools=[ + LoadArtifactsTool(enable_spreadsheet_parsing=True), + ] + ``` + + - Each sheet is rendered as a separate Markdown table under a sheet heading. + - Table output is capped at the first 100 rows per sheet to avoid exceeding + context window limits. + === "Go" ```go