docs(vlm): Update SmolDocling to GraniteDocling references (#2315)

Update minimal_vlm_pipeline.py

Signed-off-by: Luis <luis.rojas@ibm.com>
This commit is contained in:
Luis
2025-09-25 05:07:39 -04:00
committed by GitHub
parent 9d67bb9ed6
commit a873200c9d

View File

@@ -3,7 +3,7 @@
#
# What this example does
# - Runs the VLM-powered pipeline on a PDF (by URL) and prints Markdown output.
# - Shows two setups: default (Transformers/SmolDocling) and macOS MPS/MLX.
# - Shows two setups: default (Transformers/GraniteDocling) and macOS MPS/MLX.
#
# Prerequisites
# - Install Docling with VLM extras and the appropriate backend (Transformers or MLX).
@@ -15,7 +15,7 @@
#
# Notes
# - `source` may be a local path or a URL to a PDF.
# - The second section demonstrates macOS MPS acceleration via MLX (`vlm_model_specs.SMOLDOCLING_MLX`).
# - The second section demonstrates macOS MPS acceleration via MLX (`vlm_model_specs.GRANITEDOCLING_MLX`).
# - For more configurations and model comparisons, see `docs/examples/compare_vlm_models.py`.
# %%