From 43d3c74bb2088824532e9305a7b1798614ace27e Mon Sep 17 00:00:00 2001 From: Michele Dolfi Date: Mon, 15 Sep 2025 15:44:42 +0200 Subject: [PATCH] update docs and README Signed-off-by: Michele Dolfi --- README.md | 6 +++--- docs/examples/minimal_vlm_pipeline.py | 4 ++-- docs/index.md | 2 +- docs/usage/index.md | 4 ++-- docs/usage/vision_models.md | 2 ++ mkdocs.yml | 2 +- 6 files changed, 11 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index 5c921b5f..5136abfb 100644 --- a/README.md +++ b/README.md @@ -36,7 +36,7 @@ Docling simplifies document processing, parsing diverse formats — including ad * 🔒 Local execution capabilities for sensitive data and air-gapped environments * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI * 🔍 Extensive OCR support for scanned PDFs and images -* 👓 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) +* 👓 Support of several Visual Language Models ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M)) * 🎙️ Audio support with Automatic Speech Recognition (ASR) models * 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/) * 💻 Simple and convenient CLI @@ -88,9 +88,9 @@ Docling has a built-in CLI to run conversions. docling https://arxiv.org/pdf/2206.01062 ``` -You can also use 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI: +You can also use 🥚[GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M) and other VLMs via Docling CLI: ```bash -docling --pipeline vlm --vlm-model smoldocling https://arxiv.org/pdf/2206.01062 +docling --pipeline vlm --vlm-model granitedocling https://arxiv.org/pdf/2206.01062 ``` This will use MLX acceleration on supported Apple Silicon hardware. diff --git a/docs/examples/minimal_vlm_pipeline.py b/docs/examples/minimal_vlm_pipeline.py index 666c0604..9d0e83ec 100644 --- a/docs/examples/minimal_vlm_pipeline.py +++ b/docs/examples/minimal_vlm_pipeline.py @@ -9,7 +9,7 @@ from docling.pipeline.vlm_pipeline import VlmPipeline source = "https://arxiv.org/pdf/2501.17887" ###### USING SIMPLE DEFAULT VALUES -# - SmolDocling model +# - GraniteDocling model # - Using the transformers framework converter = DocumentConverter( @@ -29,7 +29,7 @@ print(doc.export_to_markdown()) # For more options see the compare_vlm_models.py example. pipeline_options = VlmPipelineOptions( - vlm_options=vlm_model_specs.SMOLDOCLING_MLX, + vlm_options=vlm_model_specs.GRANITEDOCLING_MLX, ) converter = DocumentConverter( diff --git a/docs/index.md b/docs/index.md index bfde7059..a41b1303 100644 --- a/docs/index.md +++ b/docs/index.md @@ -28,7 +28,7 @@ Docling simplifies document processing, parsing diverse formats — including ad * 🔒 Local execution capabilities for sensitive data and air-gapped environments * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI * 🔍 Extensive OCR support for scanned PDFs and images -* 👓 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) +* 👓 Support of several Visual Language Models ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M)) * 🎙️ Support for Audio with Automatic Speech Recognition (ASR) models * 🔌 Connect to any agent using the [Docling MCP](https://docling-project.github.io/docling/usage/mcp/) server * 💻 Simple and convenient CLI diff --git a/docs/usage/index.md b/docs/usage/index.md index 0eeb94a9..42d810e5 100644 --- a/docs/usage/index.md +++ b/docs/usage/index.md @@ -31,9 +31,9 @@ You can additionally use Docling directly from your terminal, for instance: docling https://arxiv.org/pdf/2206.01062 ``` -The CLI provides various options, such as 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) (incl. MLX acceleration) & other VLMs: +The CLI provides various options, such as 🥚[GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M) (incl. MLX acceleration) & other VLMs: ```bash -docling --pipeline vlm --vlm-model smoldocling https://arxiv.org/pdf/2206.01062 +docling --pipeline vlm --vlm-model granitedocling https://arxiv.org/pdf/2206.01062 ``` For all available options, run `docling --help` or check the [CLI reference](../reference/cli.md). diff --git a/docs/usage/vision_models.md b/docs/usage/vision_models.md index 6e701a3b..d181ca95 100644 --- a/docs/usage/vision_models.md +++ b/docs/usage/vision_models.md @@ -45,6 +45,8 @@ The following table reports the models currently available out-of-the-box. | Model instance | Model | Framework | Device | Num pages | Inference time (sec) | | ---------------|------ | --------- | ------ | --------- | ---------------------| +| `vlm_model_specs.GRANITEDOCLING_TRANSFORMERS` | [ibm-granite/granite-docling-258M](https://huggingface.co/ibm-granite/granite-docling-258M) | `Transformers/AutoModelForVision2Seq` | MPS | 1 | - | +| `vlm_model_specs.GRANITEDOCLING_MLX` | [ibm-granite/granite-docling-258M-mlx-bf16](https://huggingface.co/ibm-granite/granite-docling-258M-mlx-bf16) | `MLX`| MPS | 1 | - | | `vlm_model_specs.SMOLDOCLING_TRANSFORMERS` | [ds4sd/SmolDocling-256M-preview](https://huggingface.co/ds4sd/SmolDocling-256M-preview) | `Transformers/AutoModelForVision2Seq` | MPS | 1 | 102.212 | | `vlm_model_specs.SMOLDOCLING_MLX` | [ds4sd/SmolDocling-256M-preview-mlx-bf16](https://huggingface.co/ds4sd/SmolDocling-256M-preview-mlx-bf16) | `MLX`| MPS | 1 | 6.15453 | | `vlm_model_specs.QWEN25_VL_3B_MLX` | [mlx-community/Qwen2.5-VL-3B-Instruct-bf16](https://huggingface.co/mlx-community/Qwen2.5-VL-3B-Instruct-bf16) | `MLX`| MPS | 1 | 23.4951 | diff --git a/mkdocs.yml b/mkdocs.yml index e239f680..4d375b7c 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -83,7 +83,7 @@ nav: - "Custom conversion": examples/custom_convert.py - "Batch conversion": examples/batch_convert.py - "Multi-format conversion": examples/run_with_formats.py - - "VLM pipeline with SmolDocling": examples/minimal_vlm_pipeline.py + - "VLM pipeline with GraniteDocling": examples/minimal_vlm_pipeline.py - "VLM pipeline with remote model": examples/vlm_pipeline_api_model.py - "VLM comparison": examples/compare_vlm_models.py - "ASR pipeline with Whisper": examples/minimal_asr_pipeline.py