From eeee3b4371cb8207a8e7a887acba3fc5afc6de4d Mon Sep 17 00:00:00 2001
From: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Date: Mon, 4 Nov 2024 14:27:56 +0100
Subject: [PATCH] docs: add explicit artifacts path example (#224)

* docs: add explicit artifacts path example

[skip ci]

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* minor docs fix

[skip ci]

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* touch to trigger needed checks

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
---
 docs/usage.md | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/docs/usage.md b/docs/usage.md
index 9399337..06d2c3c 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -115,6 +115,29 @@ doc_converter = DocumentConverter(
 )
 ```
 
+##### Provide specific artifacts path
+
+By default, artifacts such as models are downloaded automatically upon first usage. If you would prefer to use a local path where the artifacts have been explicitly prefetched, you can do that as follows:
+
+```python
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.pipeline_options import PdfPipelineOptions
+from docling.document_converter import DocumentConverter, PdfFormatOption
+from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
+
+# # to explicitly prefetch:
+# artifacts_path = StandardPdfPipeline.download_models_hf()
+
+artifacts_path = "/local/path/to/artifacts"
+
+pipeline_options = PdfPipelineOptions(artifacts_path=artifacts_path)
+doc_converter = DocumentConverter(
+    format_options={
+        InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+    }
+)
+```
+
 #### Impose limits on the document size
 
 You can limit the file size and number of pages which should be allowed to process per document: