From 27fec3de6cca460c84dd4786cbf3f8549b6905ce Mon Sep 17 00:00:00 2001
From: Navanit Dubey <98005188+Navanit-git@users.noreply.github.com>
Date: Tue, 25 Feb 2025 14:47:30 +0530
Subject: [PATCH] Feature to use local vlm model too

Hi, This PR is used to let the user use the local repository or the model downloaded in their path.

I have ran this in my local.
```
from docling.datamodel.pipeline_options import PictureDescriptionVlmOptions

pipeline_options = PdfPipelineOptions()
pipeline_options.do_picture_description = True
pipeline_options.picture_description_options = PictureDescriptionVlmOptions(
     repo_id= "/opt/dlami/nvme/Qwen/Qwen2.5-VL-7B-Instruct",  # <-- add here the Hugging Face repo_id of your favorite VLM
    prompt="Extract the text from the images, if it is table extract the table format.If there are no text give 'No Image Text' response",
)
pipeline_options.images_scale = 2.0
pipeline_options.generate_picture_images = True

converter = DocumentConverter(
    format_options={
        InputFormat.PDF: PdfFormatOption(
            pipeline_options=pipeline_options,
        )
    }
)
```

Signed-off-by: Navanit Dubey <98005188+Navanit-git@users.noreply.github.com>
---
 .../models/picture_description_vlm_model.py   | 31 ++++++++++++-------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/docling/models/picture_description_vlm_model.py b/docling/models/picture_description_vlm_model.py
index 9fa4826d..d25743e0 100644
--- a/docling/models/picture_description_vlm_model.py
+++ b/docling/models/picture_description_vlm_model.py
@@ -1,5 +1,6 @@
 from pathlib import Path
 from typing import Iterable, Optional, Union
+import os
 
 from PIL import Image
 
@@ -59,18 +60,24 @@ class PictureDescriptionVlmModel(PictureDescriptionBaseModel):
         force: bool = False,
         progress: bool = False,
     ) -> Path:
-        from huggingface_hub import snapshot_download
-        from huggingface_hub.utils import disable_progress_bars
-
-        if not progress:
-            disable_progress_bars()
-        download_path = snapshot_download(
-            repo_id=repo_id,
-            force_download=force,
-            local_dir=local_dir,
-        )
-
-        return Path(download_path)
+         # Check if repo_id is a local path and exists
+        if os.path.exists(repo_id):
+            # If it exists, return the path directly
+            return Path(repo_id)
+        else:
+             # If it doesn't exist, download the repository
+            from huggingface_hub import snapshot_download
+            from huggingface_hub.utils import disable_progress_bars
+    
+            if not progress:
+                disable_progress_bars()
+            download_path = snapshot_download(
+                repo_id=repo_id,
+                force_download=force,
+                local_dir=local_dir,
+            )
+    
+            return Path(download_path)
 
     def _annotate_images(self, images: Iterable[Image.Image]) -> Iterable[str]:
         from transformers import GenerationConfig