update: docs with lib sources and notes

docs/document_loader/image_loader/fitzpil_img_loader.md

@@ -1,3 +1,22 @@
 # Load images from PDF files (using Fitz & PIL)
 
+??? note "Note"
+    **Underlying Library:** `fitz` & `pillow`
+
+    Extract images from PDF files using `fitz` and `pillow`.
+
+    Use it in our library with:
+    ```python
+    from medrag_multi_modal.document_loader.image_loader import FitzPILImageLoader
+    ```
+
+    For more details, please refer to the sources below.
+
+    **Sources:**
+
+    - [Docs](https://pymupdf.readthedocs.io/en/latest/intro.html)
+    - [GitHub](https://github.com/kastman/fitz)
+    - [PyPI](https://pypi.org/project/fitz/)
+    - [PyPI](https://pypi.org/project/pillow/)
+
 ::: medrag_multi_modal.document_loader.image_loader.fitzpil_img_loader

docs/document_loader/image_loader/marker_img_loader.md

@@ -1,3 +1,21 @@
 # Load images from PDF files (using Marker)
 
+??? note "Note"
+    **Underlying Library:** `marker-pdf`
+
+    Extract images from PDF files using `marker-pdf`.
+
+    Use it in our library with:
+    ```python
+    from medrag_multi_modal.document_loader.image_loader import MarkerImageLoader
+    ```
+
+    For details, please refer to the sources below.
+
+    **Sources:**
+
+    - [DataLab](https://www.datalab.to)
+    - [GitHub](https://github.com/VikParuchuri/marker)
+    - [PyPI](https://pypi.org/project/marker-pdf/)
+
 ::: medrag_multi_modal.document_loader.image_loader.marker_img_loader

docs/document_loader/image_loader/pdf2image_img_loader.md

@@ -1,3 +1,26 @@
 # Load images from PDF files (using PDF2Image)
 
+!!! danger "Warning"
+    Unlike other image extraction methods in `document_loader.image_loader`, this loader does not extract embedded images from the PDF.
+    Instead, it creates a snapshot image version of each selected page from the PDF.
+
+??? note "Note"
+    **Underlying Library:** `pdf2image`
+
+    Extract images from PDF files using `pdf2image`.
+
+
+    Use it in our library with:
+    ```python
+    from medrag_multi_modal.document_loader.image_loader import PDF2ImageLoader
+    ```
+
+    For details and available `**kwargs`, please refer to the sources below.
+
+    **Sources:**
+
+    - [DataLab](https://www.datalab.to)
+    - [GitHub](https://github.com/VikParuchuri/marker)
+    - [PyPI](https://pypi.org/project/marker-pdf/)
+
 ::: medrag_multi_modal.document_loader.image_loader.pdf2image_img_loader

docs/document_loader/image_loader/pdfplumber_img_loader.md

@@ -1,3 +1,22 @@
 # Load images from PDF files (using PDFPlumber)
 
+??? note "Note"
+    **Underlying Library:** `pdfplumber`
+
+    Extract images from PDF files using `pdfplumber`.
+
+    You can interact with the underlying library and fine-tune the outputs via `**kwargs`.
+
+    Use it in our library with:
+    ```python
+    from medrag_multi_modal.document_loader.image_loader import PDFPlumberImageLoader
+    ```
+
+    For details, please refer to the sources below.
+
+    **Sources:**
+
+    - [GitHub](https://github.com/jsvine/pdfplumber)
+    - [PyPI](https://pypi.org/project/pdfplumber/)
+
 ::: medrag_multi_modal.document_loader.image_loader.pdfplumber_img_loader

docs/document_loader/image_loader/pymupdf_img_loader.md

@@ -1,3 +1,23 @@
 # Load images from PDF files (using PyMuPDF)
 
+??? note "Note"
+    **Underlying Library:** `pymupdf`
+
+    PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
+
+    You can interact with the underlying library and fine-tune the outputs via `**kwargs`.
+
+    Use it in our library with:
+    ```python
+    from medrag_multi_modal.document_loader.image_loader import PyMuPDFImageLoader
+    ```
+
+    For details, please refer to the sources below.
+
+    **Sources:**
+
+    - [Docs](https://pymupdf.readthedocs.io/en/latest/)
+    - [GitHub](https://github.com/pymupdf/PyMuPDF)
+    - [PyPI](https://pypi.org/project/PyMuPDF/)
+
 ::: medrag_multi_modal.document_loader.image_loader.pymupdf_img_loader