docs: Add PaddleOCR VL parser installation requirements

- Add installation instructions for paddleocr[doc-parser] and platform-specific safetensors wheels
- Update README.md with installation requirements section for PaddleOCRVLPDFParser
- Update paddleocr-vl-parser.md documentation with installation requirements
- Bump version to 0.9.7

Fixes import error bug by documenting required dependencies before use

Author: AdemBoukhris457

README.md

@@ -376,6 +376,24 @@ parser = ChartTablePDFParser(
 
 The `PaddleOCRVLPDFParser` uses PaddleOCRVL (Vision-Language Model) for end-to-end document parsing. It combines PaddleOCRVL's advanced document understanding capabilities with DocRes image restoration and split table merging, providing a comprehensive solution for complex document processing.
 
+#### Installation Requirements
+
+Before using `PaddleOCRVLPDFParser`, install the required dependencies:
+
+```bash
+pip install -U "paddleocr[doc-parser]"
+```
+
+**For Linux systems:**
+```bash
+python -m pip install https://paddle-whl.bj.bcebos.com/nightly/cu126/safetensors/safetensors-0.6.2.dev0-cp38-abi3-linux_x86_64.whl
+```
+
+**For Windows systems:**
+```bash
+python -m pip install https://xly-devops.cdn.bcebos.com/safetensors-nightly/safetensors-0.6.2.dev0-cp38-abi3-win_amd64.whl
+```
+
 #### Key Features:
 - **End-to-End Parsing**: Uses PaddleOCRVL for complete document understanding in a single pass
 - **Chart Recognition**: Automatically extracts and converts charts to structured table format

docs/user-guide/parsers/paddleocr-vl-parser.md

@@ -2,6 +2,29 @@
 
 Guide to using the `PaddleOCRVLPDFParser` for end-to-end document parsing with Vision-Language Model capabilities.
 
+## Installation Requirements
+
+Before using the `PaddleOCRVLPDFParser`, you need to install the required dependencies:
+
+```bash
+pip install -U "paddleocr[doc-parser]"
+```
+
+Additionally, you need to install platform-specific safetensors wheels:
+
+**For Linux systems:**
+```bash
+python -m pip install https://paddle-whl.bj.bcebos.com/nightly/cu126/safetensors/safetensors-0.6.2.dev0-cp38-abi3-linux_x86_64.whl
+```
+
+**For Windows systems:**
+```bash
+python -m pip install https://xly-devops.cdn.bcebos.com/safetensors-nightly/safetensors-0.6.2.dev0-cp38-abi3-win_amd64.whl
+```
+
+!!! warning "Required Before Use"
+    These installation steps are **required** before using `PaddleOCRVLPDFParser`. Without them, you may encounter import errors.
+
 ## Overview
 
 The `PaddleOCRVLPDFParser` uses PaddleOCRVL (Vision-Language Model) for comprehensive document understanding. It combines PaddleOCRVL's advanced document parsing capabilities with DocRes image restoration and split table merging, providing a complete solution for complex document processing tasks.

doctra/version.py

@@ -1,2 +1,2 @@
 """Version information for Doctra."""
-__version__ = '0.9.6'
+__version__ = '0.9.7'