Update README.md

README.md

@@ -25,6 +25,7 @@ Nanonets-OCR2: A model for transforming documents into structured markdown with
   <a href="https://docstrange.nanonets.com/" target="_blank"><strong>🖥️ Live Demo</strong></a> | 
   <a href="https://nanonets.com/research/nanonets-ocr-2/" target="_blank"><strong>📢 Blog</strong></a> | 
   <a href="https://github.com/NanoNets/docstrange" target="_blank"><strong>⌨️ GitHub</strong></a>
+  <a href="https://github.com/NanoNets/Nanonets-OCR2" target="_blank"><strong>📖 Cookbooks</strong></a>
 </div>
 
 </div>
@@ -281,7 +282,7 @@ Check out [Docstrange](https://docstrange.nanonets.com/) for more details.
 1. Increasing the image resolution will improve model's performance.
 2. For complex tables (eg. Financial documents) using `repetition_penalty=1` gives better results. You can try this prompt also, which generally works better for finantial documents.
 ```python
-user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and ☑ for check boxes."""
+user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in HTML format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the <img></img> tag; otherwise, add the image caption inside <img></img>. Watermarks should be wrapped in brackets. Ex: <watermark>OFFICIAL COPY</watermark>. Page numbers should be wrapped in brackets. Ex: <page_number>14</page_number> or <page_number>9/22</page_number>. Prefer using ☐ and ☑ for check boxes. Only return HTML table within <table></table>."""
 ```
 3. This is already implemented in [Docstrange](https://docstrange.nanonets.com/?output_type=markdown-financial-docs), please use the `Markdown (Financial Docs)` option for processing table heavy financial documents.
 ```python
@@ -296,6 +297,7 @@ data = {"output_type": "markdown-financial-docs"}
 response = requests.post(url, headers=headers, files=files, data=data)
 print(response.json())
 ```
+4. Model might work best on certain resolution for specific document types. Please check the [cookbooks](https://github.com/NanoNets/Nanonets-OCR2/blob/main/Nanonets-OCR2-Cookbook/image2md.ipynb) for details.
 
 
 ## BibTex