Multilabel Image , text and URL classification.

I am seeking to develop an advanced machine learning solution designed for multi-label tagging of images, URLs, and text content. I am open to using different models for each type of content to ensure the highest accuracy and performance. The solution should be capable of the following:

1. Image Tagging:
- Automatically generate multiple relevant tags for any given image.
- Ensure high accuracy and relevance of the tags to improve content categorization and searchability.

2. URL Content Analysis and Tagging:
- Identify if the URL points to a product page, article, or other types of content.
- Scrape the content within the URL to understand its nature.
- For product pages: Extract product images and generate relevant product tags.
- For articles: Generate appropriate tags based on the article content.

3. Text Tagging:
- Analyze text documents to generate multiple relevant tags.
- Ensure the tags accurately reflect the main topics and themes of the text.

Key Requirements:
- Expertise in computer vision and natural language processing (NLP).
- Experience with web scraping tools and techniques.
- Proficiency in Python and relevant ML frameworks (e.g., TensorFlow, PyTorch).
- Strong understanding of multi-label classification techniques.
- Ability to build and integrate the model(s) into a scalable solution.

Deliverables:
- Separate models for tagging images, analyzing and tagging URL content, and tagging text.
- A scraping tool integrated with the URL content model to process URLs, identify content types, and generate relevant tags.
- Documentation and guidelines for using the models and scraper.
- Optionally, a simple user interface to demonstrate the models' capabilities.

If you have the skills and experience to build these comprehensive multi-label tagging models, please get in touch with your proposal and relevant portfolio examples.