Implement Wagtail Vector Search

[brylie]

Integrate Wagtail Vector Search into the current blog project to enhance content discovery and search functionality.

Objective: Enable semantic search capabilities to improve content discoverability and user experience.

Key Requirements:

1. Install and configure Wagtail Vector Search
2. Implement vector search fields in relevant content models
3. Update search functionality in views and templates
4. Generate embeddings for existing content

Expected Outcomes:

• Improved search result relevance
• Enhanced content discovery for users
• Foundation for potential advanced features (e.g., content recommendations)

Implementation Guidelines: Refer to the official Wagtail Vector Search documentation:

• Installation: https://wagtail-vector-index.readthedocs.io/en/latest/installation/
• Quick Start: https://wagtail-vector-index.readthedocs.io/en/latest/quick-start/

Technical Considerations:

• Selection of appropriate embedding provider
• Performance impact of vector search operations
• Storage requirements for content embeddings

Acceptance Criteria:

1. Vector search is functional and returns relevant results
2. Existing content is searchable using vector search
3. Search performance meets agreed-upon benchmarks
4. Documentation updated to reflect new search capabilities