[docs] Custom Models for Fastembed #1341
Conversation
✅ Deploy Preview for condescending-goldwasser-91acf0 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
There was a problem hiding this comment.
Thanks for taking that over! I left some comments, and I think we should refactor FastEmbed before publishing it.
Moreover, we could just show how to do it for a single model, and not for two. The idea is the same, and people will rather use this doc to bring their own models, not these particular ones either way.
| ## Why Use Qdrant with FastEmbed? | ||
|
|
||
| Qdrant seamlessly integrates with vectorization solutions like FastEmbed, offering a high-performance, distributed vector search engine. Combining Qdrant's scalable infrastructure with custom models enhances: | ||
| - Personalized search experiences | ||
| - Real-time recommendations | ||
| - Advanced semantic understanding for niche domains | ||
|
|
There was a problem hiding this comment.
I think people already know the benefits if they start to read this article.
| # Monkey patch the __init__ method | ||
| ImageEmbedding.__init__ = custom_init |
There was a problem hiding this comment.
Monkey-patching is an antipattern, and if that's the only way to do it, we need to make FastEmbed easier to extend. @joein What do you think?
| ## Practical Applications with Qdrant | ||
|
|
||
| By leveraging Qdrant alongside FastEmbed, businesses can unlock: | ||
| - **Intelligent Search**: Enable users to find relevant content faster. | ||
| - **Enhanced Recommendations**: Deliver tailored suggestions in e-commerce, media, and more. | ||
| - **Domain-Specific Insights**: Power unique applications in medicine, law, or academia. | ||
|
|
There was a problem hiding this comment.
Our users rather understand why they want to achieve. If that's not for SEO, I would remove this part.
|
|
||
| ## Get Started Today | ||
|
|
||
| Ready to enhance your AI-powered solutions? Explore Qdrant’s capabilities and integrate it with FastEmbed for cutting-edge vector search and semantic analysis. [Learn More](https://qdrant.tech/) |
There was a problem hiding this comment.
The CTA could have been to create a free-tier cluster on the Cloud. People are already on the qdrant.tech domain.
Preview