VectorHub is a free and open-sourced learning hub for people interested in adding vector retrieval to their ML stack. On VectorHub you will find practical resources to help you -
- Create MVPs with easy-to-follow learning materials
- Solve use-case-specific challenges in vector retrieval
- Get confident in taking your MVPs to production
- Learn about different tools and vendors for your use-case
Read more about our philosophy in our Manifesto.
Here are some examples from the community, more coming soon!
Subscribe to be updated when new ones come out & check the blog section.
- 02/22 - Evaluating Retrieval Augmented Generation: How to evaluate your RAG. Understanding the challenges working with RAG and 4 ways to evaluate performance.
- 02/15 - Retrieval from Image and Text Modalities: Comparing multi-modal and singular vector embeddings with image and text data to improve retrieval quality
- 02/01 - Scaling RAG for Production: How to go from working model to a production system with step-by-step instructions.
- 01/25 - Improving RAG performance with Knowledge Graphs: Adding knowledge graph embeddings as contextual data to improve the performance of RAG.
- 01/18 - Representation Learning on Graph Structured Data: Understanding how combining KGEs and semantic embeddings can improve understanding of your solution.
- 01/11 - VDB Feature Matrix: Find the right Vector Database (VDB) for your use case.
- 01/04 - Answering Questions with Knowledge Embeddings: An introduction to knowledge graph embeddings and comparing the performance with LLMs.
- 12/15 - Vector Embeddings In The Browser: Creating an LLM powered application in browser with React.
- 12/08 - Enhancing RAG With A Multi-Agent System: Using agents to improve the performance of your RAG with a multi-agent system to improve relevance, latency, and coherence.
- 12/01 - Personalized Search: How to use vector embeddings to create personalised search recommendations with user vectors.
- 11/26 - Recommender Systems: Building a recommender system using vector embeddings when you have sparce metadata.
- 11/26 - Retrieval Augmented Generation: The basics of RAG, what it is and how to implement.
VectorHub is a free and open-sourced learning hub that is sponsored and curated by Superlinked. We encourage you to contribute or make a suggestion on our GitHub.