Open WebUI, RAG, Knowledge, Sentence Transformers, Embeddings models, Re-ranking models

Explore Open WebUI's Knowledge for RAG (Retrieval Augmented Generation) and how to configure embedding and reranking models. Perfect for those looking to enhance their personal AI assistants using Open WebUI. ⭐️What You'll Learn: - How to create and manage Knowledge base and documents effortlessly - The ins and outs of embedding models suitable for Open WebUI - Choosing embedding models using leaderboard - The significance of re-ranking in optimizing search results - Practical use of Hugging Face and sentence transformers ⛓️Connect with Us: 👍 Like | 🔗 Share | 📢 Subscribe | 💬 Comments + Questions LinkedIn: https://www.linkedin.com/company/casedonebyai YouTube: www.youtube.com/@CaseDonebyAI Facebook: https://www.facebook.com/casedonebyai TikTok: https://www.tiktok.com/@casedonebyai Github: https://www.github.com/casedone SubStack: https://casedonebyai.substack.com 🎬Quick navigation: 00:49 Creating and Managing Knowledge Bases 02:50 Configuring Embedding Models in Admin Page 03:50 Selecting embedding models: SBERT-based Models and Sentence Transformers 04:52 Changing and Configuring Embedding Models 05:12 Warning on Changing Embedding Models 06:00 Deleting and Re-creating with new embedding models 07:00 Syncing Directory and Resetting Knowledge Base 08:14 Exploring Embedding Models and Semantic Search with MTEB Leaderboard 09:46 Enabling hybrid search or re-ranking models 10:55 Using OpenAI API Calls for embedding models 12:45 Demonstrating Knowledge Base Usage and Errors 15:30 Summary of the whole video #genai #openwebui #rag #knowledgebase #embeddings #ollama #sentencetransformers #berts #aiforbusiness #casedone #casedonebyai