Hacker News
- Boosting Vector Search Speed by 40% with AVX512 on Emerald Rapids https://weaviate.io/blog/intel 3 comments
- How to Reduce Memory Requirements with Product Quantization https://weaviate.io/blog/pq-rescoring 5 comments
- What Is a Vector Database? https://weaviate.io/blog/what-is-a-vector-database 2 comments
- Use relative score fusion to combine and rank vector and keyword search results https://weaviate.io/blog/hybrid-search-fusion-algorithms 2 comments
- A Deep Dive into Weaviate's Fusion Algorithms for Hybrid Search https://weaviate.io/blog/hybrid-search-fusion-algorithms 6 comments
- Weaviate – Open-Source AI Native Vector Database https://weaviate.io/ 4 comments
- Generative Search Module for Weaviate https://weaviate.io/developers/weaviate/modules/reader-generator-modules/generative-openai 3 comments
- Vector search engine ANN benchmarks https://weaviate.io/developers/weaviate/current/benchmarks/ann.html 2 comments
- Try Google's newly announced PaLM API with Weaviate https://weaviate.io/blog/announcing-palm-modules 2 comments googlecloud
- Generative Feedback Loops with LLMs for Vector Databases https://weaviate.io/blog/generative-feedback-loops-with-llms 5 comments datascience
- Vamana vs HNSW - Exploring ANN algorithms Part 1 https://weaviate.io/blog/2022/10/ANN-algorithms-Vamana-vs-HNSW.html 2 comments database
- What are Distance Metrics in Vector Search? https://weaviate.io/blog/2022/09/Distance-Metrics-in-Vector-Search.html 6 comments datascience
- Why is Vector Search so fast? https://weaviate.io/blog/2022/09/Why-is-Vector-Search-so-fast.html 3 comments database
- GOMEMLIMIT (Go 1.19) is a game-changer for high-memory applications https://weaviate.io/blog/2022/08/GOMEMLIMIT-a-Game-Changer-for-High-Memory-Applications.html 44 comments golang
Linking pages
- GitHub - awesome-selfhosted/awesome-selfhosted: A list of Free Software network services and web applications which can be hosted on your own servers https://github.com/Kickball/awesome-selfhosted/blob/master/README.md 1155 comments
- GitHub - btw-so/open-source-alternatives: List of open-source alternatives to everyday SaaS products. https://github.com/btw-so/open-source-alternatives 122 comments
- Emerging Architectures for LLM Applications | Andreessen Horowitz https://a16z.com/2023/06/20/emerging-architectures-for-llm-applications/ 95 comments
- GitHub - weaviate/healthsearch-demo: Discover Healthsearch: Unlocking Health with Semantic Search ✨ https://github.com/weaviate/healthsearch-demo 26 comments
- GitHub - langchain4j/langchain4j: Java version of LangChain https://github.com/langchain4j/langchain4j 16 comments
- The Best Vector Database for Stablecog's Semantic Search | Blog https://stablecog.com/blog/the-best-vector-database-for-stablecogs-semantic-search 5 comments
- Retrieval Augmented Generation (RAG): What, Why and How? | LLMStack https://llmstack.ai/blog/retrieval-augmented-generation 4 comments
- Understanding The Role of Vector DB in AI Application https://thebeep.substack.com/p/understanding-the-role-of-vector 4 comments
- GitHub - yoheinakajima/babyagi https://github.com/yoheinakajima/babyagi 3 comments
- The AI-First Database Ecosystem https://www.forbes.com/sites/forbestechcouncil/2022/06/23/the-ai-first-database-ecosystem/ 2 comments
- Pinecone - Cost Optimization & Performance Best Practices https://nextword.dev/blog/pinecone-cost-best-practices 2 comments
- Adding Intelligent Search to a Rails application with Weaviate | by Andrei Bondarev | Apr, 2023 | Medium https://medium.com/@rushing_andrei/adding-intelligent-search-to-a-rails-application-56d3ed794b8a 2 comments
- A Gentle Introduction to Vector Databases | Weaviate - vector database https://weaviate.io/blog/what-is-a-vector-database 2 comments
- GitHub - srush/MiniChain: A tiny library for coding with large language models. https://github.com/srush/MiniChain 1 comment
- What is new with search? … we are re-inventing it with vector embeddings! | by Karolina Kukielka | Apr, 2023 | Medium https://karolina.medium.com/what-is-new-with-search-we-are-re-inventing-it-with-vector-embeddings-fa8219a994ef 1 comment
- We Just Launched a Tom’s Hardware AI Chatbot. Here's Why. | Tom's Hardware https://www.tomshardware.com/news/tomshardware-ai-chatbot 1 comment
- GitHub - FeatureBaseDB/DoctorGPT: 💻📚💡 DoctorGPT provides advanced LLM prompting for PDFs and webpages. https://github.com/FeatureBaseDB/DoctorGPT 1 comment
- GitHub - yujiosaka/ChatIQ: ChatIQ is a versatile Slack bot using GPT & Weaviate-powered long-term memory to accomplish various tasks. https://github.com/yujiosaka/ChatIQ 1 comment
- Vector databases (1): What makes each one different? | The Data Quarry https://thedataquarry.com/posts/vector-db-1/ 1 comment
- Aman's AI Journal • Primers • Overview of Large Language Models https://aman.ai/primers/ai/LLM/ 1 comment