Artificial intelligence (AI)

On this page I have collected some information which seems to me interesting related to Artificial Intelligenc (AI) and Machine Learning (ML).

Tutorials

• Build a Simple LLM Application with LCEL

How-to’s

• How to create and query vector stores
• How-to guides
• Text embedding models
• Quick and Simple: Setting Up Your First Local LLM Project
• Build a basic LLM chat app
• Adam Hendel, Tembo, 2024-09-24: Building an image search engine on Postgres
• Taylor Grenawalt, Vation, 2023-07-05: Vector Databases 101: What are Vector Databases?
• Pavan Belagatti, 2023-08-25: Vector Databases: A Beginner’s Guide!

Code and Examples / GitHub

• snwfdhmp / llm
• LLM Plugin directory
• Python API
• ventz / easy-llms
• karpathy / llm.c
• karpathy / nanoGPT

News

• Davis David, 2020-06-04: 15 Undiscovered & Open Source Machine Learning Frameworks You Need to Know in 2020
• Ulrich Bantle, Linux Magazin, 2020-06-16: Abbyy veröffentlicht NeoML als Open Source
• Stefanie Stoppel (Machine Learning Engineer), Inovex, 2023-11-22: file://~/fromdual/technology/ai_mi/Myth of Neutrality - KI Navigator 22.11.23.pdf" target="_blank">The Myth of Neutrality - How AI is widening social divides

Vector databases

Vector database on Wikipedia

• MariaDB Vector
• Pinecone

MariaDB Vector

Vector: List of floating point numbers typical length: 20 - 2000 numbers

• Sergei Golubchik, MariaDB Foundation, MariaDB ServerFest 2024-09, Berlin: MariaDB Vector, a new Open Source vector database that you are already familiar
• Kaj Arnö, MariaDB Foundation: 2024-05-10: MariaDB is soon a vector database, too
• Kaj Arnö, MariaDB Foundation, 2024-07-29: Finally here: MariaDB Vector Preview!
• Sergei Golubchik, MariaDB plc, 2024-07-31: MariaDB Vector preview is out]
• Sergey Pronin, Percona, 2024-08-05: Open Source AI Database Agent Part 1: Introduction Keywords: generative AI, database agent
• Sergey Pronin, Percona, 2024-08-07: Open Source AI Database Agent Part 2: OSADA]
• Andrew Hutchings, MariaDB Foundation, 2024-08-30: Intel improving the performance of MariaDB Vector
• MariaDB Foundation: Creating the MariaDB Binary Tarball
• MariaDB Foundation: MariaDB Vector
• MariaDB Foundation: <a href=“https://mariadb.org/download/?t=mariadb&p=mariadb&r=11.6.0+Vector&os=source"" target="_blank”>Download MariaDB Server
• MariaDB Foundation on YouTube: MariaDB Vector - First Demo, MariaDB Server Fest Brussels
• MariaDB Vector - Project page
• MariaDB Vectors - Documentation
• Thorsten Honroth, Dr. Julien Siebert, Patricia Kelbert, Fraunhofer IESE, 2024-01-19: Open Source Large Language Models selbst betreiben
• Integrating Vector Databases with LLMs: A Hands-On Guide
• LLM Model Enhanced with Vector DB
• Building LLM Applications: Vector Database (Part 4)
• Understanding Vector Indexing: A Comprehensive Guide
• The Technical User’s Introduction to LLM Tokenization
• From prototype to production: Vector databases in generative AI applications
• Perl::Tokenizer - A tiny Perl code tokenizer
• https://www.iese.fraunhofer.de/blog/large-language-models-ki-sprachmodelle/
• https://huggingface.co/blog/2023-in-llms
• https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard
• https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard
• https://huggingface.co/spaces/mike-ravkine/can-ai-code-results
• https://huggingface.co/spaces/bigcode/bigcode-models-leaderboard
• https://huggingface.co/openchat/openchat-3.5-0106
• https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0
• https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
• https://developer.nvidia.com/blog/easy-introduction-cuda-c-and-c/
• https://en.wikipedia.org/wiki/CUDA
• https://pytorch.org/tutorials/beginner/pytorch_with_examples.html
• https://medium.com/@xriteshsharmax/quick-and-simple-setting-up-your-first-local-llm-project-c08bde3bb921
• https://github.com/ventz/easy-llms
• https://github.com/simonw/llm
• https://github.com/snwfdhmp/llm
• https://docs.mistral.ai/guides/tokenization/
• https://medium.com/@punya8147_26846/tokenizer-in-llm-060b1a35694b
• https://github.com/milahu/awesome-transpilers
• VERT: Verified Equivalent Rust Transpilation with Large Language Models as Few-Shot Learners
• Verified Code Transpilation with LLMs
• https://medium.com/@igniobydigitate/vector-databases-your-ais-secret-supercharge-129d7314545f
• https://medium.com/@igniobydigitate/word-embeddings-helping-computers-understand-language-semantics-dd3456b1f700
• https://milvus.io/docs/v2.0.x/overview.md
• DNA
• https://www.addgene.org/vector-database/6362/
• https://www.neb.com/en/tools-and-resources/interactive-tools/dna-sequences-and-maps-tool
• https://medium.com/accredian/leveraging-lstm-and-llm-models-for-stock-price-prediction-79bf15d681ec
• https://thegradient.pub/financial-market-applications-of-llms/
• https://lakefs.io/blog/what-is-vector-databases/
• https://lakefs.io/blog/what-is-vector-databases/
• https://www.techtarget.com/searchdatamanagement/tip/Top-industry-use-cases-for-vector-databases
• https://research.aimultiple.com/vector-database-use-cases/
• https://www.v7labs.com/blog/vector-databases
• https://www.contentful.com/blog/what-are-vector-databases/
• https://www.geeksforgeeks.org/vgg-16-cnn-model/
• https://huggingface.co/docs/transformers/en/model_doc/bert
• https://docs.llamaindex.ai/en/stable/examples/low_level/ingestion/#build-an-ingestion-pipeline-from-scratch
• Robert Silén, MariaDB Foundation, 2024-11-28: Try RAG with MariaDB Vector on your own MariaDB data!

Hierarchical Navigable Small Worlds (HNSW)

• https://en.wikipedia.org/wiki/Hierarchical_navigable_small_world
• https://towardsdatascience.com/similarity-search-part-4-hierarchical-navigable-small-world-hnsw-2aad4fe87d37
• https://www.pinecone.io/learn/series/faiss/hnsw/
• https://arxiv.org/abs/1603.09320

Vector database use cases

• Natural language processing (NLP)
  • Customer support
  • Perl to Python converter on premises for banking (transpiler)
• Improving machine learning models
• Clustering and classification
• Graph analytics
• Search engines
  • Document search
  • Better fulltext search (see genomics)
• Image and video recognition
  • Music and multimedia streaming services
  • Video games
  • Biometrics
  • Autonomous vehicles
• Recommendation Systems
  • Media recommendations
  • E-commerce product recommendations and Personalization
  • Personalized advertising
  • Similarity matching
  • Human Resources Matching / Dating platforms
• Healthcare, Medical diagnostics
  • Drug Discovery
  • Genomics
  • Genome search
  • DNA Sequence Classification https://milvus.io/blog/dna-sequence-classification-based-on-milvus.md https://www.kaggle.com/datasets/nageshsingh/dna-sequence-dataset
  • Patient Similarity Analysis
• Financial services
  • Fraud detection
  • Trend predictions / Market price forecast
  • Anomaly Detection
• It Security
  • Log File Monitoring
• GIS, Spatial data

Other ideas

• GPU from Bitcoin Miner