• 👉 LLMs: Beyond Chat : Using Pydantic and Instructor with OpenAI GPT-4o to use the LLM as a software device for implementing different tasks. #tutorial #python #jupyter #openais #pydantic #instructor #video

• LLMs: Beyond Chat - Javascript/Typescript : Port of 'LLMs: Beyond Chat' to JS/TS with the excellent Vercel AI SDK #sample #javascript #typescript #vercel-ai-sdk
• Two Programming-with-AI Approaches : Dialog Programming vs Bossing AI Agents. #article #programming
• Building Effective Agents with Pydantic AI : Code examples for Building Effective Agents ported and adapted to use Pydantic AI. #agents #python #jupyter #pydantic #pydantic-ai
• Don't Wait! : Independent LLM calls are parallelisable. #article
• MkFlascards : Automagically create flashcards for spaced-repetition from a piece of text. #article #app #huggingface #openai #pydantic #gradio
• Battle of the Semantics: GraphRag vs Embeddings Index : Comparing RAG over a rich and complex text using GraphRag vs traditional embeddings index. #sample #python #openai #grounding #graphrag #video
• 1% More Intelligent : AI doesn't need to transform every aspect of our software to be transformative. #article #sample #python #openai #pydantic #instructor
• The Narrowing Path : A very brief introduction to language and models and prompting. #article
• Text Clustering: Embedding vs Prompting : Using an LLM to summarise and cluster articles (works better than embeddings and traditional ML clustering). #sample #python #jupyter #openai
• Rastastream : Streaming AI responses with .NET. #sample #dotnet #csharp #azure #openai
• Should You Care about Open LLMs? : For most users of AI or developers using AI to build, "open-source" large language models are not very interesting. #article
• GPT Todo List : Take a ToDoList class and chain it to GPT-3.5 by passing the methods for interacting with the list as LangChain tools or OpenAI function calls. #sample #python #openai #langchain
• Azure Open AI Proxy : Multiplex between multiple Open AI clients and Azure Open AI deployments + track and attribute the cost of the requests per user and/or endpoint. #sample #python #azure #openai
• Grounding LLMs : Everything I learned (so far) about grounding LLMs with retrieval augmented generation to generate output that this accurate and relevant. #article
• Nobody Expects the Chatty Inquisition : We know that we can ask GPT questions. But how about it asking us? In this example GPT-3.5-turbo is working for us as a waiter in a restaurant. #sample #python #openai