Yigit Konur articles - 22 total
Using Mermaid Diagrams 100x Better with Your Favorite AI / LLM App
I use Mermaid diagrams constantly in my daily workflow. But honestly, most AI apps tend to mess them...
24 Thinking Models Can Be Used For Problem Solving (both for humans and AI agents)
I made a research about this thinking methods to change the way my AI Agents thinking but it can be...
Vercel AI SDK v5 Internals - Part 10 — Advanced Optimization: Throttling, Virtualization, Resumption, & Scaling
We've been through a whirlwind tour of the Vercel AI SDK v5 Canary in the previous nine posts,...
Vercel AI SDK v5 Internals - Part 9 — Persisting Rich `UIMessage` Histories: The v5 'Persist Once, Render Anywhere' Model
Let's talk persistence. If you've been following along with the Vercel AI SDK v5 canary journey, you...
Vercel AI SDK v5 Internals - Part 8 — Server & Client Tool Execution Deep Dive
We've been exploring the Vercel AI SDK v5 canary in this series, and today we're tackling a big one:...
Vercel AI SDK v5 Internals - Part 7 — Decoupling Your Backend: The ChatTransport Abstraction Explained
We've been journeying through the Vercel AI SDK v5 canary in this blog series, and if you've been...
Vercel AI SDK v5 Internals - Part 6 — One Store, Many Hooks: Unified Chat State Across Frameworks
Been playing around with the Vercel AI SDK v5 canary bits for a while now, especially how it handles...
Vercel AI SDK v5 Internals - Part 5 — Powering Generative UI with SSE Backbone
Been neck-deep in the Vercel AI SDK v5 canary builds for a bit now, and it’s high time we talked...
Vercel AI SDK v5 Internals - Part 4 — Decoupling Client & Server: State Management and Message Conversion
This is the fourth post in our series diving into AI SDK 5. We've previously covered the UIMessage...
Vercel AI SDK v5 Internals - Part 3 — The V2 Model Interface Contract: Type-Safety Meets Rich Capabilities
In the previous posts, we got a good look at the new UIMessage / UIMessagePart structure (the...
Vercel AI SDK v5 Internals - Part 2 — Streaming the Richness: Inside the UI Message Protocol & UIMessageStreamParts
After our first look into the Vercel AI SDK v5 and its new UIMessage structure, it's time to pull...
Vercel AI SDK v5 Internals - Part 1 — UIMessage Parts, ChatStore Sync, and Pluggable ChatTransport
Been diving deep into the Vercel AI SDK v5 canary releases lately, and wow, there are some...
How to build a scalable crawler with Prefect v3 (PokeAPI Example)
This blog post serves as an in-depth tutorial for integrating a new data source crawler—specifically...
Sentry for TS Developers: Practical Tips for Error Tracking & Performance Tuning
If you're a TypeScript developer building applications, you know how quickly complexity can grow....
Stop Fighting Your AI: 20+ Advanced Cursor / Windsurf Tricks for Vibe Coding in A way Harder, Better, Faster and Stronger
Cursor AI or Windsurf, maybe Cline? They promises a coding utopia – blasting through features,...
Ultimate Guide to Supercharging LLM JSON Outputs with Precision Schema Descriptions
You're harnessing the power of OpenAI's Large Language Models (LLMs) to generate structured JSON...
Mem0: The Comprehensive Guide to Building AI with Persistent Memory
Welcome to your complete guide (easy to copy gist for llm context) to Mem0, the intelligent memory...
Comprehensive Guide to PromptL and the Its Python Library (promptl-py)
Working with LLMs is powerful, but crafting and managing the prompts that drive them can quickly...
Building LiteLLM Plugins with `async_pre_call_hook` for Proxy Mode
You're using the LiteLLM Proxy, appreciating its ability to unify access to various Large Language...
Everything You Need to Know About LiteLLM Python SDK
This guide provides a comprehensive deep-dive into the LiteLLM Python SDK, designed to help you...
The Ultimate Guide to LiteLLM Callbacks: From Zero to Hero for Beginners
You're using LiteLLM to effortlessly manage calls to various Large Language Models (LLMs) like GPT-4,...
Comprehensive LiteLLM Configuration Guide (config.yaml with all options included)
LiteLLM is most feature-rich proxy but when it comes to write great docs, they are failing a lot!...