Early Adopter Release of Kodit: MCP server to index external repositories
Kodit lets AI coding assistants see your private or newest repos—no retraining required.
Dr. Phil Winder
/
5 minArticles in this topic
Page 1 of 3
Dr. Phil Winder
/
5 min
Intro to Vision RAG: Smarter Retrieval for Visual Content in PDFs
A debrief on the state of the art of integrating vision models into RAG pipelines for visual semantic search.
Dr. Phil Winder
/
4 min
User Feedback in LLM-Powered Applications
A guide to gathering user feedback in LLM applications, reviewing the state of the art, and some practical tips.
Dr. Phil Winder
/
5 min
Scaling GenAI to Production: Strategies for Enterprise-Grade AI Deployment
Transition your GenAI prototypes to enterprise-grade production with scalable strategies, robust monitoring, cost management, and secure governance best practices.
Natalia Kuzminykh
/
8 min
Enterprise AI Assistants: Combatting Fragmentation
Data silos are a cause of fragmentation in the enterprise. But what if we could use AI Assistants to connect them?
Dr. Phil Winder
/
12 min
Large Language Model Fine-Tuning via Context Stacking
Discover how context stacking revolutionises LLM fine-tuning with minimal data for faster AI deployment.
AI in 2024: A Year in Review
A look back at the year in AI, and a look forward to what's coming in 2025.
Dr. Phil Winder
/
5 min
Best LLMOps Tools: Comparison of Open-Source LLM Production Frameworks
Explore LLM agent and orchestration frameworks, LLMOps tools, and platforms for deploying language models effectively.
Natalia Kuzminykh
/
17 min
A Comparison of Open Source LLM Frameworks for Pipelining
Optimize your LLM projects with the best open source LLM frameworks, Python libraries, and orchestration tools.
Natalia Kuzminykh
/
27 min
Testing and Evaluating Large Language Models in AI Applications
A guide to evaluating and testing large language models. Learn how to test your system prompts and evaluate your AI's performance.
Dr. Phil Winder
/
17 minNewsletter
AI engineering insights, in your inbox
Case studies and industry analysis from our team. No hype, about once every three months.