1 min read
Semantic Kernel Filters: Intercepting and Modifying AI Operations
Semantic Kernel supports several filter types: function invocation filters, prompt render filters, and auto function invocation filters. Each intercepts…
AI Architecture
4 articles
1 min read
RAG Chunking Strategies: Finding the Optimal Approach
The simplest approach splits text at regular intervals with optional overlap. Semantic chunking respects content boundaries like paragraphs and sections.
1 min read
When to Use o1: A Decision Guide for AI Applications
o1 shines in specific scenarios. Understanding these helps you deploy it effectively.
2 min read
LLM Routing: Intelligent Model Selection for Cost and Quality
" in query or self. has code indicators(query lower): return ModelTier.STANDARD Long queries often need more capability if word count 200: return…