🗝 TLDR: This tutorial shows how to build AI agents that orchestrate multiple knowledge sources (SQL databases, vector database search, web search) to answer complex healthcare queries. We use Azure SQL, Azure AI Search, and Bing Grounding Tool via A...
💡 👉 Full Cookbook here: https://github.com/farzad528/azure-ai-search-python-playground/blob/main/azure-ai-search-perplexity-contextualized-embeddings.ipynb Perplexity just launched new SOTA embedd
🗝 TL;DR: - For AI Engineers looking to build AI Agents, this blog explores the Agentic RAG Router. It demonstrates how to leverage OpenAI Function Calling for intelligent routing of user queries to different tools, specifically Azure AI Search for p...
In today's AI landscape, building reliable knowledge systems requires more than just powerful language models. Enter Retrieval-Augmented Generation (RAG) – a pattern that enhances AI responses with contextual knowledge. In this guide, we'll build a p...
💡 DISLCAIMER: This post is intended for educational purposes only. I do not claim to be an Insurance or Underwriter professional or expert. The information shared is based on a personal project and experiences with Azure OpenAI and Semantic Kernel. ...
💡 DISCLAIMER: The content below is intended for educational purposes. Actual performance and outcomes will depend on your dataset, indexing strategies, and the task you’re trying to solve with your RAG pipeline. Experimentation is strongly recommend...
💡 DISCLAIMER: This post is intended for educational purposes only. Actual results may vary depending on your dataset, environment, and configurations. Retrieval Augmented Generation (RAG) solutions combine Large Language Models (LLMs) with externa...
💡 DISLCAIMER: This post is intended for educational purposes only. I do not claim to be an HR professional or expert. The information shared is based on a personal project and experiences with Azure OpenAI and Semantic Kernel. According to Sparkwi...
Voyage AI recently announced a major breakthrough in multimodal embeddings with the release of voyage-multimodal-3. This state-of-the-art model captures both textual and visual features in a unified vector space, enabling seamless retrieval augmented...
