Text chunking is crucial when working with vector embedding models, no matter where you host them. In my previous article, Vector Embedding for Long Documents, I explored how to combine multiple vectors into one. In this post, Read more
This blog article discusses a method for creating vector embeddings for texts longer than the input limit for a selected embedding model.
In this comprehensive guide, we delve into the powerful capabilities of Azure Cosmos DB as a vector database and demonstrate how to leverage Azure AI Foundry’s large language models (LLMs) to generate vector embeddings for advanced text search and analysis. Discover step-by-step instructions on setting up vector search, integrating LLMs, and optimizing your database for high-performance similarity queries. Explore practical use cases, best practices, and tips for making the most of these cutting-edge technologies in your applications.
