π Azure machine learning service and its different models are explored.
π Vector search support in Azure cognitive search using Langchain framework is demonstrated.
π A notebook is used to convert data into vector embeddings and perform searches in Azure cognitive search.
π The video discusses the process of vector search in Azure Cognitive Search using Langchain.
π The model catalog allows users to access different models from various companies, view their details, and deploy them.
βοΈ The speaker focuses on using Azure open AI models, specifically the text embedding ada002 model for converting text into embeddings.
π Vector search is a new capability for indexing, storing, and retrieving vector embeddings from a search index.
π’ The vector search pattern, called retrieval augmented generation (RAG), can be used to prevent model hallucinations.
ποΈ Data from various sources, such as images, audio, video, and text, can be converted into vectors using an embedding model and stored in Azure cognitive search service.
π Vector search in Azure Cognitive Search can be performed using Langchain, allowing users to retrieve matching results.
π’ The search algorithm used in Azure Cognitive Search is K nearest neighbors, similar to Google search and YouTube search.
π‘ Azure Cognitive Search does not generate Vector embeddings by default, but this limitation can be overcome by integrating Azure open AI model and Langchain framework.
π The video discusses a factor search engine called Fast provided by Meta.
π‘ Hugging Face embeddings are used instead of Open AI for vector search in Azure Cognitive Search.
π¦ Python packages for search, Open AI, and Langchain are installed, and APIs like Open AI embeddings and Azure Search are used to push vectors into Azure Cognitive Search.
π Vector search in Azure Cognitive Search can be used to group cities based on their embeddings.
πΊοΈ Cities from different regions, such as India, Europe, and the US, can be grouped together using vector representation.
π To create vector search, an instance is created with search details, index, and embedding function, and the documents are split using Langchain APIs.
π Vector search in Azure Cognitive Search using Langchain.
𧩠Pushing chunks into the vector store and performing searches based on queries and keywords.
π Ability to retrieve results based on specific countries.