Don't worry. Not everyone knows it...

In this article we will see how we can run our agents locally which means we will be using OpenAI Swarm framework but still we will not be paying anything to OpenAI as we will not be utilizing OpenAI's API key. Using OpenAI's Swarm but not using OpenAI's key, got confused?  Well, we will be achieving this using Ollama :) Now, before we proceed, if you have not watched my earlier video on what is OpenAI-Swarm and how to get started with it, I would recommend you check this one here:  Here is link of the GitHub repository containing Swarm's source code and implementation details. What Are We Trying To Do? We will create our own agent utilizing  OpenAI-Swarm framework using Ollama and the open-source model Llama3.2:1b . This agent will run locally on our machine without the need to any API key from OpenAI . Setting Up The Things Install Swarm We need to install Swarm from GitHub as it is still in experimental stage and that can be done by running below command: pip...

In the ever-evolving landscape of data management, the ability to generate SQL queries without a predefined schema can significantly enhance flexibility and efficiency. Leveraging the power of GPT-3.5 Turbo , we can achieve this by fine-tuning the model to understand and generate schema-free SQL queries.  Why Schema-Free SQL Queries? Traditional SQL queries rely on a predefined schema, which can be limiting in case of huge number of tables or columns. Here are the few benefits of using schema-free approach: Efficiency: By not requiring schema definitions in every prompt, you save on prompt size and reduce the complexity of your queries, making the process faster and more efficient. User-Friendly: It simplifies the querying process for users who may not be familiar with the database schema, enabling them to retrieve data using natural language descriptions. Adaptability: GPT models can adapt to various database structures and types, making them versatile tools for querying differen...

In the ever-evolving landscape of data management and artificial intelligence, the ability to generate SQL queries using natural language inputs is a game-changer. Azure OpenAI , with its powerful language models, offers a seamless way to translate natural language into SQL queries, making data interaction more intuitive and accessible. This article will guide you through the process of leveraging Azure OpenAI to generate SQL queries, enhancing your data querying capabilities. Introduction Azure OpenAI Service provides access to OpenAI’s powerful language models through the Azure platform. These models are capable of understanding and generating human-like text, making them ideal for tasks such as natural language processing, text generation, and, importantly, translating natural language into SQL queries. Setting Up Azure OpenAI and Azure SQL DB Before you can start generating SQL queries, you need to set up your Azure OpenAI environment. Here are the steps. Create an Azure Account...

In today’s data-driven era, where we are dealing with massive data pertaining to different data sources having different data formats, it creates a very big challenge, especially in terms of efficient search and information retrieval. Dive into this deep ocean and locating the correct data is not at all an easy task with AI. In this article, I’ll show you how you can integrate Azure SQL Database, FAISS , and advanced models from Hugging Face to enhance your search capabilities. Let’s take a quick look at each of these pillars. Understanding Terminology Azure SQL Database Azure SQL Database i s a cloud-based service that provides a totally managed database system. The high availability, scalability, and security of this particular service type make it the best option for handling large amounts of data. FAISS FAISS is short for Facebook AI Similarity Search. It is a library written by Facebook AI Research that enables efficient similarity search and clustering of dense vectors. It suppor...