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...

When dealing with multiple CSV files having different columns, it’s essential to have an efficient method for querying and extracting relevant information. Azure OpenAI and LangChain provide a robust combination for handling such scenarios.  In this article, we’ll explore how to load multiple CSV files, process them, and ask questions across all of them. Let’s get started by installing the required packages. Install Required Packages Here are the ones which you need to install: ! pip install openai ! pip install langchain ! pip install pandas ! pip install langchain_experimental ! pip install langchain_openai ! pip install tabulate Import Required Packages Here are the packages which we need to import to get started: from langchain_openai import AzureOpenAI from langchain_experimental.agents import create_csv_agent Read Configuration First of all, we need to set few variables with information from Azure portal and Azure OpenAI Studio : api_type = "azure" api_base = ...

In this tutorial, we will dive into the fascinating world of Semantic Kernel and explore how to seamlessly integrate our custom functions into AI applications. Whether you’re a developer, data scientist, or just curious about the intersection of language models and native code, this tutorial is for you! 📌 Key Points Covered: Why Create Functions for Your AI?  Large language models excel at generating text, but there are tasks they can’t handle alone. I'll discuss scenarios where native functions shine, such as retrieving data from external sources, performing complex math, and interacting with the real world. Creating Your Native Functions: Set up a new folder for your plugins Dive into the creation of your own plugin to demonstrate the required operations Implement functions as required Running Your Native Functions: I'll also highlight, how  Semantic Kernel utilizes  KernelFunctions to invoke our custom functions. 🎥  Watch the Full Tutorial: Shweta Lodha 

Large Language Models (LLMs) are powerful AI systems that can understand and generate natural language. They have many applications in various domains, such as natural language processing, machine translation, and healthcare. However, building LLM-based applications is not a trivial task. It requires careful consideration of several factors, such as the choice of the LLM, the data quality, the evaluation metrics, and the ethical implications.  In this blog post, I will share some tips to solve most common problems. How to extract correct content from LLM Problem says that, although the answer is present in the content, but model fails to extract that.  Here are the quick tips to resolve this problem: Prompt compression Remove irrelevant data Rectify typos and grammatical errors Remove duplicate data Use data cleaning libraries Problem of missing top ranked documents Problem states that correct document was not rankled while ranking the documents. Here are the fe...

In my previous article “ Passing An Audio File To LLM ”, I explained how one can pass an audio file to LLM. In continuation to that, I’m extending this article by adding more value to it by addressing the use case of sensitive information. Let’s say, an audio file contains information about your bank account number, your secure id, your pin, your passcode, your date of birth, or any such information which has to be kept secured. You will find this kind of information if you are dealing with customer facing audio calls, specifically in finance sector. As these details, which are also known as PII (Personal Identifiable Information), are very sensitive and it is not at all safe to keep them only on any server. Hence, one should be very careful while dealing with such kind of data. Now, when it comes to using PII with generative AI based application, we need a way wherein we can just remove such information from data before passing that to LLM and that’s what this article is all about. In...

In this article, I’ll explain about how we can pass an audio file to LLM and I’m taking OpenAI as our LLM . There are many people who prefer audio and video tutorials over reading along with our podcast lovers as listening seems to be more effective for them as compared to reading a book, an e-book or an article, and it is quite common that after a certain period of time, we may forget some of the portions of our tutorial. Now, in order to get the insights again, re-watching or re-listening is the only option, which could be very time-consuming. So, the best solution is to come up with a small AI-based application by writing just a few lines of code which can analyze the audio and respond to all the questions that are asked by the user. Here, utilizing generative AI could be the best option, but the problem is, we can’t pass audio directly as it is text-based. Let’s deep dive into this article, to understand how we can make this work in a step-by-step fashion. If this is what that int...