Published inMicrosoft Azure·Nov 16Member-onlyGetting started with Azure AI StudioOverview and first RAG Application — During the opening keynote of the Microsoft Ignite event, on November 15th, Artificial Intelligence was the undiscussed protagonist. Among the many AI-related announcements, a common flavor has emerged: the idea of making AI and, above all, GenAI more and more consumable and customizable by individuals and organizations. In this article…AI5 min readAI5 min read
Nov 12Member-onlyGetting started with Semantic KernelA gentle introduction with Python — In last months, we witnessed the extraordinary capabilities of Large Language Models (LLMs) like ChatGPT. However, the real paradigm shift occurred when we started embedding those LLMs within our applications. This implies the integration of a new set of LLMs-related components within our application logic, including memory, metaprompt, plug-ins and…Semantic Kernel10 min readSemantic Kernel10 min read
Published inMicrosoft Azure·Oct 22Member-onlyIntroducing AutoGenEnabling LLM-powered agents to cooperate — In my latest article, we’ve introduced the concept of Agents as a type of LLM application that are powered with a set of external tools or plug-ins that allow them to “do stuff”. In ther words, agents can be seen as AI systems that, given a user’s query, are able…Autogen11 min readAutogen11 min read
Published inMicrosoft Azure·Sep 8Member-onlyGenerating applications from sketches with LLMsAn implementation with LangChain and GPT-3.5-turbo — In last months, we’ve witnessed the great capabilities of LLMs in the context of code understanding and generation. …OpenAI7 min readOpenAI7 min read
Published inMicrosoft Azure·Aug 23Member-onlyEnhancing Recommendation Systems with Large Language ModelsAn implementation with LangChain and Azure OpenAI — Large Language Models have shown incredible capabilities in the field of Generative AI, and the potential to unlock new applications in many industries. An interesting analysis that have also emerged in last months is how LLMs can enhance or even substitute current technological approaches that we use to solve specific…Large Language Models13 min readLarge Language Models13 min read
Published inMicrosoft Azure·Jul 10Member-onlyDeploy and Orchestrate Large Foundation Models with Azure AI StudioOverview of new features of Azure AI | Machine Learning Studio — A few weeks ago at Build 2023, Microsoft announced a re-branding of the Azure service called Azure Machine Learning (AML), the workspace where data scientist could train, test, deploy and orchestrate with powerful MLOps tools their ML projects lifecycle (you can read more about AML here). The former AML is…Azureopenai5 min readAzureopenai5 min read
Published inMicrosoft Azure·Jun 21Member-onlyChat with your own data with Azure OpenAIDeploy a ChatGPT web app in minutes — On May 23rd, a stunning announcement was released, stating that new feature would have been added to the Playground soon, so that users could directly upload and chat with their own document, without worrying about the backend embedding and documents’ pre-processing. Well, the day has finally come. In this article…ChatGPT6 min readChatGPT6 min read
Published inMicrosoft Azure·Jun 9Member-onlyIntroducing LangChain toolkits for Azure Cognitive ServicesBuilding a multimodal application powered by GPT — In my previous article, I introduced LangChain agents as applications powered by LLMs and integrated with a set of tools like search engines, databases, websites, and so on. …Azure Cognitive Service6 min readAzure Cognitive Service6 min read
Published inMicrosoft Azure·Jun 8Member-onlyIntroducing LangFlow: a GUI for LangChainEmbed LLMs into your applications with no code — LangChain is a Python library that makes it easier to combine the power of LLMs with the logic of an application. LangChain allows users to create and compose modular components, such as prompt serializers, agents, and chains, to achieve various natural language tasks. However, designing and testing LangChain flows can…Langchain5 min readLangchain5 min read
Published inMicrosoft Azure·May 14Member-onlyIntroducing LangChain AgentsAn implementation with Azure OpenAI and Python — Large Language Models (LLMs) like GPT-3.5-turbo (the model behind ChatGPT) and GPT-4 have been proving their generative power in last few months. However, as they are today they suffer from a limitation: they are limited to the knowledge on which they have been trained and the additional knowledge provided as…Langchain8 min readLangchain8 min read
