Published in Microsoft Azure·4 days agoMember-onlyAzure OpenAI and LangChainA brief introduction — In last weeks, many of us have been experimenting with the powerful Azure OpenAI APIs, either in the playground or via REST API or Python SDK. However, those APIs alone are not sufficient to build powerful applications. We can summarize in three main categories the kind of results we want…Langchain4 min readLangchain4 min read
Published in Microsoft Azure·Mar 5Member-onlyCustom ChatGPT with Azure OpenAIAn implementation with Python and Streamlit-Chat — ChatGPT was one of the most stunning developments of OpenAI. Since its release to the general public in November 2022, it has been used for so many use cases. However, we are talking about a web preview that cannot be customized both in the backend and front end. That is…Chatgpt4 min readChatgpt4 min read
Published in Microsoft Azure·Feb 13Member-onlyQuerying structured data with Azure OpenAIAn implementation with Python — Imagine you have a lot of structured data and you want to extract relevant information from them. You might also want to generate some simulations, asking for specific KPIs but also generating reports about the main relevances caught in data. In fact, with so much structured data, you might also…Azureopenai6 min readAzureopenai6 min read
Published in Microsoft Azure·Jan 27Member-onlyModel interpretability with Azure OpenAIFrom code to natural language — Model interpretability refers to the ease with which a human can understand the reasoning behind the predictions made by a machine learning model. It is the ability to understand how a model is making decisions and what factors are contributing to its predictions. There are many reasons why model interpretability…OpenAI9 min readOpenAI9 min read
Published in Microsoft Azure·Jan 18Member-onlyAzure OpenAI PlaygroundOverview of language models and hyperparameters — OpenAI and its disruptive development of generative models are probably the most trending topic in the Tech industry today. With good reason. The company indeed aims to promote and develop friendly AI in a way that benefits humanity as a whole. OpenAI also provides a platform for training and deploying…OpenAI7 min readOpenAI7 min read
Published in Microsoft Azure·Jan 3Member-onlyAzure Cognitive Service for LanguagePart 1: Pre-built features — Azure Cognitive Services is a collection of cloud-based APIs that allow developers to add intelligent features to their applications. Azure Cognitive Service for Language is a subset of those APIs that enable you to process natural language input and understand the structure of the language, as well as analyze sentiment…Azure Cognitive Service8 min readAzure Cognitive Service8 min read
Published in Towards Data Science·Dec 19, 2022Member-onlyNatural Language Process for Judicial Sentences with PythonPart 10: Predictions — We got to the final Part of this series of articles, where I will use ML models to classify Judicial Sentences into categories. For this purpose, I will perform a supervised learning task using as a training set the already-labeled records, in order to apply the models to those records…Natural Language Process10 min readNatural Language Process10 min read
Published in Towards Data Science·Dec 16, 2022Member-onlyNatural Language Process for Judicial Sentences with PythonPart 9: Unsupervised Sentiment Analysis — Sentiment analysis is a natural language processing technique that involves using machine learning algorithms to identify and extract subjective information from text data. It is commonly used to determine the overall sentiment of a piece of writing, whether it is positive, negative, or neutral. This can be useful for a…Natural Language Process7 min readNatural Language Process7 min read
Published in Towards Data Science·Dec 13, 2022Member-onlyNatural Language Process for Judicial Sentences with PythonPart 8: Named Entities and Network representation — As we saw in previous articles, NLP deals with a vast amount of text data containing a huge amount of information. We saw many techniques to reduce complexity and extract relevant information from data, from the simplest tokenization/lemmatization/stemming to TF-IDF analysis and Words/Docs embedding. Another important aspect of analyzing these…Natural Language Process6 min readNatural Language Process6 min read
Published in Towards Data Science·Dec 5, 2022Member-onlyNatural Language Process for Judicial Sentences with PythonPart 7: Cluster analysis — In this article, I’m going through some further analysis and visual representation of our Judicial sentences. I will focus on clustering analysis, an unsupervised learning technique that is very useful to find patterns in data even if we do not know much about it. …Natural Language Process6 min readNatural Language Process6 min read
