Exploring artificial intelligence: deep learning project ideas
Artificial intelligence has been gaining enormous interest in recent times. The application of deep learning and AI models to real scenarios has opened up new horizons. To generate models for our applications, however, we need data on which to train these models. Let us explore some ideas that could enable us to create new applications and services.
ElasticSearch: how and when to use it
Textual search engines are a feature that plays an important role in the construction of applications. The user experience is greatly improved if the results requested are truly inherent to the words entered in the search bar. Elasticsearch allows us to integrate a full-text search system and obtain excellent results efficiently. Let us find out how and when it is possible to exploit these features.
Prompt engineering: prompting techniques [part 2]
The techniques proposed by prompt engineering allow even very complex tasks to be performed. Some of them, such as zero-shoot, few-shoot and Chain-of-Thought (CoT), manage to provide excellent results in some contexts. Where models have limitations, however, they can be remedied by even more advanced techniques such as Self-Consistency, Generated Knowledge and Tree of Thoughts.
Prompt engineering: prompting techniques [part 1]
Prompt engineering makes it possible to optimize the results obtained by acting only on what is provided to the LLMs. In recent years, several techniques have been proposed to appropriately structure prompts to solve even complex tasks without having to retrain the initial model. We will look at some simple techniques such as zero-shoot, few-shoot and Chain-of-Thought (CoT).
LLM: Prompt Examples
Creating prompts for LLM models, such as ChatGPT, can be considered a new art. From structuring prompts to using context, it is possible to improve the conversational experience and extract maximum value from interactions with LLMs. Through practical examples, we will see how to best structure prompts to generate engaging and meaningful conversations with AI based on the set task.
Prompt engineering
The advent of ChatGPT and LLM (Large Language Models) has revolutionized the world. Almost every industry has undergone a revolution and is adopting these powerful means of artificial intelligence to build new tools and services. But how do we build the prompts, i.e., the instructions, to make these models generate what we are interested in? Prompt engineering is the discipline that addresses this very issue. Let’s discover some tips for improving our prompts to artificial intelligence tools.
SQL: triggers in Oracle
Databases can play an active role in validating and implementing business rules. Through triggers it is possible, in fact. to define rules to ensure data integrity and automation of critical operations. We will analyze their definition and the different types of triggers, focusing our attention on what is provided in Oracle. Through some practical examples, we will understand how to validate data and implement business rules without having to leave these aspects to applications.
SQL: Recursive CTE
In some scenarios, there is a need to store hierarchies within the database, such as the corporate organizational chart or product categories of an e-commerce store. Although relational databases allow hierarchies to be modeled appropriately, querying them can be difficult and burdensome. Recursive CTEs were introduced to address these needs. We will study their syntax and application through an example, not before also evaluating other technological alternatives such as NoSQL databases.
SQL: correlation
In the SQL language, it is possible to condition the execution of a query on the values of the tuples being parsed. This behavior is defined by correlation, that is, conditions in the WHERE clause of a nested query that relate to attributes of the tables in the outer query. Through some examples we will discover which operators use this construct, how to appropriately define correlations, and its alternatives.
SQL: Common Table Expression
Expressing complex queries in SQL language can be really difficult. Dividing the problem into mini-queries is the best strategy to get the desired results quickly without running into errors. Common Table Expressions, also called CTEs, allow the queries of our interest to be defined once to be reused multiple times when needed. Their clean syntax increases the readability of SQL scripts, allows us to debug written code and to create very complex logic to filter and extract data. Through some examples we will discover their potential.
