My dear friends, AI is everywhere, in our cities, in our countryside, and it is stealing the jobs of people who oppose it.

So instead of pointlessly fighting the inevitable, you can better tame it and make it work for you, because it’s just another stupid tool that everyone can benefit from.

Even programmers… The proof with EvaDB, an open database that allows software developers to do this Build AI applications in just a few lines of code thanks to him Very powerful SQL API. And you don’t need any special AI knowledge to use it!

EvaDB presents itself as a turnkey solution to simplify the development of AI applications, supporting both structured and unstructured data management. The tool offers a easy connection to all existing data sources such as PostgreSQL or your S3 buckets, as well as a optimized CPU/GPU utilization and personalization of AI models (fine-tuning) collected by Hugging Face, OpenAI and YOLO.

In concrete terms, this means that you can add AI functionality to your applications simply by using functions built into queries. You can choose from various pre-trained models or create your own custom models.

Small example of a query:

SELECT name, country, email, programming_languages, social_media, GPT4(prompt,topics_of_interest)
FROM gpt4all_StargazerInsights;

And the prompt was:

--- Prompt to GPT-4
You are given 10 rows of input, each row is separated by two new line characters.
Categorize the topics listed in each row into one or more of the following 3 technical areas - Machine Learning, Databases, and Web development. If the topics listed are not related to any of these 3 areas, output a single N/A. Do not miss any input row. Do not add any additional text or numbers to your output.
The output rows must be separated by two new line characters. Each input row must generate exactly one output row. For example, the input row [Recommendation systems, Deep neural networks, Postgres] must generate only the output row [Machine Learning, Databases].
The input row [enterpreneurship, startups, venture capital] must generate the output row N/A.

Here are some possible use cases: Sentiment analysis, Answering questions asked via video with ChatGPT, Text summary from PDF documents, Traffic flow analysis, Analyzing emotions in videos or Search for similar images.

Thus, with EvaDB it is possible to address 99% of common AI problems and can be automated with a simple function call in an SQL query.

Obtaining a transcription of a video stored in a spreadsheet using a speech recognition model and then being able to ask questions about the extracted transcription using ChatGPT is typically the sort of thing EvaDB allows you to do:

CREATE TABLE text_summary AS
    SELECT SpeechRecognizer(audio) FROM ukraine_video;
SELECT ChatGPT('Is this video summary related to Ukraine russia war', text)
    FROM text_summary;

If your curiosity is piqued and you would like to find out more about this project, Everything is here on Github.

In short: don’t miss the opportunity to get to know this open source tool that will open many doors for you.