AI Consultant | Machine Learning Solutions | Expert Developers

不积跬步，无以至千里
不积小流，无以成江海

Great journeys begin with small steps;
mighty rivers grow from little streams.

60-second pitch formula

Original post in Linkedin by Yurii Rebryk. I re-post and document in my blog for personal learning. The image content is extracted by ChatGPT. Here's the content from the image transformed in...

Posted on May 08, 2025 at 11:11 PM

Don't Make the Mistake of Thinking That What's Now Happening is Mostly About Tariffs (from X, Ray Dalio)

Don't Make the Mistake of Thinking That What's Now Happening is Mostly About Tariffs At this moment, a huge amount of attention is being justifiably paid to the announced tariffs and their ver...

Posted on April 08, 2025 at 12:12 PM

Deploy local chatgpt or deepseek like application using gptme

If you are concern privacy issue or cost of running agent based application, now you can do it by setup local application using GPTME: personal AI assistant/agent in your terminal. Currently the ...

Posted on March 16, 2025 at 12:15 AM

Hallucination (error) never disappears in LLM because of its probability nature

Today another bad practice (Hallucination) using generative AI in product is pop up in news and social media. Here is a report from BBC Google remakes Super Bowl ad after AI cheese gaffe. Halluci...

Posted on February 10, 2025 at 10:18 AM

Fine-tuning NER vs LLM prompt for asset ticker extraction in finance UGC

With the increasing multiple-task capability of LLM model, it makes it easy to do specific ML task by prompting LLM to focus on specified task, such as sentiment classification, name entity recog...

Posted on January 26, 2025 at 05:37 PM

DuckDB: an efficient SQL development in Python

After a few weeks using DuckDb to develop product, particularly to handle complex data processing logic (e.g. multiple table join, condition, group, expand, cross-database operation, ...), I like...

Posted on January 19, 2025 at 12:32 PM

Resource sharing for AI fintech product development

# Fintech product development collection - Common financial risk and performance metrics. Used by zipline and pyfolio, [empyrical](https://github.com/quantopian/empyrical/tree/master) - Pytho...

Posted on January 18, 2025 at 12:19 PM

How to solve aiohttp.ClientSession failure: Client error for XXX: Can not write request body for API_URL

aiohttp_ClientSession_issue Investigate aiohttp.ClientSession randomly failure when batch calling APIs, e.g. Client error for XXX: Can not write request body for API_URL What is the issue? ...

Posted on January 12, 2025 at 02:40 PM

AGI, I don’t expect what I can see.

AGI, not PR AGI, is not possible, at least in next years. But text, vision, multi-modal foundation models make it easy to develop AI/ML based applications using domain knowledge to tailor llm to ...

Posted on January 07, 2025 at 09:20 PM

Remote conntection disconnected in FastAPI server

When I develop LLM agent based service (e.g. call openAI api async) using multiple workers to parallel processing large requests, I use uvicorn in APP code to start multiple workers. In server si...

Posted on November 21, 2024 at 09:26 PM