Dr.Jiw: กุมภาพันธ์ 2026

วันอังคารที่ 24 กุมภาพันธ์ พ.ศ. 2569

NLP library for python

spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python

https://spacy.io/

Streamlit

Streamlit is an open-source Python framework for data scientists and AI/ML engineers to deliver interactive data apps (more flexible than dashboards created by Google Looker).

Streamlit is for developers who want to turn complex Python scripts, data analyses, and machine learning models into shareable web apps with minimal front-end effort.

https://streamlit.io/

MongoDB stack

MERN stack: MongoDB, Express, Angular, Node

https://www.mongodb.com/resources/languages/mern-stack

Supabase

Supabase is the Postgres development platform. Start your project with a Postgres database, Authentication, instant APIs, Edge Functions, Realtime subscriptions, Storage, and Vector embeddings.

When to use Unstructured/Semi-structured Data?

Unstructured/Semi-structured Data is well-suited for data that doesn't fit neatly into the rows and columns of a traditional table, such as chat logs, various-structured notification messages, product catalogs with varied attributes, or IoT data.

Pyvis

A framework for Interactive network visualization

LLM temperature

LLM temperature is a hyperparameter (typically 0 to 2) that controls the randomness and creativity of an AI's output by adjusting the probability distribution of predicted tokens. Lower temperatures (0-0.3) produce deterministic, focused, and factual results, while higher temperatures (>0.8) create more diverse, random, or "creative" text.

https://dagshub.com/glossary/llm-temperature/

The following article shows how to use Bash script to interact with Ollama

https://www.inferable.ai/blog/posts/model-temperature-first-principles

Zero Temperature (0.0): Makes the model completely deterministic. It will always choose the token (word or syllable) with the absolute highest probability at that exact step.

While setting the temperature to $0$ forces the model to choose its "best guess" every single time, the model's best guess can still be completely wrong.

How Hallucinations Are Actually Mitigated

Because temperature is just a decoding hyperparameter, engineers and researchers use structural architectural patterns to combat hallucinations:

Retrieval-Augmented Generation (RAG): Grounding the model by supplying it with verified, external documents to reference before it generates an answer.
Fine-Tuning & Reinforcement Learning from Human Feedback (RLHF): Training the model specifically to say "I don't know" when it lacks data, rather than guessing.
RLHF: Human evaluators rank llm answers from best to worst based on quality, accuracy, and safety.
System Prompt Constraints: Explicitly instructing the model (e.g., "If you do not find the answer in the provided context, state that you do not know.").

If you are working on a system where factual accuracy is paramount, keeping the temperature low (around 0.0 to 0.2) is a great baseline practice—just don't mistake determinism for truth.

Tech stack

A tech stack (technology stack) is the combination of programming languages, frameworks, libraries, databases, front-end tools, back-end tools, and APIs used to build and run a software application. It acts as the "solution stack" or, foundation, organizing tools into layers—client-side (front-end) and server-side (back-end)—that work together to create a functional, scalable application.

Key Components of a Tech Stack:

Front-End (Client-Side): What users interact with, including HTML, CSS, JavaScript, and frameworks like React (for building web app with JavaScript), React Native (for building Mobile app) or Angular.
Back-End (Server-Side):
The "under the hood" logic, including programming languages like Python, Java, or Node.js, Docker, and frameworks like
Django
or
Express
.

Database: Where data is stored, such as MySQL, PostgreSQL, or MongoDB.

Popular Examples: LAMP: Linux, Apache, MySQL, PHP/Python/Perl.

IDE: Android Studio, Xcode, VScode

UX/UI Design: Figma

วันศุกร์ที่ 20 กุมภาพันธ์ พ.ศ. 2569

Backtracking

Backtracking is a class of algorithms for finding solutions to some computational problems, notably constraint satisfaction or enumeration problems, that incrementally builds candidates to the solutions, and abandons a candidate ("backtracks") as soon as it determines that the candidate cannot possibly be completed to a valid solution.

Example is Maze Solving (เขาวงกต): Moving through a maze and turning back when you hit a wall to try the other fork in the road.

Backtracking is implemented by means of recursion.

Poisson distribution (& Binomial distribution & Gaussian distribution)

Poisson distribution expresses the probability of a given number of events of the same type (e.g., counting the number of emails received between 9:00 AM and 10:00 AM. (one event type: emails)) occurring in a fixed interval of time if these events occur with a known constant mean rate and independently of the time since the last event.