Creating a Thai-language AI tool

AI engineers share their insights in a titled seminar

AI engineers share their insights in a workshop titled “Challenges, Chances, and Opportunities of Thai ChatGPT,” held recently by Nectec.

Thai Artificial Intelligence (AI) engineers from public and private organizations have teamed up to develop a Thai-language AI-based generative chatbot, which is expected to benefit different sectors, from education to business.

The National Electronics and Computer Technology Center (Nectec) recently revealed its partnership with three organizations to launch the OpenThaiGPT project.

The three organizations are the Artificial Intelligence Entrepreneur Association of Thailand (AIEAT), the Artificial Intelligence Association of Thailand (AIAT), and the NSTDA Supercomputer Center (ThaiSC).

Generative AI is a type of artificial intelligence that can interact with users in natural language and create data, ranging from articles to multimodal content such as images, video and audio.

The OpenThaiGPT project tracks the popularity of generative AI, launched when the ChatGPT chatbot took the world by storm last November. This AI-powered tool can answer questions with well-written sentences, assist programmers in writing code, and even compose music.

Created by OpenAI, an AI lab in San Francisco, ChatGPT made waves by surpassing 1 million users within a week of its launch.

Now other global tech giants are jumping on the bandwagon to produce their own versions.

“It is important for Thailand to become a producer of technology rather than just a user in the field of generative AI,” said Thepchai Supnithi, director of Nectec’s AI Research Group, at the center’s recent seminar titled “Challenges, Possibility, and Opportunities of Thai ChatGPT”.

Thepchai, who is also a representative of AIAT, said that Thailand must have the ability to develop, modify and exploit the full potential of the Thai language using artificial intelligence.

According to Nectec, the OpenThaiGPT project is a chat-based assistant project where understanding of the Thai language is crucial to enable dynamic information retrieval and a user-friendly interface.

He said OpenThaiGPT was developed on an open source basis and will be distributed free of charge, with the option for customization and extension.


“This is an ideal time for Thailand to launch this project as the country has an abundance of local language data from and the largest supercomputer facility in Asean: ThaiSC’s LANTA,” said Thepchai.

The latest version, OpenThaiGPT 0.1.0-alpha, is capable of various tasks such as Q&A, machine translation, detailed explanations, paraphrasing and coding tips.

In future releases, the number of OpenThaiGPT parameters will increase from 3.74 billion to improve language understanding and natural interaction, he said.

The project uses publicly available data, with one of the current data contributors.

The project is always mindful of data privacy and copyrights while encouraging more data contributors to join the project, Thepchai said.

Kobkrit Viriyayudhakorn, president of AIEAT, said that OpenThaiGPT can be plugged into external systems or easily expanded, customized and further developed by everyone.

The project can also be integrated with other applications, serving as a building block for the development of the next generation of AI in Thailand, he said.

Possible use cases of OpenThaiGPT include chatbots, news digests, machine translation, and document classification.

Prachya Bookwan, Nectec researcher for natural language processing, said that OpenThaiGPT 0.1.0-alpha is capable of answering general questions, translating languages ​​and coding.

Version 1.0.0 scheduled for release mid-year has up to 10 billion parameters, he said.

Furthermore, the OpenThaiGPT team aims to develop a multimode option that can specify physical references beyond the language.

Prachya said the technology has the potential to work on smartphones in the future.

Wanchat Padungrat, the founder of, said he is willing to support the project so that it has a positive impact on society.

“If this project doesn’t produce good results or outcomes, it can set us back,” Wanchat said.


Viwan Jarerattanachat, head of science support and domain research at ThaiSC, said this project should improve AI capabilities in Thailand.

However, he acknowledged that this is still a case of trial and error, requiring security reviews to ensure it won’t harm people or be misused.

The project must have transparency, accountability and accountability, Ms Viwan said.

Apivadee Piyatumrong, Nectec’s senior researcher for the AI ​​Research Group, said there are guidelines and frameworks for building trustworthy AI in many countries.

In Thailand, the Ministry of Digital Economy and Society developed the “Digital Thailand-AI Ethics Guideline” in 2018 to include ethical considerations in the principles for AI development, Apivadee said.

Regarding the development of OpenThaiGPT, he said there are three main areas to consider to ensure its reliability.

First, safety measures must be in place to prevent any harm to life or property that could result from the use of the technology, Apivadee said. For example, if OpenThaiGPT is used in the medical field, it needs to be reviewed for safety and efficacy.

Secondly, transparency is essential for OpenThaiGPT. It should be clear where the data and models used come from and what is their quality and performance.

Third, accountability and governance are important factors in ensuring OpenThaiGPT is trusted, he said.

Chai Wutitiwatchai, executive director of Nectec, said Thailand has a national AI strategy master plan that was approved by the government last year.

The country’s AI Government Readiness Index score improved from 60th in 2020 to 31st in 2022, it said.

According to Kobkrit, the AIEAT study titled “Thailand’s AI business status in 2022” reported that total AI revenue grew by 24% from 35.2 billion baht in 2020 to 40.8 billion in 2021.

The amount was mainly contributed by 105 artificial intelligence companies, 50 systems integrator companies and 50 hardware automation companies, it said.

Touchapon Kraisingkorn, co-founder of tech startup Amity, said he hopes OpenThaiGPT will become the de facto open source GPT model to gain broad acceptance in the Thai market.

He said that GPT technology has immense capabilities for solving inefficiencies in both the public and private sectors.

“This is a once-in-a-decade technology that will enable Thailand to make leaps and bounds in terms of productivity and technology proficiency,” said Touchapon.


Panutat Tejasen, managing director of new AI startup ThaiGPT Co, said the company sees a business opportunity leveraging generative AI technology and the popularity of ChatGPT.

The company is also open to using other generative AI models, he said.

Thai cryptocurrency exchange Bitkub is a major investor in ThaiGPT Co.

ThaiGPT aims to develop, integrate and customize AI solutions using the Thai language to serve its enterprise customers, Panutat said.

The company is already developing AI-powered customer service solutions to enable a customer to provide answers to questions about the customer’s products and services, as well as the ability to upsell and cross-sell.

He said development of the solutions should be finished in two months.


Ruangroj Poonpol, president of Kasikorn Business-Technology Group (KBTG), said that in recent years, many companies have seen AI play a bigger role in various job functions.

“The rise of generative AI like ChatGPT has caused a buzz in business circles that humans may soon be replaced by AI,” he said.

A cooperative relationship between humans and AI will lead to maximum efficiency and sustainability for work processes, Ruangroj said.

This cooperation results in the concept of “augmented intelligence,” in which AI is designed to help improve the work and capabilities of humans, not replace them, he said.

“By building human-centric machine learning models, AI is trained to receive human feedback and transform that data into guidelines to help improve human decision-making and certain actions to be more accurate and precise,” said Ruangroj.

KBTG and MIT Media Lab have developed artificial intelligence through research called K-GPT (Knowledge-GPT), which takes advantage of ChatGPT’s ability to provide in-depth domain knowledge by using more natural language in its conversations.

The project has improved his knowledge of the Thai language so that he can answer questions and simultaneously offer advice from different angles.

KBTG Labs and MIT Media Lab also collaborated on a proof-of-concept research called “Kookid,” featuring two conversational agents Kana and Kacha offering answers from different angles needed for user decision-making.

#Creating #Thailanguage #tool

Leave a Comment