Comprehensive research on integrating ThaiLLM into SinkAlert for the BDI Hackathon 2026 Special Prize.
ThaiLLM is BDI's flagship national AI project — an open-weight, Apache 2.0 licensed Thai Large Language Model ecosystem. It is both an open model AND accessible via API.
ThaiLLM/ThaiLLM-8B — continued pre-training of Qwen3-8B-Base on ~63B tokens (31.5B Thai + 24B English + 8B curated government, medical, legal, finance, news, education data).
Collaborative Ecosystem: Built by BDI, NECTEC, VISTEC, AIEAT, AIAT. Computing sponsored by Ministry of Digital Economy and Society.
| Model | Size | Type | Key Feature |
|---|---|---|---|
ThaiLLM/ThaiLLM-8B | 8B | Foundation | Qwen3-based, needs fine-tuning |
ThaiLLM/ThaiLLM-8B-ToolUse | 8B | Tool Calling | RL-tuned, 99.9% routing accuracy |
ThaiLLM/ThaiLLM-8B-MedApp | 8B | Medical | Fine-tuned for appointments, reminders |
ThaiLLM/ThaiLLM-30B | 30B | MoE | Qwen3-MoE, higher capacity |
| Model | Organization | Key Feature |
|---|---|---|
| Typhoon-S | SCB 10X | 🏆 Tool calling via vLLM (hermes parser), 32K context |
| THaLLE-0.2 | KBTG Labs | Thinking/non-thinking modes, best Thai benchmarks |
| OpenThaiGPT | AIEAT | API-hosted, tool calling examples |
| Pathumma | NECTEC | Thinking variant, complex reasoning |
| KhanomTanLLM2 | PyThaiNLP | GGUF quantized, easy local deployment |
Base URL: https://thaillm.or.th/vllm-qwen/v1
Model: Qwen/Qwen3-30B-A3B-Instruct-2507-FP8
Protocol: OpenAI-compatible (/v1/chat/completions)
Auth: API key required (contact BDI for hackathon access)
This is the most authoritative API for the hackathon. Found in the visai-ai/thaillm-workshop .env.example as LLM_ARENA_1_BASE_URL.
Base URL: https://api.aieat.or.th/v1
Model: openthaigpt-1.5-7b-instruct
Auth: Dummy key (public research access)
Features: Tool calling, function calling
GitHub: github.com/OpenThaiGPT/openthaigpt1.5_api_examples
| Benchmark | Improvement vs Qwen3 | Score |
|---|---|---|
| ThaiExam (A-Level) | +36 pp | — |
| Belebele-Thai | +46 pp | 0.388 → 0.845 |
| MMLU-Thai | +2 pp | — |
| M3Exam | +5.7 pp | — |
| THaLLE-0.2 (Thinking mode) | M3 Exam 0.779, Flare CFA 0.852 | |
LINE Messaging API → Your Server → ThaiLLM API
↓
1. Citizen sends "ถนนแถวสุขุมวิทซอย 22 ทรุดตัว"
2. ThaiLLM-ToolUse classifies: damage_type=SUBSIDENCE, severity=HIGH
3. Typhoon-S generates Thai response: "ขอบคุณสำหรับการแจ้งเตือน..."
4. Risk data logged to SinkAlert pipeline
Pipeline: InSAR Data + Environmental Data → ThaiLLM Summary
คุณคือนักธรณีวิทยา AI ของกรมทางหลวง
กรุณาสรุปรายงานความเสี่ยงถนนทรุดตัวประจำวัน:
1. บทสรุปผู้บริหาร
2. พื้นที่เสี่ยงสูงสุด 5 อันดับ
3. แนวโน้มการทรุดตัว
4. ข้อเสนอแนะสำหรับเจ้าหน้าที่
5. แผนปฏิบัติการเร่งด่วน
| Resource | URL |
|---|---|
| ThaiLLM HuggingFace | huggingface.co/ThaiLLM |
| Official Playground API | thaillm.or.th |
| OpenThaiGPT API | api.aieat.or.th/v1 |
| ThaiLLM Workshop (Docker) | github.com/visai-ai/thaillm-workshop |
| ThaiLLM Fact Vector DB | github.com/visai-ai/thaillm-fact-vector-db |
| Typhoon-S (SCB 10X) | huggingface.co/typhoon-ai/... |
| THaLLE-0.2 (KBTG) | huggingface.co/KBTG-Labs/... |
| OpenThaiGPT Examples | github.com/OpenThaiGPT/... |
| GGUF Quantized Models | huggingface.co/mradermacher |
| BDI Hackathon Page | bdi.or.th/bkkhackathon2026/ |