<!--
-->

<img src="https://hackmd.io/_uploads/H1Csx_gMye.png" alt="【臺東縣消防局】視訊選案輔導暨技術支援.pptx (1080 x 680 像素) (1)" width="800" height="300">

## 5-Day Gen AI Intensive Course with Google

<!--
<details>
<summary>All Resources</summary>
-->

### Other Related
<details>
<summary> Resource </summary>

<details>
<summary>1. Youtube回放清單</summary>

- [Youtube連結](https://youtube.com/playlist?list=PLqFaTIg4myu-b1PlxitQdY0UYIbys-2es&si=fFnRmVlJJAwixt2Q)
</details>

<details>
<summary>2. Whitepaper PDF 文檔</summary>

- [雲端連結](https://drive.google.com/drive/folders/1eF-WCsQ39OF0pLlHMJHFHm794iQBxwc5?usp=sharing)
</details>

<details>
<summary>3. Whitepaper Companion Podcast</summary>

- [1. Foundational LLMs & Text Generation](https://youtu.be/mQDlCZZsOyo?si=DG8o9lUNeLriqRrL)
- [2. Prompt Engineering](https://youtu.be/F_hJ2Ey4BNc?si=5x6f_SFMx6OBNdNf)
- [3. Embeddings & Vector Stores](https://youtu.be/1CC39K76Nqs?si=qMqbDz_Tmwriba2j)
- [4. Solving Domain-Specific Problems Using LLMs](https://youtu.be/b1a4ZOQ8XdI?si=GHA7SSYoyUhbH0Lb)
- [5. Operationalizing Generative AI on Vertex AI using MLOps](https://youtu.be/k9S6IhiUUj4?si=AzO-iu6GN1lXas6B)
</details>

<details>
<summary>4. What's being covered?</summary>

- **Day 1: Foundational Models & Prompt Engineering** - Explore the evolution of LLMs, from transformers to techniques like fine-tuning and inference acceleration. Get trained with the art of prompt engineering for optimal LLM interaction.

- **Day 2: Embeddings and Vector Stores/Databases** - Learn about the conceptual underpinning of embeddings and vector databases, including embedding methods, vector search algorithms, and real-world applications with LLMs, as well as their tradeoffs.

- **Day 3: Generative AI Agents** - Learn to build sophisticated AI agents by understanding their core components and the iterative development process.

- **Day 4: Domain-Specific LLMs** - Delve into the creation and application of specialized LLMs like SecLM and Med-PaLM, with insights from the researchers who built them.

- **Day 5: MLOps for Generative AI** - Discover how to adapt MLOps practices for Generative AI and leverage Vertex AI's tools for foundation models and generative AI applications.

</details>

</details>

### Day1 - Foundational Models & Prompt Engineering
<details>
<summary>Resource</summary>

- [Day 1 - Prompting](https://www.kaggle.com/code/markishere/day-1-prompting)
- [心智圖](https://xmind.ai/share/HMKKsqDu?xid=bfPJSouu)

</details>

### Day2 - Embeddings and Vector Stores/Databases
<details>
<summary>Resource</summary>

- [Day 2 - Classifying embeddings with Keras](https://www.kaggle.com/code/markishere/day-2-classifying-embeddings-with-keras)
- [Day 2 - Embeddings and similarity scores](https://www.kaggle.com/code/markishere/day-2-embeddings-and-similarity-scores)
- [Day 2 - Document Q&A with RAG](https://www.kaggle.com/code/markishere/day-2-document-q-a-with-rag)
- [心智圖](https://xmind.ai/share/Uec7Eudp?xid=uil1ADTc)

</details>

</details>

### Day3 - Generative AI Agents
<details>
<summary>Resource</summary>

- [Day 3 - Function calling with the Gemini API](https://www.kaggle.com/code/markishere/day-3-function-calling-with-the-gemini-api)
- [Day 3 - Building an agent with LangGraph](https://www.kaggle.com/code/markishere/day-3-building-an-agent-with-langgraph/)
- [心智圖](https://xmind.ai/share/RjSMAnqm?xid=OkYK9osq)

</details>

</details>

</details>

### Day4 - Domain-Specific LLMs
<details>
<summary>Resource</summary>

- [Day 4 - Google Search grounding](https://www.kaggle.com/code/markishere/day-4-google-search-grounding)
- [Day 4 - Fine tuning a custom model](https://www.kaggle.com/code/markishere/day-4-fine-tuning-a-custom-model)
- [心智圖](https://xmind.ai/share/acOGPGgw?xid=xXh1brXQ)

</details>

</details>

### Day5 - MLOps for Generative AI
<details>
<summary>Resource</summary>

- [Bonus Day - Extra API features to try](https://github.com/GoogleCloudPlatform/generative-ai/tree/main/gemini/sample-apps/e2e-gen-ai-app-starter-pack)
- [心智圖](https://xmind.ai/share/NzQVZDUq?xid=tddJQLlM)

</details>

</details>

### Bonus Day - Extra API features to try
<details>
<summary>Resource</summary>

- [GoogleCloudPlatform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai/tree/main/gemini/sample-apps/e2e-gen-ai-app-starter-pack)
- [心智圖](https://xmind.ai/share/rTgK7c4U?xid=LfuIS8vq)

</details>

</details>