Chapter 0.2 - Architecture Ingredients
[!info] Overview of the tech stack and tools.
📚 Tech Stack
| Component | Tool | Description |
|---|---|---|
| Programming Language | Python | The industry standard for AI/ML development. |
| Framework | LangChain / LlamaIndex | Helps orchestrate the different components of the RAG pipeline. |
| Vector Database | Pinecone / ChromaDB / Weaviate | Stores and searches vector embeddings efficiently. |
| Embedding Model | SentenceTransformers / OpenAI Embeddings | Converts text to vectors. |
| LLM | GPT-4 / LLaMA / Mistral | Generates the final answers. |
🛠️ Prerequisites
To get the most out of this course, you should be comfortable with:
Must-Have
- Python: Intermediate knowledge (functions, classes, libraries).
- Machine Learning Basics: Understanding what a model is and how training/inference works.
Good-to-Have
- NLP Concepts: Basic understanding of tokens, embeddings, and neural networks.
- APIs: Familiarity with using external services (like OpenAI).
- Vector Math: Understanding dot products and cosine similarity (covered in Chapter 1).