2

Understanding Transformers: The Brain Behind LLMs

3

Tokenization: How LLMs See Your Text

4

Temperature, Top-P, and Frequency Penalties

5

script_id: day_005_temperature_and_sampling_part2/penalties_example

6

Zero-Shot vs Few-Shot Prompting

7

Chain of Thought (CoT) and Step-by-Step Reasoning

8

script_id: day_008_chain_of_thought_part2/problem_decomposition

9

System Prompts vs User Prompts

10

Using OpenAI and Anthropic Python SDKs

11

script_id: day_011_openai_anthropic_sdks_part2/unified_llm_wrapper

12

Streaming Responses: Real-Time LLM Output

13

script_id: day_013_streaming_responses_part2/streaming_chat_interface

14

Using Pydantic to Define Strict Data Schemas

15

Testing LLM Applications

16

Building Retry Loops for LLM Output Errors

17

DSPy -- Programmatic Prompt Optimization

18

Capstone — Build a Structured Data Extraction Pipeline

Capstone