Day 5 - Jan 25 2026

First LLM Call (Hello World)

1. The Anatomy of an LLM Call

When we talk to an AI via code, we aren't just sending text; we are constructing a Payload.

• Model: Specifies which "brain" to use (e.g., llama3.2, gpt-4).

• Messages: A list of dictionaries representing the conversation history.

  • role: "user" → My input.

  • role: "assistant" → The AI's previous answers.

  • role: "system" → Instructions on how the AI should behave (we will cover this tomorrow).

2. The Response Object

The AI doesn't just return a string. It returns a JSON Object containing:

• model: The name of the model used.

• created_at: Timestamp.

• message: The actual content (this is what we extract).

• done: Boolean status.

3. Why Local (Ollama)?

I chose to use Ollama for this stage because:

• Zero Latency: No internet lag.

• Zero Cost: I can test a loop of 100 calls without paying $0.01.

• Privacy: My prompts (which might eventually contain private data) never leave my machine.

Status:

• SDK Installed (pip install ollama)

• Python Script day5_llm_call.py Created

• Successful Response Received