04. Control Flow

If, Elif, Else

temperature = 0.8

if temperature < 0.3:
    response_type = "creative"
elif temperature < 0.7:
    response_type = "balanced"
else:
    response_type = "focused"

print(f"Using {response_type} mode")

Ternary Expressions

For simple conditional assignment:

status = "success" if temperature < 1.0 else "failed"

For Loops

models = ["gpt-4", "gpt-3.5-turbo", "claude-3"]

for model in models:
    print(f"Processing {model}")

Use enumerate() when you need the index:

for i, model in enumerate(models):
    print(f"{i}: {model}")

While Loops

attempts = 0
max_attempts = 3

while attempts < max_attempts:
    print(f"Attempt {attempts + 1}")
    attempts += 1

Break and Continue

# Stop after finding the first match
for model in models:
    if "gpt-4" in model:
        print(f"Found: {model}")
        break

# Skip invalid entries
valid_tokens = [0, 100, 200, None, 500]
total = 0
for tokens in valid_tokens:
    if tokens is None:
        continue
    total += tokens

Checking Conditions

# Multiple conditions
if temperature > 0 and temperature < 1:
    print("Valid temperature")

# Membership
if model in ["gpt-4", "gpt-3.5-turbo"]:
    print("OpenAI model")

Local verification checkpoint

Run the smallest example from this chapter in a local workspace and record the package version, runtime, data path, and observed output. If the result depends on model size, vector count, CPU/GPU backend, or available memory, note that constraint beside the exercise so the lesson remains reproducible.

Local verification checkpoint

Run the smallest example from this chapter in a local workspace and record the package version, runtime, data path, and observed output. If the result depends on model size, vector count, CPU/GPU backend, or available memory, note that constraint beside the exercise so the lesson remains reproducible.