08. File I/O

Reading Files

# Read entire file
with open("prompts.txt", "r") as f:
    content = f.read()
    print(content)

The with statement ensures the file closes even if errors occur.

Reading Lines

# Read as list of lines
with open("prompts.txt", "r") as f:
    lines = f.readlines()

# Or iterate line by line (memory efficient for large files)
with open("prompts.txt", "r") as f:
    for line in f:
        print(line.strip())

Writing Files

# Write (overwrites existing content)
with open("output.txt", "w") as f:
    f.write("Hello, AI\n")
    f.write("Second line\n")

# Append (adds to existing content)
with open("output.txt", "a") as f:
    f.write("Third line\n")

JSON Files

AI systems frequently use JSON for configuration and data exchange:

import json

config = {
    "model": "gpt-4",
    "temperature": 0.7,
    "batch_size": 32
}

# Write JSON
with open("config.json", "w") as f:
    json.dump(config, f, indent=2)

# Read JSON
with open("config.json", "r") as f:
    loaded_config = json.load(f)

Handling Missing Files

import json
from pathlib import Path

config_path = Path("config.json")

if config_path.exists():
    with open(config_path) as f:
        config = json.load(f)
else:
    config = {"model": "gpt-4", "temperature": 0.7}
    with open(config_path, "w") as f:
        json.dump(config, f, indent=2)

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.