Reference library

AI & LLM integration patterns

Call LLM APIs, structure prompts, parse responses, and ship AI features safely.

4 matches

How to Append Few-Shot Examples to a Prompt in Python

This code builds a complete LLM prompt by appending few-shot examples in alternating user/assistant format using a simple loop.

prompt-engineering few-shot llm

Python

def append_few_shot_examples(prompt: str, examples: list[tuple[str, str]], separator: str = "\n\n") -> str:
    """Append few-shot examples to a prompt in alternating user/assistant format."""
    full_prompt = prompt
    for user_input, assistant_output in examples:
        full_prompt = f"{full_prompt}{separator}Use…

15 0 Open

AI & LLM integration patterns medium

How to Build a Data Helper for LLM Prompts in Python

A beginner-friendly helper class that flattens nested dictionaries, formats prompt templates, and safely parses JSON for AI/LLM pipelines.

llm prompt-engineering data-prep

Python

import json
from typing import Any, Dict, List, Optional


class DataHelper:
    """Simple helper class for working with data in AI/LLM pipelines."""
    
    def __init__(self, data: Optional[Dict[str, Any]] = None) -> None:
        self.data = data or {}
    
    def flatten(self, prefix: str = "") -> Dict[str, Any]…

17 0 Open

AI & LLM integration patterns easy

How to Mock OpenAI Tool Call Messages in Python

Create an assistant message with a function tool call in OpenAI's chat format, useful for testing and mocking.

openai tool-calls mock

Python

from openai import OpenAI


def mock_tool_call(tool_name: str, arguments: dict) -> dict:
    """Simulate a tool call message in OpenAI style."""
    return {
        "role": "assistant",
        "content": None,
        "tool_calls": [
            {
                "id": "call_" + "a1b2c3d4e5f6",
                "type…

14 0 Open

AI & LLM integration patterns easy

Serialize and Format Data for LLM Prompts in Python

Use dataclasses and the json module to convert Python objects to JSON strings, parse them back, and format structured data into prompt-friendly text for LLM calls.

dataclasses json llm

Python

import json
from dataclasses import dataclass, asdict


@dataclass
class Recipe:
    """Simple data model to represent a recipe."""
    name: str
    cuisine: str
    prep_minutes: int


def to_json(recipe: Recipe) -> str:
    """Serialize a Recipe to a JSON string."""
    return json.dumps(asdict(recipe), indent=2)

…

14 0 Open

Browse by section

Each section groups closely related Python snippets.