Reference library

AI & LLM integration patterns

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

3 matches

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 medium

How to cache embeddings with a Python dict to avoid recomputation

Caches embeddings computed from text in a dictionary keyed by SHA-256 hash, returning cached results for repeated calls.

embedding cache dict

Python

import hashlib
import time


class EmbeddingCache:
    def __init__(self):
        self.cache = {}

    def _hash_text(self, text):
        return hashlib.sha256(text.encode()).hexdigest()

    def get_embedding(self, text, compute_func):
        key = self._hash_text(text)
        if key not in self.cache:
          …

15 0 Open

AI & LLM integration patterns medium

How to parallel map embeddings with a thread pool in Python

Run embedding computations in parallel using ThreadPoolExecutor, collect results into a dict keyed by the original item.

concurrency threadpool embeddings

Python

import threading
from concurrent.futures import ThreadPoolExecutor
import time


def compute_embedding(item: int) -> tuple[int, int]:
    time.sleep(0.05)  # Simulate embedding work
    return item, item * 10


def parallel_map_embed(items, max_workers=3):
    results = {}
    with ThreadPoolExecutor(max_workers=max_w…

15 0 Open

Browse by section

Each section groups closely related Python snippets.