Reference library

AI & LLM integration patterns

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

4 matches

Cosine Similarity to Retrieve Top K Chunks in Python

Compute cosine similarity between a query vector and a list of chunk vectors, then return the indices and scores of the top k most similar chunks.

cosine-similarity retrieval embeddings

Python

import numpy as np
from numpy.linalg import norm

def cosine_similarity(vec1, vec2):
    return np.dot(vec1, vec2) / (norm(vec1) * norm(vec2))

def retrieve_top_k(query_vec, chunk_vectors, k=3):
    similarities = [cosine_similarity(query_vec, vec) for vec in chunk_vectors]
    top_indices = sorted(range(len(similarit…

16 0 Open

AI & LLM integration patterns easy

How to Build a Simple Semantic Cache for Similar Prompts in Python

Mock a semantic cache that finds the closest matching prompt using word-overlap similarity and returns cached results above a threshold.

semantic cache prompt matching llm

Python

prompt_cache = [
    "What is the capital of France?",
    "How does recursion work?",
    "Best practices for Python logging?",
    "Explain binary search in one line.",
    "How to reverse a string in Python?"
]

def normalize(text):
    return " ".join(text.lower().split())

def similarity(a, b):
    a_words = set(…

14 0 Open

AI & LLM integration patterns easy

How to Build an In-Memory Vector Store in Python

Build a lightweight in-memory vector store using a Python dict and cosine similarity for fast nearest-neighbor searches.

vector-store cosine-similarity embeddings

Python

import math
from typing import Dict, List, Optional


class InMemoryVectorStore:
    def __init__(self) -> None:
        self.vectors: Dict[str, List[float]] = {}
        self.index: Dict[str, List[str]] = {}  # query -> list of ids sorted by similarity

    def add(self, vector_id: str, vector: List[float]) -> None:
…

13 0 Open

AI & LLM integration patterns easy

How to Keep Last K Turns in a Memory Buffer in Python

A TurnBuffer class using deque with maxlen to keep only the most recent k conversation turns in memory for LLM context.

deque llm-context memory-buffer

Python

from collections import deque

class TurnBuffer:
    def __init__(self, k):
        self.k = k
        self.turns = deque(maxlen=k)

    def add(self, turn):
        self.turns.append(turn)

    def last_k(self):
        return list(self.turns)


if __name__ == "__main__":
    buffer = TurnBuffer(3)
    buffer.add("tu…

14 0 Open

Browse by section

Each section groups closely related Python snippets.