Cache de LLM

Reduza custos e latência de LLM com camadas de cache de correspondência exata, semântica e do lado do provedor.

Quando Usar Esta Habilidade

Use esta habilidade quando:

• As mesmas consultas ou consultas semelhantes são feitas repetidamente (bots de FAQ, ferramentas de suporte)
• Os custos da API de LLM estão crescendo e você precisa de economias imediatas
• Atendendo a altos volumes de requisições onde consultas repetidas causam gargalos
• Implementando cache de prompt para prompts de sistema longos (Anthropic/OpenAI)
• Construindo recursos de IA com capacidade offline que precisam de persistência de resposta

Camadas de Cache

Request → Exact Cache → Semantic Cache → Provider Cache → LLM API
             ↓ hit            ↓ hit             ↓ hit
           instant          ~5ms           50-80% cheaper

Camada 1: Cache de Correspondência Exata (Redis)

import hashlib
import json
import redis
from openai import OpenAI

r = redis.Redis(host="localhost", port=6379, decode_responses=True)
client = OpenAI()

def build_cache_key(model: str, messages: list, temperature: float) -> str:
    """Deterministic key from request parameters."""
    payload = json.dumps({
        "model": model,
        "messages": messages,
        "temperature": temperature,
    }, sort_keys=True)
    return f"llm:exact:{hashlib.sha256(payload.encode()).hexdigest()}"

def cached_completion(model: str, messages: list, temperature: float = 0.0,
                      ttl: int = 3600) -> dict:
    key = build_cache_key(model, messages, temperature)

    # Check cache
    if cached := r.get(key):
        return json.loads(cached)

    # Call API
    response = client.chat.completions.create(
        model=model, messages=messages, temperature=temperature
    )
    result = response.model_dump()

    # Cache result (only cache deterministic responses)
    if temperature == 0.0:
        r.setex(key, ttl, json.dumps(result))

    return result

Camada 2: Cache Semântico (GPTCache)

from gptcache import cache, Config
from gptcache.adapter import openai
from gptcache.embedding import Onnx
from gptcache.manager import CacheBase, VectorBase, get_data_manager
from gptcache.similarity_evaluation.distance import SearchDistanceEvaluation

# Configure GPTCache with Qdrant backend
def init_gptcache(cache_obj, llm: str):
    onnx = Onnx()                              # local embedding model
    data_manager = get_data_manager(
        CacheBase("redis"),                    # metadata store
        VectorBase("qdrant",
                   host="localhost",
                   port=6333,
                   collection_name=f"llm-cache-{llm}",
                   dimension=onnx.dimension),
    )
    cache_obj.init(
        embedding_func=onnx.to_embeddings,
        data_manager=data_manager,
        similarity_evaluation=SearchDistanceEvaluation(),
        config=Config(similarity_threshold=0.80),  # 80% similarity = cache hit
    )

cache.set_openai_key()
init_gptcache(cache, "gpt-4o-mini")

# Now openai calls are automatically cached
response = openai.ChatCompletion.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "What is machine learning?"}],
)
# Second call with similar question ("Explain machine learning") → cache hit

Cache Semântico Personalizado (Pronto para Produção)

from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct, Filter, FieldCondition, Range
import numpy as np
import uuid
import time

embed_model = SentenceTransformer("BAAI/bge-small-en-v1.5")  # rápido, 33M parâmetros
qdrant = QdrantClient("http://localhost:6333")

CACHE_COLLECTION = "semantic-cache"
SIMILARITY_THRESHOLD = 0.88
CACHE_TTL_SECONDS = 86400  # 24h

# Cria a coleção uma vez
qdrant.create_collection(
    collection_name=CACHE_COLLECTION,
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
    on_disk_payload=True,
)

def semantic_cache_lookup(query: str, model: str) -> str | None:
    embedding = embed_model.encode(query).tolist()
    results = qdrant.query_points(
        collection_name=CACHE_COLLECTION,
        query=embedding,
        query_filter=Filter(must=[
            FieldCondition(key="model", match={"value": model}),
            FieldCondition(key="expires_at", range=Range(gte=time.time())),
        ]),
        limit=1,
        score_threshold=SIMILARITY_THRESHOLD,
    )
    if results.points:
        return results.points[0].payload["response"]
    return None


…