Optimization

fluiq.optimize() enables semantic caching on Fluiq-managed Redis. Calls with semantically similar prompts are served from cache — instant response, zero API cost.

One call to optimize() enables semantic caching for all traced OpenAI calls — chat, streaming, and embeddings.

Python

import openai
from fluiq import instrument, optimize

instrument(api_key="fl_...")
optimize()  # semantic caching (Team+ plan)

client = openai.OpenAI()

# First call — hits OpenAI, response cached in Redis
r1 = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What is machine learning?"}],
)

# Semantically similar call — served instantly from cache
r2 = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain machine learning to me"}],
)
# r2: same quality, zero latency, zero API cost