Интеграция · Настройка за 60 секунд · Без наценки

LlamaIndex + OrcaRouter

LlamaIndex's OpenAI LLM class accepts api_base and api_key overrides. Route indexing, query, and synthesis calls through OrcaRouter for zero markup and automatic failover across providers.

Настройка

Пять шагов.

  1. 1.Install: pip install llama-index-llms-openai
  2. 2.Import OpenAI from llama_index.llms.openai
  3. 3.Construct with api_base='https://api.orcarouter.ai/v1' and api_key='sk-orca-…'
  4. 4.Assign to Settings.llm so every query engine picks it up.
  5. 5.Build indices and query as usual — synthesis routes through OrcaRouter.
Конфигурация
from llama_index.llms.openai import OpenAI
from llama_index.core import Settings

Settings.llm = OpenAI(
    api_base="https://api.orcarouter.ai/v1",
    api_key="sk-orca-...",
    model="gpt-4o",
)

# Now every query engine, agent, and chat engine uses OrcaRouter.
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
docs = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(docs)
response = index.as_query_engine().query("Summarize the key points.")
Зачем направлять LlamaIndex через OrcaRouter?

RAG pipelines make many small calls per query (retrieve → rerank → synthesize). OrcaRouter's per-request routing means each of those calls independently picks the cheapest healthy backend, and you see the full breakdown in one dashboard.

Другие интеграции

Подключите LlamaIndex к OrcaRouter сегодня.

Зарегистрируйтесь меньше чем за минуту, получите sk-orca-… ключ и вставьте его в LlamaIndex. Никакой наценки на токены. Автоматический failover между провайдерами.

Получить API-ключ →