Integratie · 60 seconden installatie · Geen marge
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.
Instellen
Vijf stappen.
- 1.Install: pip install llama-index-llms-openai
- 2.Import OpenAI from llama_index.llms.openai
- 3.Construct with api_base='https://api.orcarouter.ai/v1' and api_key='sk-orca-…'
- 4.Assign to Settings.llm so every query engine picks it up.
- 5.Build indices and query as usual — synthesis routes through OrcaRouter.
Configuratie
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.")Waarom LlamaIndex via OrcaRouter routeren?
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.
Overige integraties
Route LlamaIndex vandaag nog via OrcaRouter.
Registreer je in minder dan een minuut, pak een sk-orca-…-sleutel en plak deze in LlamaIndex. Geen marge op tokens. Automatische failover over elke provider.
