Home/Integrazioni/LlamaIndex
Integrazione · Configurazione in 60 secondi · Zero markup

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.

Configurazione

Pronto in cinque passi.

  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.
Configurazione
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.")
Perché instradare LlamaIndex attraverso 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.

Altre integrazioni

Instrada subito LlamaIndex attraverso OrcaRouter.

Registrati in un minuto, ottieni una chiave sk-orca-… e incollala in LlamaIndex. Zero markup sui token, failover automatico tra tutti i provider.

Ottieni API key →