LlamaIndex Integration

LlamaIndex Integration

LlamaIndex works with Forge through the OpenAI-compatible API. Use Forge as your LLM and embedding provider to get intelligent routing and security for all your RAG pipelines.

Setup

pip install llama-index llama-index-llms-openai-like

Configure LLM

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="auto",
    api_key="forge_sk_your_key",
    api_base="https://api.optima-forge.com/v1",
    is_chat_model=True,
)

response = llm.complete("Summarize the benefits of RAG architectures.")
print(response.text)

RAG Pipeline

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents, llm=llm)
query_engine = index.as_query_engine()

response = query_engine.query("What are the key findings?")
print(response)

Benefits with Forge

• Automatic model selection based on query complexity
• Provider failover if your primary LLM is unavailable
• Cost optimization for embedding and completion calls
• Security scanning on all inputs and outputs
• Full tracing via Langfuse for every LlamaIndex operation