TokenLab

프레임워크 및 플랫폼

LlamaIndex

OpenAI 호환 연동을 통해 TokenLab을 LlamaIndex와 연동하기

개요

TokenLab에는 LlamaIndex OpenAILike를 사용하세요. 커스텀 Base URL을 지원하며 OpenAI 모델 이름으로부터 모델 메타데이터를 유추하지 않습니다.

설치

pip install llama-index-core \
  llama-index-readers-file \
  llama-index-llms-openai-like \
  llama-index-embeddings-openai-like

기본 설정

from llama_index.core import Settings
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

llm = OpenAILike(
    model="gpt-5.6-terra",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
    is_chat_model=True,
)

embed_model = OpenAILikeEmbedding(
    model_name="text-embedding-3-small",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
)

Settings.llm = llm
Settings.embed_model = embed_model

기본 사용법

response = llm.complete("Explain TokenLab in one sentence.")
print(response.text)

최소 OpenAILike LLM

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="claude-sonnet-5",
    api_base="https://api.tokenlab.sh/v1",
    api_key="sk-your-tokenlab-key",
    context_window=200000,
    is_chat_model=True,
    is_function_calling_model=True,
)

채팅

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="What is the capital of France?")
]

response = llm.chat(messages)
print(response.message.content)

스트리밍

for chunk in llm.stream_complete("Write a short poem about AI."):
    print(chunk.delta, end="", flush=True)

임베딩

vector = embed_model.get_text_embedding("Hello, world!")
print(vector[:5])

문서를 활용한 RAG

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What is in my documents?")
print(response)

채팅 엔진

chat_engine = index.as_chat_engine(chat_mode="condense_question")

response = chat_engine.chat("What is TokenLab?")
print(response)

response = chat_engine.chat("How many models does it support?")
print(response)

비동기 사용법

import asyncio

async def main():
    response = await llm.acomplete("Hello!")
    print(response.text)

asyncio.run(main())

모범 사례

이 페이지의 내용