Framework & platform

LlamaIndex

Integrasikan TokenLab dengan LlamaIndex menggunakan integrasi yang kompatibel dengan OpenAI

Gambaran Umum

Gunakan LlamaIndex OpenAILike untuk TokenLab. Ini menerima Base URL kustom dan tidak menyimpulkan metadata model dari nama model OpenAI.

Instalasi

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

Konfigurasi Dasar

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

Penggunaan Dasar

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

LLM OpenAILike Minimal

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,
)

Chat

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)

Streaming

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

Embeddings

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

RAG dengan Dokumen

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)

Chat Engine

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)

Penggunaan Asinkron

import asyncio

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

asyncio.run(main())

Praktik Terbaik

Di halaman ini