LlamaIndex

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

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-5.4",
    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

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

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)

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

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

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 = 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)

import asyncio

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

asyncio.run(main())