MyMagic AI 大语言模型

%pip install llama-index-llms-mymagic

!pip install llama-index

from llama_index.llms.mymagic import MyMagicAI

llm = MyMagicAI(
    api_key="your-api-key",
    storage_provider="s3",  # s3, gcs
    bucket_name="your-bucket-name",
    session="your-session-name",  # files should be located in this folder on which batch inference will be run
    role_arn="your-role-arn",
    system_prompt="your-system-prompt",
    region="your-bucket-region",
    return_output=False,  # Whether you want MyMagic API to return the output json
    input_json_file=None,  # name of the input file (stored on the bucket)
    list_inputs=None,  # Option to provide inputs as a list in case of small batch
    structured_output=None,  # json schema of the output
)

resp = llm.complete(
    question="your-question",
    model="chhoose-model",  # currently we support mistral7b, llama7b, mixtral8x7b, codellama70b, llama70b, more to come...
    max_tokens=5,  # number of tokens to generate, default is 10
)

# The response indicated that the final output is stored in your bucket or raises an exception if the job failed
print(resp)

import asyncio

async def main():
    response = await llm.acomplete(
        question="your-question",
        model="choose-model",  # supported models constantly updated and are listed at docs.mymagic.ai
        max_tokens=5,  # number of tokens to generate, default is 10
    )

    print("Async completion response:", response)

await main()