Skip to content
LlamaIndex 文档版本 跟随上游 源快照 973119c0 更新于 2026-10-18

安装

首先,安装所需的软件包:

终端窗口

%pip install llama-index-llms-deepinfra
%pip install llama-index-llms-deepinfra

初始化

使用你的 API 密钥和所需参数设置 DeepInfraLLM 类:

from llama_index.llms.deepinfra import DeepInfraLLM
import asyncio

llm = DeepInfraLLM(
    model="mistralai/Mixtral-8x22B-Instruct-v0.1",  # Default model name
    api_key="your-deepinfra-api-key",  # Replace with your DeepInfra API key
    temperature=0.5,
    max_tokens=50,
    additional_kwargs={"top_p": 0.9},
)

同步补全

使用 complete 方法同步生成文本补全:

response = llm.complete("Hello World!")
print(response.text)

同步流式补全

使用 stream_complete 方法同步生成流式文本补全:

content = ""
for completion in llm.stream_complete("Once upon a time"):
    content += completion.delta
    print(completion.delta, end="")

同步聊天

使用 chat 方法同步生成聊天响应:

from llama_index.core.base.llms.types import ChatMessage

messages = [
    ChatMessage(role="user", content="Tell me a joke."),
]
chat_response = llm.chat(messages)
print(chat_response.message.content)

同步流式聊天

使用 stream_chat 方法同步生成流式聊天响应:

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="Tell me a story."),
]
content = ""
for chat_response in llm.stream_chat(messages):
    content += chat_response.message.delta
    print(chat_response.message.delta, end="")

异步补全

使用 acomplete 方法异步生成文本补全:

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

asyncio.run(async_complete())

异步流式补全

使用 astream_complete 方法异步生成流式文本补全:

async def async_stream_complete():
    content = ""
    response = await llm.astream_complete("Once upon an async time")
    async for completion in response:
        content += completion.delta
        print(completion.delta, end="")

asyncio.run(async_stream_complete())

异步聊天

使用 achat 方法异步生成聊天响应:

async def async_chat():
    messages = [
        ChatMessage(role="user", content="Tell me an async joke."),
    ]
    chat_response = await llm.achat(messages)
    print(chat_response.message.content)

asyncio.run(async_chat())

异步流式聊天

使用 astream_chat 方法异步生成流式聊天响应:

async def async_stream_chat():
    messages = [
        ChatMessage(role="system", content="You are a helpful assistant."),
        ChatMessage(role="user", content="Tell me an async story."),
    ]
    content = ""
    response = await llm.astream_chat(messages)
    async for chat_response in response:
        content += chat_response.message.delta
        print(chat_response.message.delta, end="")

asyncio.run(async_stream_chat())

如有任何问题或反馈,请通过 feedback@deepinfra.com 联系我们。

BytesRouter 是社区翻译站点,所有译文仅供参考,一切以官方英文原文为准。