ErisPulse-OpenAI 模块文档
简介
ErisPulse-OpenAI 是一个 OpenAI 通用接口的封装模块,提供了便捷的异步接口来与 OpenAI API 交互。
使用示例
基本使用
from ErisPulse import sdk
# 初始化模块
openai = sdk.OpenAI
# 同步聊天
messages = [{"role": "user", "content": "你好"}]
response = await openai.chat(messages)
print(response)
# 流式聊天
async for chunk in openai.chat_stream(messages):
print(chunk, end="", flush=True)
自定义配置
# 自定义模型和参数
response = await openai.chat(
messages,
model="gpt-4",
temperature=0.5,
max_tokens=500
)
流式处理回调
async def handle_stream(content):
print(content, end="", flush=True)
response = await openai.chat(
messages,
stream=True,
stream_handler=handle_stream
)
API 参考
chat(messages, model=None, stream=False, stream_handler=None, **kwargs)
messages: List[Dict[str, str]] - 对话消息列表model: Optional[str] - 指定模型,默认为配置中的模型stream: bool - 是否使用流式响应stream_handler: Optional[Callable] - 流式响应的回调函数**kwargs: 其他 OpenAI API 参数- 返回: str - AI 响应内容
chat_stream(messages, model=None, **kwargs)
messages: List[Dict[str, str]] - 对话消息列表model: Optional[str] - 指定模型,默认为配置中的模型**kwargs: 其他 OpenAI API 参数- 返回: AsyncGenerator[str, None] - 流式响应生成器
配置说明
需要在项目的 config.toml 中配置OpenAI相关参数
参考链接
Metadata
Release files for ErisPulse-OpenAI 2.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| erispulse_openai-2.1.3.tar.gz | 3.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| erispulse_openai-2.1.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.9 kB
Release files / erispulse_openai-2.1.3.tar.gz
| Download URL | erispulse_openai-2.1.3.tar.gz |
|---|---|
| Size | 3.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ecbefe0caba80b661770523a237beac21815a0cd6b3ffc62030ef882d56274ca
|
|
BLAKE2b-256 checksum How to use checksums |
242a88e2c6719a7e4a9c4e571aa693aa74c3ea32d0f697011ea4fccb78969b11
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 17, 2025.
Transparency logRelease files / erispulse_openai-2.1.3-py3-none-any.whl
| Download URL | erispulse_openai-2.1.3-py3-none-any.whl |
|---|---|
| Size | 5.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
86254edf876cbdf2061bd477a3b5270f271dee17d6be1872621225accc5e9a0d
|
|
BLAKE2b-256 checksum How to use checksums |
dc957ee72f629065cd99c687d3465db6c9e65d57c0fa6de33772664d19634a9a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 17, 2025.
Transparency log