YZ-OpenAI
有赞 LLM 统一调用库 - 支持 Chat 对话、Podcast TTS、ASR 语音识别
安装
pip install yz-openai
使用示例
1. Chat 对话(同步调用)
from yz_openai import YzOpenAI
# 使用上下文管理器
with YzOpenAI(provider="volcengine", api_key="your-api-key") as client:
# 非流式调用
result = client.chat.completion(
model="doubao-pro-32k",
messages=[{"role": "user", "content": "你好"}]
)
print(result["message"]["content"])
# 流式调用
for chunk in client.chat.completion(
model="doubao-pro-32k",
messages=[{"role": "user", "content": "写一篇文章"}],
stream=True
):
print(chunk["message"]["content"], end="", flush=True)
# 或手动管理客户端
client = YzOpenAI(provider="volcengine", api_key="your-api-key")
result = client.chat.completion(
model="doubao-pro-32k",
messages=[{"role": "user", "content": "你好"}]
)
print(result["message"]["content"])
client.close()
2. Podcast TTS - 生成播客
import asyncio
from yz_openai import YzOpenAI
async def main():
client = YzOpenAI(
provider="volcengine",
app_id="your-app-id",
access_key="your-access-key"
)
# 根据文档URL生成
result = await client.podcast.generate({
"action": 0,
"input_url": "https://example.com/document.pdf",
"speakers": [
"zh_male_dayixiansheng_v2_saturn_bigtts",
"zh_female_mizaitongxue_v2_saturn_bigtts"
],
"audio_format": "mp3"
})
# 根据文本生成
result = await client.podcast.generate({
"action": 0,
"input_text": "人工智能正在改变我们的生活...",
"speakers": [
"zh_male_dayixiansheng_v2_saturn_bigtts",
"zh_female_mizaitongxue_v2_saturn_bigtts"
]
})
# 根据对话文本生成
result = await client.podcast.generate({
"action": 3,
"nlp_texts": [
{"speaker": "zh_male_dayixiansheng_v2_saturn_bigtts", "text": "你好"},
{"speaker": "zh_female_mizaitongxue_v2_saturn_bigtts", "text": "你好"}
]
})
# 保存音频
with open("podcast.mp3", "wb") as f:
f.write(result.audio_data)
client.close()
asyncio.run(main())
3. ASR 语音识别
import asyncio
from yz_openai import YzOpenAI
async def main():
client = YzOpenAI(
provider="volcengine",
app_id="your-app-id",
access_key="your-access-key"
)
# 使用URL
result = await client.asr.transcribe({
"file_url": "https://example.com/audio.mp3"
})
# 使用本地文件
result = await client.asr.transcribe({
"file_path": "/path/to/audio.mp3",
"enable_itn": True,
"enable_punc": True
})
print(f"识别文本: {result.text}")
client.close()
asyncio.run(main())
异常处理
from yz_openai import YzOpenAI
from yz_openai.base.exceptions import YzOpenAIException, YzOpenAIErrorCode
# Chat 异常处理(同步)
try:
client = YzOpenAI(provider="volcengine", api_key="your-api-key")
result = client.chat.completion(
model="doubao-pro-32k",
messages=[{"role": "user", "content": "你好"}]
)
except YzOpenAIException as e:
print(f"错误码: {e.code}")
print(f"错误信息: {e.message}")
finally:
client.close()
# ASR/TTS/Podcast 异常处理(异步)
import asyncio
async def main():
try:
client = YzOpenAI(
provider="volcengine",
app_id="your-app-id",
access_key="your-access-key"
)
result = await client.asr.transcribe({"file_url": "..."})
except YzOpenAIException as e:
print(f"错误码: {e.code}")
print(f"错误信息: {e.message}")
finally:
client.close()
asyncio.run(main())
YZ-OpenAI - 让 LLM 调用更简单 🚀
Metadata
Release files for yz-openai 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| yz_openai-0.1.5.tar.gz | 35.1 kB | Without provenance | Details for yz_openai-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| yz_openai-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for yz_openai-0.1.5-py3-none-any.whl |
Total release size: 73.2 kB
Release files / yz_openai-0.1.5.tar.gz
| Download URL | yz_openai-0.1.5.tar.gz |
|---|---|
| Size | 35.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
15847044257830788d6a8dfeabadaea41e16b633477b902926cee80ad03392c6
|
|
BLAKE2b-256 checksum How to use checksums |
613720c1224663aad42a20c91cbde74eb64b2909870b0394f1031a4eee024d74
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Release files / yz_openai-0.1.5-py3-none-any.whl
| Download URL | yz_openai-0.1.5-py3-none-any.whl |
|---|---|
| Size | 38.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0c7c8710b3e1cbce70296b14309856efccb3ac2e8e73ceca6b67e7c89d177829
|
|
BLAKE2b-256 checksum How to use checksums |
d6761e8cd8aa0240fd1e5c09ddc3c0667f2c9aa4a60abdef58bfd257b4a132f6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.14
|
Security for yz-openai 0.1.5
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.