novusai — NovusAI 推理服务 Python SDK
NovusAI 网络的官方 Python 客户端。零第三方依赖(纯标准库),走 NovusAI 自有协议(/api/chat)。
安装
pip install novusai
本地源码安装:pip install .(项目根目录)。
快速开始
- 打开 https://www.t-cab.net →「新建 ID」→ 生成 API key(
nvk-前缀,永不过期可撤销); - 你的节点/程序贡献推理与容量获得贡献值(CP),API 调用按实耗扣减 CP(输入 0.01 / 输出 0.04 CP/百 token)。
from novusai import Client
client = Client(api_key="nvk-...") # 或环境变量 NOVUSAI_API_KEY
result = client.chat("帮我总结这段日志")
print(result["response"])
带进度回调(模型加载/推理阶段):
result = client.chat(
"跨节点推理测试",
on_progress=lambda task: print(task["stage_label"]),
)
非阻塞 + 手动轮询:
submitted = client.chat_async("你好")
task = client.poll(submitted["task_id"]) # status: processing/done/failed
API
| 方法 | 说明 |
|---|---|
Client(api_key=None, base_url="https://www.t-cab.net", timeout=30, task_timeout=360) |
缺省从 NOVUSAI_API_KEY 读 key |
chat(prompt, mode="default", on_progress=None) -> dict |
阻塞直到完成,返回 {success, response, ...} |
chat_async(prompt, mode="default") -> dict |
返回 {task_id, status, stage, poll_url} |
poll(task_id) -> dict |
轮询任务态;done 携带 result |
usage(registration_id, days=7, include_ids=None) -> dict |
用量/消耗聚合(注册 ID 见页面贡献区;include_ids 支持本人历史 ID 聚合) |
错误
| 异常 | HTTP | 含义 |
|---|---|---|
AuthenticationError |
401 | key 无效或已撤销 |
InsufficientBalance |
402 | 贡献值(CP)≤0,预检拒绝——先让节点上线积累贡献 |
RateLimited |
429 | 限速(60s 窗口 6 次),retry_after_s 给出等待秒数 |
TaskFailed |
— | 任务 failed 或推理产出为空 |
所有异常继承 NovusAIError(status_code / payload 属性保留服务端原始响应)。
Metadata
Release files for novusai 0.1.0
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 | |
|---|---|---|---|---|
| novusai-0.1.0.tar.gz | 106.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| novusai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 112.3 kB
Release files / novusai-0.1.0.tar.gz
| Download URL | novusai-0.1.0.tar.gz |
|---|---|
| Size | 106.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
14fb9cbb38ae0392b5af23056880f5fe66509d78933a861414d42f20434bfa3d
|
|
BLAKE2b-256 checksum How to use checksums |
e681c97158f13850c00a99e2392aa4e9f63b58303ea0082aa62c9e0b469e02c4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / novusai-0.1.0-py3-none-any.whl
| Download URL | novusai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 6.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
686a3ccf69dc48f82b5e573ea71c82b715ea3c71b24d7105b5fac01aabf9ebad
|
|
BLAKE2b-256 checksum How to use checksums |
0a85b413ce85e2d2a867ec199423ac9d9a818751d575e96990c33ef18f4f5690
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Security for novusai 0.1.0
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.