nbChatGPT 🚀
国内一键安装的 ChatGPT-5.4 Nano 中转服务 SDK
每天免费 0.3K tokens,零配置开箱即用!
✨ 特性
- ✅ 零配置 - 无需 API Key,无需代理设置,开箱即用
- ✅ 免费额度 - 每天 0.3K tokens 免费使用
- ✅ 流式输出 - 支持逐字输出,实时响应
- ✅ 对话管理 - Conversation 类自动维护上下文
- ✅ 命令行工具 - 支持终端直接使用
- ✅ 国内可用 - 专为国内网络环境优化
📦 安装
pip install nbchatgpt
🚀 快速开始
基础对话
python
from nbchatgpt import Client
client = Client()
response = client.chat("你好")
print(response.content)
流式输出
python
from nbchatgpt import Client
client = Client()
for chunk in client.chat_stream("讲个笑话"):
print(chunk.content, end="")
多轮对话
python
from nbchatgpt import Client
client = Client()
messages = [
{"role": "system", "content": "你是历史专家"},
{"role": "user", "content": "唐朝有哪些著名诗人?"}
]
response1 = client.chat_with_history(messages)
print(response1.content)
messages.append({"role": "assistant", "content": response1.content})
messages.append({"role": "user", "content": "李白呢?"})
response2 = client.chat_with_history(messages)
print(response2.content)
使用 Conversation 管理器
python
from nbchatgpt import Conversation
conv = Conversation(system_prompt="你是诗歌创作助手")
conv.chat("写一首关于春天的诗")
conv.chat("再写一首,风格悲伤一点") # 自动携带历史
print(conv.get_history())
查询今日使用情况
python
from nbchatgpt import Client
client = Client()
usage = client.get_usage()
print(f"今日已用: {usage['used_tokens']} tokens")
print(f"今日剩余: {usage['remaining_tokens']} tokens")
💻 命令行使用
安装后可直接在终端使用:
bash
# 单轮对话
nbchatgpt chat "你好"
# 流式输出
nbchatgpt chat "写一首诗" --stream
# 带系统提示词
nbchatgpt chat "你是谁" --system "你是历史专家"
# JSON 格式输出
nbchatgpt chat "你好" --json
# 查询使用情况
nbchatgpt usage
# 交互式对话
nbchatgpt conv
nbchatgpt conv --system "你是专家" --stream
🔧 自定义配置
python
from nbchatgpt import Client
# 自定义中转地址和用户 ID
client = Client(
base_url="http://your-proxy.com:8000",
user_id="your-custom-user-id",
api_key="your-api-key",
timeout=30
)
📚 API 文档
Client
方法 说明
chat(prompt, ...) 单轮对话
chat_with_history(messages, ...) 多轮对话
chat_stream(prompt, ...) 流式对话
chat_stream_with_history(messages, ...) 流式多轮对话
get_usage() 查询今日使用情况
Conversation
方法 说明
chat(prompt, ...) 对话(自动携带历史)
chat_stream(prompt, ...) 流式对话
clear() 清空历史
get_history() 获取历史记录
count_messages() 获取消息条数
⚠️ 错误处理
python
from nbchatgpt import Client
from nbchatgpt.exceptions import QuotaExceededError, NetworkError
client = Client()
try:
response = client.chat("你好")
except QuotaExceededError as e:
print(f"额度已用完: {e}")
except NetworkError as e:
print(f"网络错误: {e}")
📝 注意事项
每人每天免费 0.3K tokens(约 300 tokens)
额度按自然日重置(北京时间 00:00)
不支持自定义模型名称,仅支持 gpt-5.4-nano
🤝 贡献
欢迎提交 Issue 和 Pull Request!
Metadata
Release files for nbchatgpt 0.2.0
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 | Actions |
|---|---|---|---|---|
| nbchatgpt-0.2.0.tar.gz | 40.8 kB | Without provenance | Details for nbchatgpt-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| nbchatgpt-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for nbchatgpt-0.2.0-py3-none-any.whl |
Total release size: 81.2 kB
Release files / nbchatgpt-0.2.0.tar.gz
| Download URL | nbchatgpt-0.2.0.tar.gz |
|---|---|
| Size | 40.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c99ebe16021357e952a97bc58a2953bf22d9e8b9a4a97a5a0b96457932a7a65a
|
|
BLAKE2b-256 checksum How to use checksums |
a237afeaf49345e496b8b2b0ffe35707397b32203452289d273ea277ae644376
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.7
|
Release files / nbchatgpt-0.2.0-py3-none-any.whl
| Download URL | nbchatgpt-0.2.0-py3-none-any.whl |
|---|---|
| Size | 40.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2528e5ceb9c11f57470f42ba63a418a849bbb9dd9caf08a15345730846c43773
|
|
BLAKE2b-256 checksum How to use checksums |
0e8856cdbd047bfbaef0de72ab8515b85e2034606b8c77056ff5399be5bd1024
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.7
|
Security for nbchatgpt 0.2.0
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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.