strands-agents/sdk-python.git:

代码拉取完成,页面将自动刷新

richgiteeai

Watch

不关注关注所有动态仅关注版本发行动态关注但不提醒动态

1 Star 0 Fork 0

杨干/sdk-python

代码 Issues 0 Pull Requests 0 Wiki 统计流水线

服务

加入 Gitee

与超过 1400万开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)

免费加入

已有帐号? 立即登录

文件

新建文件新建 Diagram 文件

main

分支 (12)

标签 (35)

管理

main

dependabot/pip/pre-commit-gte-3.2.0-and-lt-4.6.0

dependabot/github_actions/actions/checkout-6

dependabot/pip/openai-gte-1.68.0-and-lt-2.9.0

dependabot/pip/dev-dependencies-85b6f7c93c

dependabot/pip/pytest-asyncio-gte-1.0.0-and-lt-1.4.0

dependabot/github_actions/actions/upload-artifact-5

dependabot/github_actions/actions/download-artifact-6

dependabot/pip/ruff-gte-0.13.0-and-lt-0.15.0

v0.2.1

v0.1.x

v0.1.5

v1.18.0

v1.17.0

v1.16.0

v1.15.0

v1.14.0

v1.13.0

v1.12.0

v1.11.0

v1.10.0

v1.9.1

v1.9.0

v1.8.0

v1.7.1

v1.7.0

v1.6.0

v1.5.0

v1.4.0

v1.3.0

v1.2.0

v1.1.0

克隆/下载

HTTPS SSH SVN SVN+SSH 下载ZIP

提示

下载代码请复制以下命令到终端执行

为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName 
git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥中

在 Gitee 上使用 SVN,请访问使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议配置并使用私人令牌替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

新建文件新建 Diagram 文件

分支 12

标签 35

贡献代码

同步代码

创建 Pull Request

了解更多

对比差异通过 Pull Request 同步

同步更新到分支

通过 Pull Request 同步

将会在向当前分支创建一个 Pull
Request,合入后将完成同步

Your Name siliconflow exzample e038042

416 次提交

File empty ...

README.md

ollama_local_example.py

siliconflow_agent_example.py

siliconflow_example.py

README

# Examples — Silicon Flow and local Ollama

This folder contains quick, runnable examples showing how to use two model backends with the SDK:

- `siliconflow_example.py` — Demonstrates calling Silicon Flow's OpenAI-compatible endpoint using `OpenAIModel`.
- `siliconflow_example.py` — Demonstrates calling Silicon Flow's OpenAI-compatible endpoint using `OpenAIModel`.
- `siliconflow_agent_example.py` — Demonstrates building an `Agent` using Silicon Flow as the model provider (sync + async examples).
- `ollama_local_example.py` — Demonstrates calling a local Ollama server using `OllamaModel`.

Important: do not hard-code API keys in the repository. Use environment variables instead.

1) Silicon Flow (uses OpenAI-compatible interface)

Prerequisites:
- Python 3.10+
- Install the OpenAI extra: pip install -e .[openai]

Run (PowerShell):

```powershell
$Env:SILICONFLOW_API_KEY = 'YOUR_SILICON_FLOW_API_KEY' # set in session only
python -m examples.siliconflow_example
```

Notes:
- The example sets OpenAI client args with base_url=https://api.siliconflow.cn/v1 so the built-in
 `OpenAIModel` in the SDK will call Silicon Flow.
- Replace the default `model_id` in the example if your account uses a different model.

2) Local Ollama

Prerequisites:
- Ollama running locally (default host http://localhost:11434). For instructions: https://ollama.com/
- Install the Ollama extra: pip install -e .[ollama]

Run (PowerShell):

```powershell
# If you are using a non-default host or non-default model id:
#$Env:OLLAMA_HOST = 'http://localhost:11434'
#$Env:OLLAMA_MODEL_ID = 'llama3.3:70b'
python -m examples.ollama_local_example
```

Verification / Troubleshooting
- If the example errors connecting to the model, verify your network or the local server is running.
- Do not commit credentials or secrets into the repo. Use the environment to pass API keys.

If you want, run the full test suite (may be heavy):

```powershell
# Optional, recommended for contributors
pip install -e .[dev]
hatch test
```