多模型协作调度系统 - Multi-Model Collaboration Dispatch System
Project description
馃幖 Symphony 鏅鸿兘澶氭ā鍨嬪崗浣滅郴缁?## Symphony - Intelligent Multi-Model Collaboration System
馃殌 绠€浠?| Introduction
Symphony锛堜氦鍝嶏級 鈥?鍙蹭笂鏈€寮哄妯″瀷鍗忎綔璋冨害绯荤粺锛? Symphony 鈥?The Most Powerful Multi-Model Collaboration Dispatch System!
鉁?鏍稿績鐗规€?| Core Features
| 鐗规€?Feature | 璇存槑 Description |
|---|---|
| 馃 澶氭ā鍨嬪苟琛? | 鍚屾椂璋冪敤澶氫釜AI妯″瀷锛屽崗鍚屽伐浣? |
| 馃洝锔?鏅鸿兘瀹归敊 | 鑷姩鏁呴殰杞Щ锛岀‘淇濇湇鍔℃案缁? |
| 馃幆 浠诲姟璋冨害 | 鏅鸿兘鍒嗛厤浠诲姟锛屾彁鍗囨晥鐜? |
| 馃攧 妯″瀷鐑彃鎷? | 杩愯鏃跺姩鎬佸垏鎹㈡ā鍨? |
| 馃搳 璐熻浇鍧囪 | 鍚堢悊鍒嗛厤璁$畻璧勬簮 |
| 馃寪 璺ㄥ钩鍙版敮鎸? | Windows/Linux/Mac鍏ㄩ潰鍏煎 |
馃彈锔?杞欢鏋舵瀯 | Software Architecture
绯荤粺鏋舵瀯鍥?| System Architecture
鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹?鈹? Symphony Core 鈹?鈹溾攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹?鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹? 鈹? 浠诲姟璋冨害 鈹? 鈹? 妯″瀷绠$悊 鈹? 鈹? 瀹归敊绯荤粺 鈹? 鈹?鈹? 鈹?Task Schedule鈹? 鈹侻odel Manager 鈹? 鈹侳ault Tolerance鈹? 鈹?鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹溾攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹?鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹? 鈹? 宸ュ叿鍏变韩绯荤粺 鈹? 鈹? 璁板繂绯荤粺 鈹? 鈹? 鍗忎綔缂栨帓 鈹? 鈹?鈹? 鈹俆ool Sharing 鈹? 鈹侻emory System 鈹? 鈹侰ollaboration 鈹? 鈹?鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹溾攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹?鈹? Model Providers 鈹?鈹? 鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹?鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹?鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹?鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹?鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹?鈹屸攢鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹? 鈹傛櫤璋? 鈹?鈹傜伀灞? 鈹?鈹侼VIDIA鈹?鈹侻inimax鈹?鈹傞樋閲? 鈹?鈹傝吘璁? 鈹? 鈹?鈹? 鈹俍hipu 鈹?鈹侫rk 鈹?鈹? 鈹?鈹? 鈹?鈹侫li 鈹?鈹俆encent鈹? 鈹?鈹? 鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹? 鈹?鈹斺攢鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹€鈹?```
### 鏍稿績妯″潡 | Core Modules
| 妯″潡 Module | 鍔熻兘 Function | 琛屾暟 Lines |
|------------|--------------|------------|
| `symphony_core.py` | 缁熶竴璋冨害鏍稿績 | ~500 |
| `model_manager.py` | 妯″瀷绠$悊鍣?| ~400 |
| `fault_tolerance.py` | 瀹归敊绯荤粺 | ~300 |
| `skill_manager.py` | 鎶€鑳界鐞嗗櫒 | ~350 |
| `memory_system.py` | 璁板繂绯荤粺 | ~450 |
| `mcp_manager.py` | MCP宸ュ叿绠$悊 | ~280 |
| `tool_sharing.py` | 宸ュ叿鍏变韩 | ~250 |
---
## 馃摝 瀹夎璇存槑 | Installation
### 鐜瑕佹眰 | Requirements
| 瑕佹眰 Requirement | 鏈€浣庣増鏈?Minimum Version |
|-----------------|------------------------|
| Python | 3.9+ |
| pip | 20.0+ |
| 鍐呭瓨 RAM | 4GB+ |
| 纾佺洏绌洪棿 | 1GB+ |
### 瀹夎鏂瑰紡 | Installation Methods
#### 鏂瑰紡涓€锛歱ip瀹夎锛堟帹鑽愶級| Method 1: pip (Recommended)
```bash
# 瀹夎鏈€鏂扮増鏈?pip install symphony
# 瀹夎鎸囧畾鐗堟湰
pip install symphony==2.3.1
# 鍗囩骇鍒版渶鏂扮増鏈?pip install --upgrade symphony
鏂瑰紡浜岋細浠庢簮鐮佸畨瑁?| Method 2: From Source
# 鍏嬮殕浠撳簱
git clone https://github.com/songleiwww/symphony.git
# 杩涘叆鐩綍
cd symphony
# 瀹夎渚濊禆
pip install -r requirements.txt
# 閰嶇疆API
cp config.template.py config.py
# 缂栬緫 config.py 濉叆浣犵殑API瀵嗛挜
# 杩愯绀轰緥
python examples/demo.py
鏂瑰紡涓夛細Docker瀹夎 | Method 3: Docker
# 鎷夊彇闀滃儚
docker pull songleiwww/symphony:latest
# 杩愯瀹瑰櫒
docker run -it -v $(pwd)/config.py:/app/config.py songleiwww/symphony
閰嶇疆璇存槑 | Configuration
# config.py 閰嶇疆绀轰緥
API_KEY = "your_api_key_here"
BASE_URL = "https://ark.cn-beijing.volces.com/api/coding/v3"
# 涓绘ā鍨?PRIMARY_MODEL = "ark-code-latest"
# 澶囩敤妯″瀷鍒楄〃锛堟敮鎸?3涓ā鍨嬶紒锛?FALLBACK_MODELS = [
"deepseek-v3.2",
"doubao-seed-2.0-code",
"glm-4.7",
"kimi-k2.5",
"MiniMax-M2.5",
# ... 鏇村妯″瀷
]
馃幆 蹇€熷紑濮?| Quick Start
鍩虹鐢ㄦ硶 | Basic Usage
from symphony import SymphonyCore
# 鍒涘缓浜ゅ搷瀹炰緥
symphony = SymphonyCore()
# 鍙戣捣鍗忎綔浠诲姟
result = symphony.dispatch("甯垜瀹夋帓涓€涓?浜哄洟闃熻璁轰細")
# 浜彈澶氭ā鍨嬪崗浣滅殑鍔涢噺锛?print(result)
楂樼骇鐢ㄦ硶 | Advanced Usage
# 鑷畾涔夋ā鍨嬮厤缃?symphony = SymphonyCore(
primary_model="ark-code-latest",
fallback_models=["deepseek-v3.2", "glm-4.7"],
timeout=60,
max_retries=3
)
# 骞惰璋冪敤澶氫釜妯″瀷
results = symphony.parallel_dispatch([
"鍒嗘瀽杩欐浠g爜鐨勬€ц兘闂",
"浼樺寲杩欎釜绠楁硶鐨勫鏉傚害",
"娣诲姞鍗曞厓娴嬭瘯"
])
# 鑾峰彇妯″瀷鎶曠エ缁撴灉
vote_result = symphony.vote("Python濂借繕鏄疛ava濂?")
馃専 鐗规妧 | Special Features
1. 馃幁 澶氭ā鍨嬩汉鏍煎垏鎹?| Multi-Personality Switching
# 6绉嶄汉鏍兼ā鍨嬶紝浠讳綘鍒囨崲
personalities = {
"鏋楁€濊繙": "杈撳叆鐞嗚В涓撳",
"闄堢編鐞?: "瑙嗚璁捐鎬荤洃",
"鐜嬫旦鐒?: "浜や簰宸ョ▼甯?,
"鍒樺績鎬?: "鍐呭绛栧垝甯?,
"寮犳槑杩?: "璐ㄩ噺淇濊瘉涓荤",
"璧垫晱": "椤圭洰鍗忚皟鍛?
}
2. 馃 鏅鸿兘璁板繂绯荤粺 | Intelligent Memory System
- 鐭湡璁板繂锛氭渶杩戝璇濅笂涓嬫枃
- 闀挎湡璁板繂锛氶噸瑕佷俊鎭寔涔呭寲
- 宸ヤ綔璁板繂锛氬綋鍓嶄换鍔$浉鍏?- 鎯呮櫙璁板繂锛氱壒瀹氫簨浠跺拰鏃堕棿
3. 馃攧 鑷姩鏁呴殰杞Щ | Automatic Failover
# 涓绘ā鍨嬪け璐ヨ嚜鍔ㄥ垏鎹?try:
result = symphony.dispatch(task)
except PrimaryModelError:
# 鑷姩鍒囨崲鍒板鐢ㄦā鍨? result = symphony.dispatch(task, use_fallback=True)
4. 馃搳 瀹炴椂鐩戞帶 | Real-time Monitoring
# 鑾峰彇绯荤粺鐘舵€?status = symphony.get_status()
print(f"鍦ㄧ嚎妯″瀷: {status['active_models']}")
print(f"鎴愬姛璋冪敤: {status['successful_calls']}")
print(f"骞冲潎鍝嶅簲鏃堕棿: {status['avg_response_time']}ms")
5. 馃帹 澧炲己UI杈撳嚭 | Enhanced UI Output
# 缇庤鐨勬秷鎭緭鍑?symphony.display_header("浜ゅ搷 v2.3.0")
symphony.display_success("浠诲姟瀹屾垚锛?)
symphony.display_table(data)
symphony.display_progress(75)
6. 馃攲 鎻掍欢绯荤粺 | Plugin System
# 鍔犺浇鑷畾涔夋彃浠?symphony.load_plugin("my_custom_plugin")
# 鎻掍欢甯傚満
plugins = symphony.list_plugins()
# 鍙敤鎻掍欢锛氱炕璇戙€佺粯鍥俱€佽闊宠瘑鍒?..
馃 鍙備笌璐$尞 | Contributing
娆㈣繋璐$尞 | Welcome Contributions
鎴戜滑娆㈣繋浠讳綍褰㈠紡鐨勮础鐚紒
We welcome contributions in any form!
璐$尞鏂瑰紡 | How to Contribute
1. 鎶ュ憡Bug | Report Bugs
# 鍦?GitHub Issues 涓姤鍛?# 璇峰寘鍚細
# - 澶嶇幇姝ラ
# - 棰勬湡琛屼负
# - 瀹為檯琛屼负
# - 鐜淇℃伅
2. 鎻愬嚭鏂板姛鑳?| Suggest Features
# 鍦?GitHub Issues 涓彁浜ょ壒鎬ц姹?# 璇疯鏄庯細
# - 鍔熻兘鎻忚堪
# - 浣跨敤鍦烘櫙
# - 瀹炵幇鎬濊矾
3. 鎻愪氦浠g爜 | Submit Code
# Fork 浠撳簱
git clone https://github.com/songleiwww/symphony.git
# 鍒涘缓鍒嗘敮
git checkout -b feature/your-feature
# 寮€鍙戝苟娴嬭瘯
python -m pytest tests/
# 鎻愪氦 Pull Request
git push origin feature/your-feature
寮€鍙戣鑼?| Development Standards
| 瑙勮寖 Standard | 瑕佹眰 Requirement |
|---|---|
| 浠g爜椋庢牸 | PEP 8 |
| 娉ㄩ噴 | 涓嫳鍙岃 |
| 娴嬭瘯 | 瑕嗙洊鐜?> 80% |
| 鏂囨。 | 鍚屾鏇存柊 |
璐$尞鑰呭悕鍗?| Contributors
| 璐$尞鑰?Contributor | 瑙掕壊 Role | 璐$尞 |
|---|---|---|
| 閫犳ⅵ鑰?& 浜や氦 | 鍒涘浜? | 鏍稿績鏋舵瀯 |
| 鏋楁€濊繙 | 杈撳叆鐞嗚В | 绠楁硶浼樺寲 |
| 闄堢編鐞? | 瑙嗚璁捐 | UI澧炲己 |
| 鐜嬫旦鐒? | 浜や簰璁捐 | 鎻掍欢绯荤粺 |
馃搳 鏀寔鐨勬ā鍨?| Supported Models
| 鎻愪緵鍟?Provider | 妯″瀷鏁伴噺 | 浠h〃妯″瀷 |
|---|---|---|
| 鏅鸿氨 (Zhipu) | 6涓? | GLM-4.7 |
| 鐏北寮曟搸 (Ark) | 5涓? | ark-code-latest |
| NVIDIA | 7涓? | Nemotron Ultra |
| ModelScope | 10涓? | Qwen绯诲垪 |
| MiniMax | 1涓? | M2.5 |
| 鎬昏 | 23+ | 鈥? |
馃摓 鑱旂郴鎴戜滑 | Contact Us
| 娓犻亾 Channel | 鍦板潃 Link |
|---|---|
| 馃摟 閭 | songlei_www@qq.com |
| 馃悰 闂鍙嶉 | GitHub Issues |
| 馃挰 浜ゆ祦缇? | 娆㈣繋鍔犲叆璁ㄨ |
| 馃摉 鏂囨。 | ReadTheDocs |
馃搫 璁稿彲璇?| License
MIT License 鈥?寮€婧愬厤璐瑰晢鐢紒
馃専 绔嬪嵆浣撻獙 | Get Started Now!
pip install symphony
璁〢I鍗忎綔鍙樺緱濡傛绠€鍗曪紒
Make AI Collaboration So Simple!
猸?鏀寔鎴戜滑 | Support Us
濡傛灉浣犺寰桽ymphony鏈夊府鍔╋紝璇凤細
- 猸?缁欎釜 Star
- 馃摙 鍒嗕韩缁欐湅鍙?- 馃摑 鍐欎竴绡囧崥瀹?- 馃挕 鎻愬嚭浣犵殑鎯虫硶
馃殌 鏅洪煹浜ゅ搷锛屽叡鍒涘崕绔?| Symphony of Intelligence, Creating Masterpieces Together
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file symphony_ai-2.4.0.tar.gz.
File metadata
- Download URL: symphony_ai-2.4.0.tar.gz
- Upload date:
- Size: 8.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4f8434410144982cc8de982bc5c25bf52fbee919d28516e292d3851e01f6e4e6
|
|
| MD5 |
adb7ab71afbd09b3c540e2d18100e149
|
|
| BLAKE2b-256 |
5e50132cf58ddd29b121817d536a4b38c0acd07288fa2f60a1f4c4f24a5bebc5
|
File details
Details for the file symphony_ai-2.4.0-py3-none-any.whl.
File metadata
- Download URL: symphony_ai-2.4.0-py3-none-any.whl
- Upload date:
- Size: 7.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1486e029b7824b1fb3189d69cc4a33af16eab4cbeb9e4bdc93447bd6aeef3802
|
|
| MD5 |
1301095230962c8df13d099005eccfc8
|
|
| BLAKE2b-256 |
7bd9a7cb0501902385d630fb6c6f56317de6361e9d35a5770f6c49912a4b9362
|