UntilDot commited on
Commit
a997fd6
·
verified ·
1 Parent(s): acbdb83

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -2
README.md CHANGED
@@ -1,10 +1,112 @@
1
  ---
2
  title: Flask
3
- emoji: 📊
4
  colorFrom: purple
5
  colorTo: purple
6
  sdk: docker
7
  pinned: false
8
  ---
9
 
10
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: Flask
3
+ emoji: 🤖
4
  colorFrom: purple
5
  colorTo: purple
6
  sdk: docker
7
  pinned: false
8
  ---
9
 
10
+ # MoA Chat
11
+
12
+ MoA Chat is a multi-agent AI chat platform where several LLMs respond in parallel, and an aggregator model combines their outputs into a single response.
13
+
14
+ ## Features
15
+
16
+ - Python 3 backend using Flask
17
+ - Frontend with HTML, JavaScript, TailwindCSS (optional)
18
+ - Simultaneous queries to multiple AI models
19
+ - Aggregator LLM refines the combined output
20
+ - Supports light and dark themes
21
+ - Switch documentation language between English and Spanish
22
+ - Secret API keys management
23
+ - Hugging Face Spaces compatibility
24
+ - Docker support
25
+ - Free models through OpenRouter and others
26
+
27
+ ## Requirements
28
+
29
+ - Python 3.11+
30
+ - pip
31
+ - API keys for model providers
32
+
33
+ ## Installation
34
+
35
+ 1. Clone the repository:
36
+
37
+ ```bash
38
+ git clone https://huggingface.co/spaces/UntilDot/Flask
39
+ cd Flask
40
+ ```
41
+
42
+ 2. Create a `.env` file:
43
+
44
+ ```env
45
+ OPENROUTER_API_KEY=your-openrouter-key
46
+ TOGETHER_API_KEY=your-together-key
47
+ GROK_API_KEY=your-grok-key
48
+ GROQ_API_KEY=your-groq-key
49
+ ```
50
+
51
+ 3. Install dependencies:
52
+
53
+ ```bash
54
+ pip install -r requirements.txt
55
+ ```
56
+
57
+ 4. Run the application:
58
+
59
+ ```bash
60
+ python app.py
61
+ ```
62
+
63
+ The server will be available at `http://localhost:7860`.
64
+
65
+ ## Adding New Models
66
+
67
+ Edit the file `llm/model_config.json` to register new models and providers.
68
+
69
+ Example:
70
+
71
+ ```json
72
+ {
73
+ "providers": {
74
+ "openrouter": {
75
+ "url": "https://openrouter.ai/api/v1/chat/completions",
76
+ "key_env": "OPENROUTER_API_KEY"
77
+ }
78
+ },
79
+ "models": {
80
+ "deepseek/deepseek-chat-v3-0324:free": "openrouter"
81
+ }
82
+ }
83
+ ```
84
+
85
+ ## Docker Support
86
+
87
+ To build and run using Docker:
88
+
89
+ Create the following `Dockerfile`:
90
+
91
+ ```Dockerfile
92
+ FROM python:3.11-slim
93
+ WORKDIR /app
94
+ COPY requirements.txt ./
95
+ RUN pip install --no-cache-dir -r requirements.txt
96
+ COPY . .
97
+ EXPOSE 7860
98
+ CMD ["python", "app.py"]
99
+ ```
100
+
101
+ Then:
102
+
103
+ ```bash
104
+ docker build -t moa-chat .
105
+ docker run -d -p 7860:7860 --env-file .env moa-chat
106
+ ```
107
+
108
+ Environment variables or an `.env` file are required for API keys.
109
+
110
+ ## License
111
+
112
+ Licensed under the Apache License 2.0.