OneFineStarstuff.github.io/Description.json at main · OneFineStarstuff/OneFineStarstuff.github.io · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
{
  "pipeline": {
    "name": "Enhanced AGI Pipeline",
    "description": "A multimodal pipeline for NLP, CV, and Speech Processing.",
    "modules": [
      {
        "name": "NLP Module",
        "model": "google/flan-t5-small",
        "description": "Generates responses based on text prompts.",
        "inputs": ["prompt: string"],
        "outputs": ["response: string"]
      },
      {
        "name": "CV Module",
        "model": "YOLOv5su",
        "description": "Performs object detection on images.",
        "inputs": ["image: Image"],
        "outputs": ["detections: JSON"]
      },
      {
        "name": "Speech Processor",
        "components": [
          {
            "name": "Speech-to-Text",
            "model": "Whisper Base",
            "description": "Converts audio input to text.",
            "inputs": ["audio_file: file"],
            "outputs": ["text: string"]
          },
          {
            "name": "Text-to-Speech",
            "engine": "pyttsx3",
            "description": "Synthesizes text into speech.",
            "inputs": ["text: string"],
            "outputs": ["audio: playback"]
          }
        ]
      }
    ]
  },
  "endpoints": [
    {
      "path": "/process-nlp/",
      "method": "POST",
      "description": "Processes NLP tasks.",
      "input_model": {
        "type": "JSON",
        "schema": {
          "text": "string"
        }
      },
      "output_model": {
        "type": "JSON",
        "schema": {
          "response": "string"
        }
      }
    },
    {
      "path": "/process-cv-detection/",
      "method": "POST",
      "description": "Processes image object detection tasks.",
      "input_model": {
        "type": "file",
        "accepted_formats": ["jpg", "png"]
      },
      "output_model": {
        "type": "JSON",
        "schema": {
          "detections": "JSON"
        }
      }
    },
    {
      "path": "/speech-to-text/",
      "method": "POST",
      "description": "Converts speech to text.",
      "input_model": {
        "type": "file",
        "accepted_formats": ["wav", "mp3", "m4a"]
      },
      "output_model": {
        "type": "JSON",
        "schema": {
          "response": "string"
        }
      }
    },
    {
      "path": "/text-to-speech/",
      "method": "POST",
      "description": "Synthesizes text to speech.",
      "input_model": {
        "type": "JSON",
        "schema": {
          "text": "string"
        }
      },
      "output_model": {
        "type": "JSON",
        "schema": {
          "response": "string"
        }
      }
    }
  ],
  "authentication": {
    "type": "OAuth2",
    "token_url": "token",
    "environment_variable": "SECURE_TOKEN",
    "description": "Validates requests with a secure token."
  },
  "logging": {
    "level": "DEBUG",
    "rotation": "1 MB",
    "log_file": "pipeline_{time}.log"
  },
  "deployment": {
    "framework": "FastAPI",
    "host": "0.0.0.0",
    "port": 8000,
    "workers": 4
  }
}