File size: 3,464 Bytes
6e73cd3
793ea24
 
6e73cd3
793ea24
6e73cd3
793ea24
6e73cd3
 
 
 
793ea24
6e73cd3
 
 
 
 
 
793ea24
6e73cd3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
793ea24
 
6e73cd3
 
 
 
 
 
 
 
 
793ea24
dd96d5f
793ea24
 
 
 
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
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
from Perceptrix.engine import perceptrix, robotix, identify_objects_from_text, search_keyword
from CircumSpect import answer_question, find_object_description, locate_object
from flask import Flask, request, jsonify
import numpy as np
import threading
import whisper
import cv2
import os

model = whisper.load_model("base")


def transcribe(audio):
    result = model.transcribe(audio)
    transcription = result['text']
    print(transcription)
    return transcription


app = Flask(__name__)


@app.route('/locate_object', methods=['POST'])
def display_image():
    try:
        image_data = request.json['image_data']
        prompt = request.json['prompt']

        image_data = np.array(image_data, dtype=np.uint8)
        image = cv2.imdecode(image_data, cv2.IMREAD_COLOR)

        cv2.imwrite('API.jpg', image)
        answer, annotated_image = locate_object(prompt, "API.jpg")

        return jsonify({'message': answer, 'annotated_image': annotated_image})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/vqa', methods=['POST'])
def display_image():
    try:
        image_data = request.json['image_data']
        prompt = request.json['prompt']

        image_data = np.array(image_data, dtype=np.uint8)
        image = cv2.imdecode(image_data, cv2.IMREAD_COLOR)

        cv2.imwrite('API.jpg', image)
        answer = answer_question(prompt, "API.jpg")

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/object_description', methods=['POST'])
def display_image():
    try:
        image_data = request.json['image_data']

        image_data = np.array(image_data, dtype=np.uint8)
        image = cv2.imdecode(image_data, cv2.IMREAD_COLOR)

        cv2.imwrite('API.jpg', image)
        answer = find_object_description("API.jpg")

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/perceptrix', methods=['POST'])
def display_image():
    try:
        prompt = request.json['prompt']

        answer = perceptrix(prompt)

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/robotix', methods=['POST'])
def display_image():
    try:
        prompt = request.json['prompt']

        answer = robotix(prompt)

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/search_keyword', methods=['POST'])
def display_image():
    try:
        prompt = request.json['prompt']

        answer = search_keyword(prompt)

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/identify_objects_from_text', methods=['POST'])
def display_image():
    try:
        prompt = request.json['prompt']

        answer = identify_objects_from_text(prompt)

        return jsonify({'message': answer})

    except Exception as e:
        return jsonify({'error': str(e)})


@app.route('/transcribe', methods=['POST'])
def upload_audio():
    audio_file = request.files['audio']

    filename = os.path.join("database", audio_file.filename)
    audio_file.save(filename)
    return jsonify({'message': transcribe(filename)})


def run_app():
    app.run(port=7777)

if __name__ == "__main__":
    runner = threading.Thread(target=run_app)
    runner.start()