File size: 9,937 Bytes
a36de18
 
1706d7c
6b1796d
1706d7c
a36de18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1706d7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a36de18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1706d7c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
from langchain_core.tools import tool
from tools.image import decode_image, encode_image, save_image
from typing import Dict, Any, List, Optional
import numpy as np
from PIL import Image, ImageDraw, ImageFont, ImageEnhance, ImageFilter

@tool
def analyze_image(image_base64: str) -> Dict[str, Any]:
    """
    Analyze basic properties of an image (size, mode, color analysis, thumbnail preview).
    Args:
        image_base64 (str): Base64 encoded image string
    Returns:
        Dictionary with analysis result
    """
    try:
        img = decode_image(image_base64)
        width, height = img.size
        mode = img.mode

        if mode in ("RGB", "RGBA"):
            arr = np.array(img)
            avg_colors = arr.mean(axis=(0, 1))
            dominant = ["Red", "Green", "Blue"][np.argmax(avg_colors[:3])]
            brightness = avg_colors.mean()
            color_analysis = {
                "average_rgb": avg_colors.tolist(),
                "brightness": brightness,
                "dominant_color": dominant,
            }
        else:
            color_analysis = {"note": f"No color analysis for mode {mode}"}

        thumbnail = img.copy()
        thumbnail.thumbnail((100, 100))
        thumb_path = save_image(thumbnail, "thumbnails")
        thumbnail_base64 = encode_image(thumb_path)

        return {
            "dimensions": (width, height),
            "mode": mode,
            "color_analysis": color_analysis,
            "thumbnail": thumbnail_base64,
        }
    except Exception as e:
        return {"error": str(e)}

@tool
def transform_image(
    image_base64: str, operation: str, params: Optional[Dict[str, Any]] = None
) -> Dict[str, Any]:
    """
    Apply transformations: resize, rotate, crop, flip, brightness, contrast, blur, sharpen, grayscale.
    Args:
        image_base64 (str): Base64 encoded input image
        operation (str): Transformation operation
        params (Dict[str, Any], optional): Parameters for the operation
    Returns:
        Dictionary with transformed image (base64)
    """
    try:
        img = decode_image(image_base64)
        params = params or {}

        if operation == "resize":
            img = img.resize(
                (
                    params.get("width", img.width // 2),
                    params.get("height", img.height // 2),
                )
            )
        elif operation == "rotate":
            img = img.rotate(params.get("angle", 90), expand=True)
        elif operation == "crop":
            img = img.crop(
                (
                    params.get("left", 0),
                    params.get("top", 0),
                    params.get("right", img.width),
                    params.get("bottom", img.height),
                )
            )
        elif operation == "flip":
            if params.get("direction", "horizontal") == "horizontal":
                img = img.transpose(Image.FLIP_LEFT_RIGHT)
            else:
                img = img.transpose(Image.FLIP_TOP_BOTTOM)
        elif operation == "adjust_brightness":
            img = ImageEnhance.Brightness(img).enhance(params.get("factor", 1.5))
        elif operation == "adjust_contrast":
            img = ImageEnhance.Contrast(img).enhance(params.get("factor", 1.5))
        elif operation == "blur":
            img = img.filter(ImageFilter.GaussianBlur(params.get("radius", 2)))
        elif operation == "sharpen":
            img = img.filter(ImageFilter.SHARPEN)
        elif operation == "grayscale":
            img = img.convert("L")
        else:
            return {"error": f"Unknown operation: {operation}"}

        result_path = save_image(img)
        result_base64 = encode_image(result_path)
        return {"transformed_image": result_base64}

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


@tool
def draw_on_image(
    image_base64: str, drawing_type: str, params: Dict[str, Any]
) -> Dict[str, Any]:
    """
    Draw shapes (rectangle, circle, line) or text onto an image.
    Args:
        image_base64 (str): Base64 encoded input image
        drawing_type (str): Drawing type
        params (Dict[str, Any]): Drawing parameters
    Returns:
        Dictionary with result image (base64)
    """
    try:
        img = decode_image(image_base64)
        draw = ImageDraw.Draw(img)
        color = params.get("color", "red")

        if drawing_type == "rectangle":
            draw.rectangle(
                [params["left"], params["top"], params["right"], params["bottom"]],
                outline=color,
                width=params.get("width", 2),
            )
        elif drawing_type == "circle":
            x, y, r = params["x"], params["y"], params["radius"]
            draw.ellipse(
                (x - r, y - r, x + r, y + r),
                outline=color,
                width=params.get("width", 2),
            )
        elif drawing_type == "line":
            draw.line(
                (
                    params["start_x"],
                    params["start_y"],
                    params["end_x"],
                    params["end_y"],
                ),
                fill=color,
                width=params.get("width", 2),
            )
        elif drawing_type == "text":
            font_size = params.get("font_size", 20)
            try:
                font = ImageFont.truetype("arial.ttf", font_size)
            except IOError:
                font = ImageFont.load_default()
            draw.text(
                (params["x"], params["y"]),
                params.get("text", "Text"),
                fill=color,
                font=font,
            )
        else:
            return {"error": f"Unknown drawing type: {drawing_type}"}

        result_path = save_image(img)
        result_base64 = encode_image(result_path)
        return {"result_image": result_base64}

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


@tool
def generate_simple_image(
    image_type: str,
    width: int = 500,
    height: int = 500,
    params: Optional[Dict[str, Any]] = None,
) -> Dict[str, Any]:
    """
    Generate a simple image (gradient, noise, pattern, chart).
    Args:
        image_type (str): Type of image
        width (int), height (int)
        params (Dict[str, Any], optional): Specific parameters
    Returns:
        Dictionary with generated image (base64)
    """
    try:
        params = params or {}

        if image_type == "gradient":
            direction = params.get("direction", "horizontal")
            start_color = params.get("start_color", (255, 0, 0))
            end_color = params.get("end_color", (0, 0, 255))

            img = Image.new("RGB", (width, height))
            draw = ImageDraw.Draw(img)

            if direction == "horizontal":
                for x in range(width):
                    r = int(
                        start_color[0] + (end_color[0] - start_color[0]) * x / width
                    )
                    g = int(
                        start_color[1] + (end_color[1] - start_color[1]) * x / width
                    )
                    b = int(
                        start_color[2] + (end_color[2] - start_color[2]) * x / width
                    )
                    draw.line([(x, 0), (x, height)], fill=(r, g, b))
            else:
                for y in range(height):
                    r = int(
                        start_color[0] + (end_color[0] - start_color[0]) * y / height
                    )
                    g = int(
                        start_color[1] + (end_color[1] - start_color[1]) * y / height
                    )
                    b = int(
                        start_color[2] + (end_color[2] - start_color[2]) * y / height
                    )
                    draw.line([(0, y), (width, y)], fill=(r, g, b))

        elif image_type == "noise":
            noise_array = np.random.randint(0, 256, (height, width, 3), dtype=np.uint8)
            img = Image.fromarray(noise_array, "RGB")

        else:
            return {"error": f"Unsupported image_type {image_type}"}

        result_path = save_image(img)
        result_base64 = encode_image(result_path)
        return {"generated_image": result_base64}

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


@tool
def combine_images(
    images_base64: List[str], operation: str, params: Optional[Dict[str, Any]] = None
) -> Dict[str, Any]:
    """
    Combine multiple images (collage, stack, blend).
    Args:
        images_base64 (List[str]): List of base64 images
        operation (str): Combination type
        params (Dict[str, Any], optional)
    Returns:
        Dictionary with combined image (base64)
    """
    try:
        images = [decode_image(b64) for b64 in images_base64]
        params = params or {}

        if operation == "stack":
            direction = params.get("direction", "horizontal")
            if direction == "horizontal":
                total_width = sum(img.width for img in images)
                max_height = max(img.height for img in images)
                new_img = Image.new("RGB", (total_width, max_height))
                x = 0
                for img in images:
                    new_img.paste(img, (x, 0))
                    x += img.width
            else:
                max_width = max(img.width for img in images)
                total_height = sum(img.height for img in images)
                new_img = Image.new("RGB", (max_width, total_height))
                y = 0
                for img in images:
                    new_img.paste(img, (0, y))
                    y += img.height
        else:
            return {"error": f"Unsupported combination operation {operation}"}

        result_path = save_image(new_img)
        result_base64 = encode_image(result_path)
        return {"combined_image": result_base64}

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