File size: 11,087 Bytes
9883bdb 3a3681c 9883bdb 46f2212 9883bdb 46f2212 9883bdb 3a3681c 9883bdb 46f2212 9883bdb 46f2212 9883bdb 46f2212 4fc1a2f 9883bdb 46f2212 9883bdb | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 | import base64
from openai import OpenAI
from PIL import Image
from io import BytesIO
import os
def resize_image(image_input, max_size=1024, preserve_aspect_ratio=True):
"""
Resize an image while preserving aspect ratio
Args:
image_input: Either a PIL Image object or a string file path to an image
max_size (int): Maximum width or height (whichever is larger)
preserve_aspect_ratio (bool): Whether to preserve the aspect ratio
Returns:
PIL.Image: Resized image
"""
# Load the image if it's a file path
if isinstance(image_input, str):
if not os.path.exists(image_input):
raise FileNotFoundError(f"Image file not found: {image_input}")
img = Image.open(image_input)
else:
# Already a PIL Image
img = image_input
# Get original dimensions
width, height = img.size
# Skip if already smaller than max_size
if width <= max_size and height <= max_size:
return img
if preserve_aspect_ratio:
# Calculate the ratio
if width > height:
new_width = max_size
new_height = int(height * (max_size / width))
else:
new_height = max_size
new_width = int(width * (max_size / height))
else:
new_width = max_size
new_height = max_size
# Resize the image
resized_img = img.resize((new_width, new_height), Image.LANCZOS)
return resized_img
def encode_image(image_input, format="JPEG", max_size=None):
"""
Convert an image to a base64 encoded string, with optional resizing.
Args:
image_input: Either a PIL Image object or a string file path to an image
format: Image format for saving (default: "JPEG")
max_size: Maximum size for the image (width or height). If None, no resizing is done.
Returns:
base64 encoded string of the image
"""
# Check if input is a file path (string) or PIL Image
if isinstance(image_input, str):
# Input is a file path
if not os.path.exists(image_input):
raise FileNotFoundError(f"Image file not found: {image_input}")
if max_size:
# Load, resize, and encode
img = Image.open(image_input)
resized_img = resize_image(img, max_size=max_size)
buffered = BytesIO()
resized_img.save(buffered, format=format)
return base64.b64encode(buffered.getvalue()).decode("utf-8")
else:
# Read file directly without resizing
with open(image_input, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
else:
# Input is a PIL Image object
if max_size:
image_input = resize_image(image_input, max_size=max_size)
buffered = BytesIO()
image_input.save(buffered, format=format)
return base64.b64encode(buffered.getvalue()).decode("utf-8")
class OpenRouterAPI:
def __init__(self, api_key=None,base_url="https://openrouter.ai/api/v1"):
"""
Initialize the OpenRouter client
Args:
api_key (str, optional): OpenRouter API key. If None, will try to get from environment variable
"""
api_key = api_key or os.getenv("OPENROUTER_API_KEY")
if not api_key:
raise ValueError("OpenRouter API key not provided and not found in environment variables")
self.client = OpenAI(
api_key=api_key,
base_url=base_url
)
def list_models(self):
"""
List all available models on OpenRouter
Returns:
list: List of model IDs
"""
models = self.client.models.list()
model_ids = [model.id for model in models.data]
return model_ids
def generate_caption(self, image_path,
model="anthropic/claude-3-7-sonnet",
prompt_dev="",
prompt="Give a very brief description of this image.",
detail="high",
temperature=0.7,
max_image_size=1024):
"""
Generate captions for an image using OpenRouter models
Args:
image_path (str): Path to the image file
model (str): Model to use (e.g., 'anthropic/claude-3-7-sonnet', 'openai/gpt-4o')
prompt_dev (str): System prompt or developer prompt
prompt (str): Text prompt to guide caption generation
detail (str): Level of detail for image analysis ('low', 'high', etc.) - only applies to OpenAI models
temperature (float): Sampling temperature for generation
max_image_size (int): Maximum dimension of the image before encoding. Set to None to disable resizing.
Returns:
str: Generated caption
"""
# Getting the Base64 string with optional resizing
base64_image = encode_image(image_path, max_size=max_image_size)
# Prepare messages based on OpenRouter's format
messages = []
# Add system message if prompt_dev is provided
if prompt_dev:
messages.append({
"role": "system",
"content": prompt_dev
})
# Add user message with text and image
content = [
{
"type": "text",
"text": prompt,
}
]
content.append({
"type": "image_url",
"image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
})
messages.append({
"role": "user",
"content": content,
"provider": {
"data_collection": "deny"
}
})
response = self.client.chat.completions.create(
model=model,
messages=messages,
temperature=temperature
)
return response.choices[0].message.content
def generate_text_response(self, text_prompt,
model="anthropic/claude-3-5-haiku",
prompt_dev="",
temperature=0.7):
"""
Generate responses based on text input using OpenRouter models
Args:
text_prompt (str): The text to analyze or respond to
model (str): Model to use (e.g., 'anthropic/claude-3-5-haiku', 'openai/gpt-4o-mini', 'google/gemini-pro')
prompt_dev (str): System prompt or developer prompt
temperature (float): Sampling temperature for generation
Returns:
str: Generated response
"""
# Prepare messages based on OpenRouter's format
messages = []
# Add system message if prompt_dev is provided
if prompt_dev:
messages.append({
"role": "system",
"content": prompt_dev
})
# Add user message with text
messages.append({
"role": "user",
"content": text_prompt
})
response = self.client.chat.completions.create(
model=model,
messages=messages,
temperature=temperature,
)
return response.choices[0].message.content
def classify_objs(self, image_path,
categories=["Painting/sketch", "Statue/Bust", "Clothing", "Porcelain/Ceramic tableware", "Text based Document", "Other"],
model="openai/gpt-4o-mini",
detail="low",
max_image_size=512): # Using smaller size for classification since less detail is needed
"""
Classify objects in an image into predefined categories
Args:
image_path (str): Path to the image file
categories (list): List of categories for classification
model (str): Model to use for classification
detail (str): Level of detail for image analysis ('low', 'high') - only applies to OpenAI models
max_image_size (int): Maximum dimension for the image. Can be smaller for classification tasks.
Returns:
str: Classification result
"""
prompt = f"This is an image of a museum object. Classify it into one of these categories: {categories}. Only classify it if you are confident it belongs in that category and the category represents the main portion of the image, otherwise return 'Other'. Respond with only the category name."
return self.generate_caption(image_path, model=model, prompt=prompt, detail=detail, max_image_size=max_image_size)
def estimate_cost(self, model, tokens_in=1000, tokens_out=200, image=False, detail="low"):
"""
Estimate the cost of using a specific model based on input/output tokens
Args:
model (str): Model identifier
tokens_in (int): Number of input tokens
tokens_out (int): Number of output tokens
image (bool): Whether the request includes an image
detail (str): Image detail level ('low', 'high')
Returns:
dict: Cost estimate information
"""
# This is a simplified approach - in a real implementation,
# you might want to use OpenRouter's pricing API or maintain
# a more complete pricing table
# Simplified pricing mapping (in USD per 1M tokens)
# These are example values - please update with actual OpenRouter pricing
pricing = {
"anthropic/claude-3-7-sonnet": {"input": 15.0, "output": 75.0},
"anthropic/claude-3-5-haiku": {"input": 1.0, "output": 5.0},
"openai/gpt-4o": {"input": 10.0, "output": 30.0},
"openai/gpt-4o-mini": {"input": 0.2, "output": 0.6},
"google/gemini-pro": {"input": 0.5, "output": 1.5},
}
# Default to a moderate pricing if model not found
model_pricing = pricing.get(model, {"input": 5.0, "output": 15.0})
# Image tokens estimation
image_tokens = 0
if image:
if detail == "low":
image_tokens = 1200
else: # high
image_tokens = 4000
# Calculate costs
input_cost = (tokens_in + image_tokens) * model_pricing["input"] / 1000000
output_cost = tokens_out * model_pricing["output"] / 1000000
total_cost = input_cost + output_cost
return {
"model": model,
"input_tokens": tokens_in + image_tokens,
"output_tokens": tokens_out,
"input_cost": input_cost,
"output_cost": output_cost,
"total_cost": total_cost
}
|