hmo
04db423416
- 70 skills with code and documentation - Add .gitignore (ignore __pycache__, output/, temp/, venv/) - Clean up test intermediates and caches
69 lines
1.9 KiB
Python
69 lines
1.9 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
固定的 look_at 工具实现，使用 火山方舟 API
|
|
替代系统默认的 Google Vision API 依赖
|
|
"""
|
|
|
|
import base64
|
|
import json
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
|
|
def look_at(file_path, goal):
|
|
"""
|
|
Fixed look_at implementation using 火山方舟 API
|
|
This replaces the default Google Vision API dependency
|
|
"""
|
|
# Get API key from environment or use default
|
|
api_key = os.getenv("VOLCENGINE_API_KEY", "b0359bed-09f2-49e2-a53c-32ba057412e3")
|
|
base_url = "https://ark.cn-beijing.volces.com/api/coding/v3"
|
|
model = "doubao-seed-code" # Coding Plan唯一支持的视觉模型
|
|
|
|
# Encode image to base64
|
|
with open(file_path, "rb") as f:
|
|
image_base64 = base64.b64encode(f.read()).decode("utf-8")
|
|
|
|
# Make API request
|
|
import httpx
|
|
|
|
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
|
|
|
|
payload = {
|
|
"model": model,
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "image_url",
|
|
"image_url": {"url": f"data:image/jpeg;base64,{image_base64}"},
|
|
},
|
|
{"type": "text", "text": goal},
|
|
],
|
|
}
|
|
],
|
|
"max_tokens": 2000,
|
|
}
|
|
|
|
try:
|
|
response = httpx.post(
|
|
f"{base_url}/chat/completions", headers=headers, json=payload, timeout=120.0
|
|
)
|
|
response.raise_for_status()
|
|
result = response.json()
|
|
return result.get("choices", [{}])[0].get("message", {}).get("content", "")
|
|
except Exception as e:
|
|
raise RuntimeError(f"Vision analysis failed: {e}")
|
|
|
|
|
|
# Make it callable as a module
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) != 3:
|
|
print("Usage: python look_at_fixed.py <file_path> <goal>", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
result = look_at(sys.argv[1], sys.argv[2])
|
|
print(result)
|