Suya OCR API — vLLM-backed, OpenAI-compatible OCR service

FastAPI service wrapping the Surya-OCR-2 model (datalab-to) served through vLLM:
legacy /v1/api/ai/* endpoints, an OpenAI-compatible /v1/chat/completions endpoint,
a coalescing request batcher, a local OCR CLI, Docker packaging, multilingual
example outputs, and quantization/concurrency benchmarks.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

api_test.py

@@ -0,0 +1,64 @@
+# import base64
+# import requests
+# import os
+
+# # Configuration
+# API_URL = "http://localhost:5002/v1/api/ai/suya_ocr"
+
+# # Helper to encode image
+# def encode_image_to_base64(path):
+#     with open(path, "rb") as image_file:
+#         return base64.b64encode(image_file.read()).decode("utf-8")
+
+# def test_ocr_endpoint_requests():
+#     image_path = "/path/to/surya/ttt.png"
+#     assert os.path.exists(image_path), f"Image file not found: {image_path}"
+
+#     encoded_image = encode_image_to_base64(image_path)
+
+#     payload = {
+#         "file": encoded_image,
+#         "type": "jpg",
+#         "skip_text_detection": False,
+#         "skip_table_detection": False,
+#         "recognize_math": False,
+#         "ocr_with_boxes": True
+#     }
+
+#     # Send request using requests
+#     response = requests.post(API_URL, json=payload)
+
+#     assert response.status_code == 200
+#     response_json = response.json()
+#     assert response_json["code"] == 200
+#     assert "ocr_text_json" in response_json["data"]
+#     assert "text_lines" in response_json["data"]
+
+#     print("OCR Response Text:")
+#     print(response_json["data"]["text_lines"])
+
+
+# import time
+# tik = time.time()
+# test_ocr_endpoint_requests()
+# tok = time.time()
+# print("time consumption: ", tok - tik)
+
+
+
+import requests
+
+# API 地址
+url = "http://127.0.0.1:5002/image2text"
+
+# 测试用图像路径
+image_path = "/path/to/surya/ttt.png"  # 替换为你自己的图像路径
+
+# 发起 POST 请求
+with open(image_path, "rb") as image_file:
+    files = {"file": ("ttt.png", image_file, "image/png")}
+    response = requests.post(url, files=files)
+
+# 打印响应
+print("Status Code:", response.status_code)
+print("Response JSON:", response.json())