|
|
@@ -66,13 +66,14 @@ class UnderstandImageProvider:
|
|
|
print("UnderstandImageProvider called")
|
|
|
def understand_image(self, image_url: str, *, model: str) -> DataResponse:
|
|
|
|
|
|
-
|
|
|
client = OpenAI(
|
|
|
api_key = settings.dashscope_api_key or "",
|
|
|
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
|
|
|
)
|
|
|
+
|
|
|
if not client:
|
|
|
logger.error("OpenAI client is not initialized.")
|
|
|
+ return DataResponse(code=1, data=None, msg=f"OpenAI client is not initialized")
|
|
|
|
|
|
completion = client.chat.completions.create(
|
|
|
model=model,
|
|
|
@@ -105,6 +106,7 @@ class UnderstandImageProvider:
|
|
|
ocr_text = str(args.get("ocr_text", "")).strip()
|
|
|
except Exception as e:
|
|
|
logger.error("parse tool call failed: %s", e, exc_info=True)
|
|
|
+ return DataResponse(code=1, data=None, msg=f"parse tool call failed: {e}")
|
|
|
|
|
|
# Fallback: if no tool-calls returned, try to read text content
|
|
|
content = getattr(msg, "content", None)
|
|
|
@@ -113,5 +115,5 @@ class UnderstandImageProvider:
|
|
|
|
|
|
print("✅ OCR_TEXT:\n", ocr_text)
|
|
|
|
|
|
- return DataResponse(code=200, data=ocr_text, msg="Image understood successfully")
|
|
|
+ return DataResponse(code=0, data=ocr_text, msg="success")
|
|
|
|
