update

app.py

@@ -28,8 +28,8 @@ except Exception as e:
     logger.error(f"Failed to load model: {e}")
     raise HTTPException(status_code=500, detail="Model loading failed")
 
-# class EmbeddingRequest(BaseModel):
-#     input: str = Field(..., min_length=1, max_length=1000)
+class EmbeddingRequest(BaseModel):
+    input: str | list[str]
 
 @app.post("/v1/embeddings")
 async def embeddings(request, authorization: str = Depends(check_authorization)):
@@ -37,10 +37,10 @@ async def embeddings(request, authorization: str = Depends(check_authorization))
     # logger.info("Received request for embeddings")
     # return '2222222222'
     # return request.input
-    input_texts = request.input
+    input = request.input
 
     try:
-        if not input_texts:
+        if not input:
             return {
                 "object": "list",
                 "data": [],
@@ -52,8 +52,8 @@ async def embeddings(request, authorization: str = Depends(check_authorization))
             }
 
         # Calculate embeddings
-        # embeddings = model.encode(input_text)
-        embeddings_1 = model.encode(input_texts, normalize_embeddings=True)
+        # embeddings = model.encode(input)
+        embeddings = model.encode(input, normalize_embeddings=True)
 
         # Format the embeddings in OpenAI compatible format
         data = {
@@ -67,8 +67,8 @@ async def embeddings(request, authorization: str = Depends(check_authorization))
             ],
             "model": "BAAI/bge-large-zh-v1.5",
             "usage": {
-                "prompt_tokens": len(input_texts),
-                "total_tokens": len(input_texts)
+                "prompt_tokens": len(input),
+                "total_tokens": len(input)
             }
         }