update sth. at 2025-03-03 19:15:11

README.md

@@ -56,4 +56,42 @@ curl -X POST https://sanbo1200-jina-embeddings-v3.hf.space/hf/v1/embeddings \
   }'
 
 
+
+
+
+curl https://api.jina.ai/v1/embeddings \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer jina_xxxx" \
+  -d @- <<EOFEOF
+  {
+    "model": "jina-clip-v2",
+    "dimensions": 1024,
+    "normalized": true,
+    "embedding_type": "float",
+    "input": [
+        {
+            "text": "A beautiful sunset over the beach"
+        },
+        {
+            "text": "Un beau coucher de soleil sur la plage"
+        },
+        {
+            "text": "海滩上美丽的日落"
+        },
+        {
+            "text": "浜辺に沈む美しい夕日"
+        },
+        {
+            "image": "https://i.ibb.co/nQNGqL0/beach1.jpg"
+        },
+        {
+            "image": "https://i.ibb.co/r5w8hG8/beach2.jpg"
+        },
+        {
+            "image": "R0lGODlhEAAQAMQAAORHHOVSKudfOulrSOp3WOyDZu6QdvCchPGolfO0o/XBs/fNwfjZ0frl3/zy7////wAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACH5BAkAABAALAAAAAAQABAAAAVVICSOZGlCQAosJ6mu7fiyZeKqNKToQGDsM8hBADgUXoGAiqhSvp5QAnQKGIgUhwFUYLCVDFCrKUE1lBavAViFIDlTImbKC5Gm2hB0SlBCBMQiB0UjIQA7"
+        }
+    ]
+  }
+EOFEOF
+
 ```

app.py

@@ -35,8 +35,10 @@ class EmbeddingRequest(BaseModel):
         return values
 
 class EmbeddingResponse(BaseModel):
-    status: str
-    embeddings: List[List[float]]
+    object: str = "list"
+    data: List[Dict[str, any]]
+    model: str
+    usage: Dict[str, int]
 
 class EmbeddingService:
     def __init__(self):
@@ -114,14 +116,29 @@ app.add_middleware(
 @app.post("/hf/v1/chat/completions", response_model=EmbeddingResponse)
 async def generate_embeddings(request: EmbeddingRequest):
     try:
+        # 计算token数量
+        token_count = len(embedding_service.tokenizer.encode(request.inputs))
+
         embedding = await asyncio.get_running_loop().run_in_executor(
             None,
             embedding_service.get_embedding,
             request.inputs  # 使用合并后的输入字段
         )
+        
         return EmbeddingResponse(
-            status="success",
-            embeddings=[embedding]
+            object="list",
+            data=[
+                {
+                    "object": "embedding",
+                    "index": 0,
+                    "embedding": embedding
+                }
+            ],
+            model=request.model,
+            usage={
+                "prompt_tokens": token_count,
+                "total_tokens": token_count
+            }
         )
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
@@ -166,4 +183,4 @@ async def startup_event():
 if __name__ == "__main__":
     asyncio.run(embedding_service.initialize())
     gr.mount_gradio_app(app, iface, path="/ui")
-    uvicorn.run(app, host="0.0.0.0", port=7860, workers=1)
+    uvicorn.run(app, host="0.0.0.0", port=7860, workers=2)