update

app copy.py

@@ -0,0 +1,38 @@
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+import numpy as np
+
+app = FastAPI()
+
+# Load the Sentence Transformer model
+model = SentenceTransformer("BAAI/bge-large-zh-v1.5")
+
+class EmbeddingRequest(BaseModel):
+    input: str
+
+@app.post("/embeddings")
+async def embeddings(request: EmbeddingRequest):
+    input_text = request.input
+
+    # Calculate embeddings
+    embeddings = model.encode(input_text)
+
+    # Format the embeddings in OpenAI compatible format
+    data = {
+        "object": "list",
+        "data": [
+            {
+                "object": "embedding",
+                "embedding": embeddings.tolist(),
+                "index": 0
+            }
+        ],
+        "model": "BAAI/bge-large-zh-v1.5",
+        "usage": {
+            "prompt_tokens": len(input_text),
+            "total_tokens": len(input_text)
+        }
+    }
+
+    return data

app.py

@@ -1,38 +1,62 @@
-from fastapi import FastAPI, Request
-from pydantic import BaseModel
+from fastapi import FastAPI, Request, HTTPException
+from pydantic import BaseModel, Field
 from sentence_transformers import SentenceTransformer
 import numpy as np
+import logging
+
+# 设置日志记录
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-# Load the Sentence Transformer model
-model = SentenceTransformer("BAAI/bge-large-zh-v1.5")
+try:
+    # Load the Sentence Transformer model
+    model = SentenceTransformer("BAAI/bge-large-zh-v1.5")
+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
+    input: str = Field(..., min_length=1, max_length=1000)
 
 @app.post("/embeddings")
 async def embeddings(request: EmbeddingRequest):
     input_text = request.input
 
-    # Calculate embeddings
-    embeddings = model.encode(input_text)
-
-    # Format the embeddings in OpenAI compatible format
-    data = {
-        "object": "list",
-        "data": [
-            {
-                "object": "embedding",
-                "embedding": embeddings.tolist(),
-                "index": 0
+    try:
+        if not input_text:
+            return {
+                "object": "list",
+                "data": [],
+                "model": "BAAI/bge-large-zh-v1.5",
+                "usage": {
+                    "prompt_tokens": 0,
+                    "total_tokens": 0
+                }
+            }
+
+        # Calculate embeddings
+        embeddings = model.encode(input_text)
+
+        # Format the embeddings in OpenAI compatible format
+        data = {
+            "object": "list",
+            "data": [
+                {
+                    "object": "embedding",
+                    "embedding": embeddings.tolist(),
+                    "index": 0
+                }
+            ],
+            "model": "BAAI/bge-large-zh-v1.5",
+            "usage": {
+                "prompt_tokens": len(input_text),
+                "total_tokens": len(input_text)
             }
-        ],
-        "model": "BAAI/bge-large-zh-v1.5",
-        "usage": {
-            "prompt_tokens": len(input_text),
-            "total_tokens": len(input_text)
         }
-    }
 
-    return data
+        return data
+    except Exception as e:
+        logger.error(f"Error processing embeddings: {e}")
+        raise HTTPException(status_code=500, detail="Internal Server Error")