Add application file

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.15.4
+
+# Copy the current directory contents into the container at .
+COPY . .
+
+# Set the working directory to /
+WORKDIR /
+
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /requirements.txt
+
+# Start the FastAPI app on port 7860, the default port expected by Spaces
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,60 @@
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from enum import Enum
+import os
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+        "dunzhang/stella_en_400M_v5",
+        trust_remote_code=True,
+        device="cpu",
+        config_kwargs={"use_memory_efficient_attention": False, "unpad_inputs": False}
+    )
+
+class Enum(str, Enum):
+    s2p_query = "s2p_query" # sentence-to-sentence
+    s2s_query = "s2s_query" # sentence-to-passage, Q&A
+
+class Embedding(BaseModel):
+    input: list[str]
+    embedding_type: Enum = None
+    
+    
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["POST"],
+    allow_headers=["Authorization"]
+)
+
+def parse(data):
+    result = []
+    for dimension in data:
+        temp = []
+        for val in dimension:
+            temp.append(round(val, 8))
+        result.append(temp)
+    return result
+
+
+@app.post("/embeddings/")
+async def get_embedding(embedding: Embedding, req: Request):
+    
+    token = req.headers.get("Authorization")
+    if os.environ.get('token') != token[7:]:
+        raise HTTPException(status_code=401, detail="Unauthorized.")
+    
+    if model == None:
+        raise HTTPException(status_code=400, detail="Model load failed.")
+    
+    if embedding.embedding_type == None:
+        data = model.encode(embedding.input).tolist()
+        return parse(data)
+    else:
+        data = model.encode(embedding.input, prompt_name=embedding.embedding_type).tolist()
+        return parse(data)
+    

requirements.txt

@@ -0,0 +1,4 @@
+fastapi==0.108.0
+uvicorn
+pydantic
+sentence_transformers==3.0.1