Create server.py

server.py

@@ -0,0 +1,47 @@
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer
+import time
+import hashlib
+import os
+
+app = FastAPI()
+
+# Load embedding model (fast + free)
+model_name = "sentence-transformers/all-MiniLM-L6-v2"
+model = SentenceTransformer(model_name)
+
+# OpenAI compatible request/response
+class EmbeddingRequest(BaseModel):
+    input: list[str]
+
+class EmbeddingResponse(BaseModel):
+    object: str = "list"
+    data: list
+    model: str
+    usage: dict
+
+@app.post("/v1/embeddings", response_model=EmbeddingResponse)
+async def create_embeddings(request: EmbeddingRequest):
+    start_time = time.time()
+
+    embeddings = model.encode(request.input, convert_to_numpy=True).tolist()
+
+    # Pack in OpenAI-like format
+    data = []
+    for i, emb in enumerate(embeddings):
+        data.append({
+            "object": "embedding",
+            "index": i,
+            "embedding": emb
+        })
+
+    return {
+        "object": "list",
+        "data": data,
+        "model": model_name,
+        "usage": {
+            "prompt_tokens": len(" ".join(request.input).split()),
+            "total_tokens": len(" ".join(request.input).split())
+        }
+    }