🚀 localにembedding modelを構築

docker/embedding-api/Dockerfile

@@ -0,0 +1,8 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+COPY embedding_api.py .
+
+RUN pip install fastapi uvicorn sentence-transformers
+
+CMD ["uvicorn", "embedding_api:app", "--host", "0.0.0.0", "--port", "8001"]

docker/embedding-api/embedding_api.py

@@ -0,0 +1,19 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from typing import List
+from sentence_transformers import SentenceTransformer
+
+app = FastAPI()
+model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+class EmbeddingRequest(BaseModel):
+    input: List[str]
+
+@app.post("/v1/embeddings")
+async def embed(request: EmbeddingRequest):
+    embeddings = model.encode(request.input).tolist()
+    return {
+        "data": [{"embedding": emb, "index": i} for i, emb in enumerate(embeddings)],
+        "model": "sentence-transformers/all-MiniLM-L6-v2",
+        "object": "list"
+    }