added

.gitignore

@@ -0,0 +1,2 @@
+__pycache__/*
+__pycache__

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,11 @@
+from fastapi import FastAPI
+from back_end.routers import embedding
+
+app = FastAPI(title="Text Embedding API")
+
+# Include the embedding router
+app.include_router(embedding.router, prefix="/api")
+
+@app.get("/")
+def home():
+    return {"message": "Welcome to the Text Embedding API"}

back_end/models/embedding_model.py

@@ -0,0 +1,9 @@
+from sentence_transformers import SentenceTransformer
+
+# Load the pre-trained embedding model
+model = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True)
+
+def generate_embedding(text: str):
+    """Generate a 768-dimensional embedding for the input text."""
+    embedding = model.encode(text).tolist()  # Convert NumPy array to list
+    return embedding

back_end/routers/__init__.py

@@ -0,0 +1,3 @@
+from fastapi import APIRouter
+
+router = APIRouter()

back_end/routers/embedding.py

@@ -0,0 +1,14 @@
+from fastapi import APIRouter, HTTPException
+from back_end.models.embedding_model import generate_embedding
+from back_end.schemas.request import TextRequest
+
+router = APIRouter()
+
+@router.get("/generate_embedding/")
+def get_embedding(text: str):
+    """Returns a 768-dimensional embedding for the given text."""
+    if not text:
+        raise HTTPException(status_code=400, detail="Text cannot be empty")
+
+    embedding = generate_embedding(text)
+    return {"embedding": embedding, "dimensions": len(embedding)}

back_end/schemas/request.py

@@ -0,0 +1,4 @@
+from pydantic import BaseModel
+
+class TextRequest(BaseModel):
+    text: str

requirements.txt

@@ -0,0 +1,5 @@
+pandas
+sentence-transformers
+scikit-learn
+openpyxl
+fastapi[standard]