first commit

.gitignore

@@ -0,0 +1,2 @@
+venv
+__pycache__

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.12
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["gunicorn", "-w", "5", "main:app"]

main.py

@@ -0,0 +1,22 @@
+from flask import Flask
+from flask import request
+from sentence_transformers import SentenceTransformer
+
+app = Flask(__name__)
+model = SentenceTransformer('Alibaba-NLP/gte-large-en-v1.5', trust_remote_code=True)
+
+@app.route("/embedding", methods=['POST'])
+def embedding():
+    """
+    {
+        text: <text>
+    }
+    """
+
+    message = request.get_json()
+    message = model.encode(message)
+
+    return model.encode(message['text'])
+
+
+# curl -v -X POST 'http://127.0.0.1:8000/completion' --header 'Content-Type: application/json' --data '{"text": "what is an apple?"}'

requirements.txt

@@ -0,0 +1,47 @@
+blinker==1.8.2
+certifi==2024.6.2
+charset-normalizer==3.3.2
+click==8.1.7
+filelock==3.14.0
+Flask==3.0.3
+fsspec==2024.6.0
+gunicorn==22.0.0
+huggingface-hub==0.23.2
+idna==3.7
+itsdangerous==2.2.0
+Jinja2==3.1.4
+joblib==1.4.2
+MarkupSafe==2.1.5
+mpmath==1.3.0
+networkx==3.3
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.5.40
+nvidia-nvtx-cu12==12.1.105
+packaging==24.0
+pillow==10.3.0
+PyYAML==6.0.1
+regex==2024.5.15
+requests==2.32.3
+safetensors==0.4.3
+scikit-learn==1.5.0
+scipy==1.13.1
+sentence-transformers==3.0.0
+sympy==1.12.1
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+torch==2.3.0
+tqdm==4.66.4
+transformers==4.41.2
+typing_extensions==4.12.1
+urllib3==2.2.1
+Werkzeug==3.0.3