add GHA and Dockerfile

.github/workflows/tests.yml

@@ -0,0 +1,27 @@
+name: Python integration tests
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      # You can test your matrix by printing the current Python version
+      - name: Display Python version
+        run: python -c "import sys; print(sys.version)"
+      - name: Install dependencies
+        run: pip install -r requirements.txt
+      - name: Install test dependencies
+        run: pip install -r test-requirements.txt
+      - name: Integration tests
+        run: pytest

Dockerfile

@@ -0,0 +1,22 @@
+FROM nvidia/cuda:12.2.2-runtime-ubuntu22.04
+
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PORT=8080
+
+RUN --mount=target=/var/lib/apt/lists,type=cache,sharing=locked \
+    --mount=target=/var/cache/apt,type=cache,sharing=locked \
+    apt-get update && \
+    apt-get -y --no-install-recommends install python3 python3-pip git && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt requirements.txt
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip3 install --upgrade pip && \
+    pip3 install -r requirements.txt
+
+COPY main.py .
+COPY entrypoint.sh /usr/local/bin/
+CMD [ "entrypoint.sh" ]
+
+EXPOSE ${PORT}

README.md

@@ -1,5 +1,10 @@
 # Sentence Transformers API
 
+OpenAI compatible endpont for Sentence Transformer embedding models
+
+## Usage (Docker)
+
+
 ## Development
 
 ```

entrypoint.sh

@@ -0,0 +1,3 @@
+#!/usr/bin/env bash
+
+uvicorn main:app --host 0.0.0.0 --port $PORT

main.py

@@ -1,12 +1,13 @@
 from typing import Union, List, Dict
 from contextlib import asynccontextmanager
+import os
 
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel, Field
 from sentence_transformers import SentenceTransformer
 
 models: Dict[str, SentenceTransformer] = {}
-default_model_name = 'all-MiniLM-L6-v2'
+default_model_name = os.getenv("MODEL", 'all-MiniLM-L6-v2')
 
 class EmbeddingRequest(BaseModel):
     input: str | List[str] = Field(examples=["substratus.ai provides the best LLM tools"])

requirements.txt

@@ -1,3 +1,3 @@
 fastapi
 sentence-transformers
-uvicorn
+uvicorn[standard]