pluto
74e12eca60
FastAPI service that loads ViT-L-14 model and exposes /embed, /similarity, and /batch-similarity endpoints. Runs on RTX 3090 with NVIDIA GPU reservation. Includes 9 cosine similarity tests. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
16 lines
369 B
Docker
16 lines
369 B
Docker
FROM pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends curl \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
WORKDIR /app
|
|
|
|
COPY app/requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
COPY app/ .
|
|
|
|
EXPOSE 5200
|
|
|
|
CMD ["python", "-u", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "5200"]
|