5290287058
- TTS: xtts-v2 integration with voice cloning support
- Document: docling integration for PDF/DOCX/PPTX processing
- Memory Service: added /facts/upsert, /facts/{key}, /facts endpoints
- Added required dependencies (TTS, docling)
38 lines
622 B
Docker
38 lines
622 B
Docker
FROM nvidia/cuda:12.1.0-runtime-ubuntu22.04
|
|
|
|
WORKDIR /app
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
python3.11 \
|
|
python3-pip \
|
|
curl \
|
|
git \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install Python dependencies
|
|
RUN pip3 install --no-cache-dir \
|
|
torch \
|
|
torchvision \
|
|
transformers \
|
|
accelerate \
|
|
pillow \
|
|
fastapi \
|
|
uvicorn \
|
|
python-multipart \
|
|
pydantic \
|
|
httpx \
|
|
tiktoken \
|
|
sentencepiece \
|
|
einops \
|
|
verovio
|
|
|
|
# Copy inference service
|
|
COPY . /app
|
|
|
|
# Expose port
|
|
EXPOSE 8000
|
|
|
|
# Run inference service
|
|
CMD ["python3", "main.py"]
|