Dockerfile-docman

# Dockerfile for docman - TinyLLM Document Manager
#
#   Author: Jason A. Cox
#   22 Sept 2024
#   https://github.com/jasonacox/TinyLLM

# Use a base image
FROM python:3.10-slim

# Setting build related env vars
ENV MAX_CHUNK_SIZE=1024
ENV UPLOAD_FOLDER=uploads
ENV WEAVIATE_HOST=localhost
ENV WEAVIATE_GRPC_HOST=localhost
ENV WEAVIATE_PORT=8080
ENV WEAVIATE_GRPC_PORT=50051
ENV PORT=5001
ENV COLLECTIONS_ADMIN=true

# Set the working directory
WORKDIR /app

# Install dependencies
RUN apt-get update && apt-get install -y binutils
RUN pip install fastapi uvicorn jinja2 bs4 pypdf requests lxml aiohttp
RUN pip install weaviate-client pdfreader pypandoc
RUN pip install python-multipart
RUN pip install pandas openpyxl
RUN pip install python-socketio
RUN pip install passlib bcrypt

# Copy local files into container
COPY docman.py /app/docman.py
COPY documents.py /app/documents.py
COPY version.py /app/version.py
COPY docman /app/docman
COPY setup_pandoc.py /app/setup_pandoc.py

# Build Pandoc
RUN python setup_pandoc.py

# Network
EXPOSE $PORT

# Run the server
CMD uvicorn docman:app --host 0.0.0.0 --port $PORT