- Create parser-service/ with full structure - Add FastAPI app with endpoints (/parse, /parse_qa, /parse_markdown, /parse_chunks) - Add Pydantic schemas (ParsedDocument, ParsedBlock, ParsedChunk, etc.) - Add runtime module with model_loader and inference (with dummy parser) - Add configuration, Dockerfile, requirements.txt - Update TODO-PARSER-RAG.md with completed tasks - Ready for dots.ocr model integration
28 lines
529 B
Docker
28 lines
529 B
Docker
FROM python:3.11-slim
|
|
|
|
WORKDIR /app
|
|
|
|
# Install system dependencies
|
|
RUN apt-get update && apt-get install -y \
|
|
poppler-utils \
|
|
libgl1-mesa-glx \
|
|
libglib2.0-0 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Copy requirements and install dependencies
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
# Copy application code
|
|
COPY . .
|
|
|
|
# Create temp directory
|
|
RUN mkdir -p /tmp/parser
|
|
|
|
# Expose port
|
|
EXPOSE 9400
|
|
|
|
# Run application
|
|
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "9400"]
|
|
|