UmdTask437_DATA605_Spring2026_DocsGPT_1

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/.env.example

@@ -0,0 +1 @@
+DOCSGPT_API_KEY='add-agent-key'

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/.gitignore

@@ -0,0 +1,7 @@
+.env
+!.env.example
+.gradio/
+__pycache__/
+.ipynb_checkpoints/
+.DS_Store
+.venv

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/.gitkeep

@@ -0,0 +1 @@
+

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/Dockerfile

@@ -0,0 +1,30 @@
+# Use Python 3.12 slim (already has Python and pip).
+FROM python:3.12-slim
+
+# Avoid interactive prompts during apt operations.
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install CA certificates (needed for HTTPS).
+RUN apt-get update && apt-get install -y \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install project specific packages.
+RUN mkdir -p /install
+COPY requirements.txt /install/requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir jupyterlab jupyterlab_vim jupytext -r /install/requirements.txt
+
+# Config.
+COPY etc_sudoers /install/
+COPY etc_sudoers /etc/sudoers
+COPY bashrc /root/.bashrc
+
+# Report package versions.
+COPY version.sh /install/
+RUN /install/version.sh 2>&1 | tee version.log
+
+# Jupyter.
+EXPOSE 8888
+
+CMD ["/bin/bash"]

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/Dockerfile.python_slim

@@ -0,0 +1,28 @@
+# Use Python 3.12 slim (already has Python and pip).
+FROM python:3.12-slim
+
+# Avoid interactive prompts during apt operations.
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install CA certificates (needed for HTTPS).
+RUN apt-get update && apt-get install -y \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install project specific packages.
+RUN mkdir -p /install
+COPY requirements.txt /install/requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir jupyterlab jupyterlab_vim jupytext -r /install/requirements.txt
+
+# Config.
+COPY etc_sudoers /install/
+COPY etc_sudoers /etc/sudoers
+COPY bashrc /root/.bashrc
+
+# Report package versions.
+COPY version.sh /install/
+RUN /install/version.sh 2>&1 | tee version.log
+
+# Jupyter.
+EXPOSE 8888

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/Dockerfile.ubuntu

@@ -0,0 +1,40 @@
+FROM ubuntu:24.04
+ENV DEBIAN_FRONTEND noninteractive
+
+# Install system utilities and Python in a single layer.
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+      sudo \
+      curl \
+      git \
+      build-essential \
+      python3 \
+      python3-pip \
+      python3-dev \
+      python3-venv \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create virtual environment.
+RUN python3 -m venv /opt/venv
+
+# Make the venv the default Python.
+ENV PATH="/opt/venv/bin:$PATH"
+
+# Install project specific packages.
+RUN mkdir /install
+COPY requirements.txt /install/requirements.txt
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir jupyterlab jupyterlab_vim jupytext -r /install/requirements.txt
+
+# Config.
+COPY etc_sudoers /install/
+COPY etc_sudoers /etc/sudoers
+COPY bashrc /root/.bashrc
+
+# Report package versions.
+COPY version.sh /install/
+RUN /install/version.sh 2>&1 | tee version.log
+
+# Jupyter.
+EXPOSE 8888

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/Dockerfile.uv

@@ -0,0 +1,49 @@
+FROM ubuntu:24.04
+ENV DEBIAN_FRONTEND noninteractive
+
+# Install system utilities and Python in a single layer.
+RUN apt-get update && \
+  apt-get upgrade -y && \
+  apt-get install -y --no-install-recommends \
+    sudo \
+    curl \
+    git \
+    build-essential \
+    python3 \
+    python3-pip \
+    python3-dev \
+    python3-venv \
+    libgomp1 \
+    g++ \
+  && rm -rf /var/lib/apt/lists/*
+
+# Install uv for package management.
+RUN curl -LsSf https://astral.sh/uv/install.sh | sh
+ENV PATH="/root/.local/bin:$PATH"
+
+# Install project specific packages using uv.
+COPY pyproject.toml uv.lock /app/
+WORKDIR /app
+RUN uv sync
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Install Jupyter.
+RUN pip install --upgrade pip && \
+    pip install --no-cache-dir jupyterlab jupyterlab_vim jupytext
+
+# Copy project files.
+COPY . /app
+
+RUN mkdir /install
+
+# Config.
+COPY etc_sudoers /install/
+COPY etc_sudoers /etc/sudoers
+COPY bashrc /root/.bashrc
+
+# Report package versions.
+COPY version.sh /install/
+RUN /install/version.sh 2>&1 | tee version.log
+
+# Jupyter.
+EXPOSE 8888

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/README.md

@@ -0,0 +1,46 @@
+# DocsGPT Tutorial — Intelligent Documentation Assistant
+
+DocsGPT is an open-source, RAG-based AI platform (15k+ GitHub stars) that
+retrieves relevant document chunks and passes them to a language model to
+generate grounded answers. This tutorial builds a complete documentation
+assistant on top of the DocsGPT Cloud API — covering summarisation, FAQ
+generation, evaluation, multi-language output, streaming, and an interactive UI.
+
+## Quick Start
+
+```bash
+cd tutorials/docsgpt
+cp .env.example .env          # add your agent key to .env
+./docker_build.sh             # build the Docker image
+./docker_jupyter.sh           # launch Jupyter Lab at localhost:8888
+```
+
+Get your Agent key: https://app.docsgpt.cloud → Settings → Agents → Create New
+
+Open **http://localhost:8888** and work through the notebooks in order:
+
+1. **`docsgpt.API.ipynb`** (20 min) — Walks through every real DocsGPT Cloud
+   endpoint with raw HTTP calls and `docsgpt_utils` wrapper calls side by side:
+   `/api/answer`, `/stream`, `/api/store_attachment`, `/api/task_status`.
+   Also covers multi-turn conversation, SSE streaming, and the file attachment flow.
+
+2. **`docsgpt.example.ipynb`** (25 min) — End-to-end documentation assistant:
+   loads data from three real datasets (Awesome ML, Stack Overflow, The Pile),
+   summarises each document, generates FAQs, evaluates output with ROUGE + BLEU,
+   produces multi-language output in 9 languages, and launches an interactive
+   Gradio UI.
+
+
+## Key files
+
+| File | Purpose |
+|------|---------|
+| `docsgpt_utils.py` | All reusable functions and API wrappers |
+| `docsgpt.API.ipynb` + `.py` | API walkthrough (Jupytext paired) |
+| `docsgpt.example.ipynb` + `.py` | Full application (Jupytext paired) |
+| `Dockerfile` + `docker_*.sh` | Container setup and management |
+| `requirements.txt` | Pinned Python dependencies |
+| `.env.example` | Template for API key configuration |
+
+See [project template README](project_template_README.md) for full
+Docker usage details.

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/bashrc

@@ -0,0 +1 @@
+set -o vi

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/copy_docker_files.py

@@ -0,0 +1,140 @@
+#!/usr/bin/env python
+
+"""
+Copy Docker-related files from the source directory to a destination directory.
+
+This script copies all Docker configuration and utility files from
+class_project/project_template/ to a specified destination directory.
+
+Usage examples:
+    # Copy all files to a target directory.
+    > ./copy_docker_files.py --dst_dir /path/to/destination
+
+    # Copy with verbose logging.
+    > ./copy_docker_files.py --dst_dir /path/to/destination -v DEBUG
+
+Import as:
+
+import class_project.project_template.copy_docker_files as cpdccodo
+"""
+
+import argparse
+import logging
+import os
+from typing import List
+
+import helpers.hdbg as hdbg
+import helpers.hio as hio
+import helpers.hparser as hparser
+import helpers.hsystem as hsystem
+
+_LOG = logging.getLogger(__name__)
+
+# #############################################################################
+# Constants
+# #############################################################################
+
+# List of files to copy from the source directory.
+_FILES_TO_COPY = [
+    "bashrc",
+    "docker_bash.sh",
+    "docker_build.sh",
+    "docker_clean.sh",
+    "docker_cmd.sh",
+    "docker_exec.sh",
+    "docker_jupyter.sh",
+    "docker_name.sh",
+    "docker_push.sh",
+    "etc_sudoers",
+    "install_jupyter_extensions.sh",
+    "run_jupyter.sh"
+    "version.sh",
+]
+
+
+# #############################################################################
+# Helper functions
+# #############################################################################
+
+
+def _get_source_dir() -> str:
+    """
+    Get the absolute path to the source directory containing Docker files.
+
+    :return: absolute path to class_project/project_template/
+    """
+    # Get the directory where this script is located.
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    _LOG.debug("Script directory='%s'", script_dir)
+    return script_dir
+
+
+def _copy_files(
+    *,
+    src_dir: str,
+    dst_dir: str,
+    files: List[str],
+) -> None:
+    """
+    Copy specified files from source directory to destination directory.
+
+    :param src_dir: source directory path
+    :param dst_dir: destination directory path
+    :param files: list of filenames to copy
+    """
+    # Verify source directory exists.
+    hdbg.dassert_dir_exists(src_dir, "Source directory does not exist:", src_dir)
+    # Create destination directory if it doesn't exist.
+    hio.create_dir(dst_dir, incremental=True)
+    _LOG.info("Copying %d files from '%s' to '%s'", len(files), src_dir, dst_dir)
+    # Copy each file.
+    copied_count = 0
+    for filename in files:
+        src_path = os.path.join(src_dir, filename)
+        dst_path = os.path.join(dst_dir, filename)
+        # Verify source file exists.
+        hdbg.dassert_path_exists(
+            src_path, "Source file does not exist:", src_path
+        )
+        # Copy the file using cp -a to preserve all permissions and attributes.
+        _LOG.debug("Copying '%s' -> '%s'", src_path, dst_path)
+        cmd = f"cp -a {src_path} {dst_path}"
+        hsystem.system(cmd)
+        copied_count += 1
+    #
+    _LOG.info("Successfully copied %d files", copied_count)
+
+
+# #############################################################################
+
+
+def _parse() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description=__doc__,
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+    )
+    parser.add_argument(
+        "--dst_dir",
+        action="store",
+        required=True,
+        help="Destination directory where files will be copied",
+    )
+    hparser.add_verbosity_arg(parser)
+    return parser
+
+
+def _main(parser: argparse.ArgumentParser) -> None:
+    args = parser.parse_args()
+    hdbg.init_logger(verbosity=args.log_level, use_exec_path=True)
+    # Get source directory.
+    src_dir = _get_source_dir()
+    # Copy files to destination.
+    _copy_files(
+        src_dir=src_dir,
+        dst_dir=args.dst_dir,
+        files=_FILES_TO_COPY,
+    )
+
+
+if __name__ == "__main__":
+    _main(_parse())

class_project/data605/Spring2026/projects/UmdTask437_DATA605_Spring2026_DocsGPT/docker_bash.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+# """
+# This script launches a Docker container with an interactive bash shell for
+# development.
+# """
+
+# Exit immediately if any command exits with a non-zero status.
+set -e
+
+# Import the utility functions from the project template.
+GIT_ROOT=$(git rev-parse --show-toplevel)
+source $GIT_ROOT/class_project/project_template/utils.sh
+
+# Parse default args (-h, -v) and enable set -x if -v is passed.
+parse_default_args "$@"
+
+# Load Docker configuration variables for this script.
+get_docker_vars_script ${BASH_SOURCE[0]}
+source $DOCKER_NAME
+print_docker_vars
+
+# List the available Docker images matching the expected image name.
+run "docker image ls $FULL_IMAGE_NAME"
+
+# Configure and run the Docker container with interactive bash shell.
+# - Container is removed automatically on exit (--rm)
+# - Interactive mode with TTY allocation (-ti)
+# - Port forwarding for Jupyter or other services
+# - Git root mounted to /git_root inside container
+CONTAINER_NAME=${IMAGE_NAME}_bash
+PORT=
+DOCKER_CMD=$(get_docker_bash_command)
+DOCKER_CMD_OPTS=$(get_docker_bash_options $CONTAINER_NAME $PORT)
+run "$DOCKER_CMD $DOCKER_CMD_OPTS $FULL_IMAGE_NAME"