Skip to main content

Summarize Research Papers from the Command Line

Level: Intermediate · Time: 35–45 min · Category: Command line

Tags: Python · OpenAI SDK · PDF · Summarization

Build a CLI that reads a PDF and asks the Research Computing OpenAI-compatible API for a structured summary: the problem, the approach, the key findings, and the limitations. It is a practical tool for reading groups and literature reviews.

Prerequisites​

Confirm Python 3 and pip are available before you start:

python3 --version      # expect 3.9 or newer
python3 -m pip --version

If Python is not found, install it from python.org. On the supercomputer, load a Python module instead (for example module load python), then run the checks again.

What you will do​

  • Create a Python CLI workspace with the OpenAI SDK and a PDF reader.
  • Extract text from a PDF file.
  • Ask the API for a structured, section-by-section summary.
  • Add batch mode and a markdown export.

Build it step by step​

1. Create the CLI workspace​

Install the OpenAI SDK, an environment loader, a PDF reader, and a terminal formatter.

mkdir paper-summarizer
cd paper-summarizer
python3 -m venv .venv
source .venv/bin/activate
pip install openai python-dotenv pypdf rich
Keep this out of Git

If you track this project with Git, do not commit your virtual environment or any secrets. Create a .gitignore file in the project folder with at least these lines:

.gitignore
.venv/
.env
__pycache__/

.venv/ is large and specific to your machine, and .env holds your API key — neither belongs in a shared repository. New to Git? See Track a New Project with Git.

2. Add API connection values​

Your program needs three values to reach the API: your API key, the gateway URL, and a model ID. You keep them in a small text file named .env so they stay out of your code — and out of Git.

What is a .env file, and where does it go?

A .env ("dot-env") file is a plain text file that stores settings as NAME=value lines, one per line. Programs read it at startup so you never have to paste secrets like API keys directly into your code.

  • The filename is literally .env — a leading dot with nothing before it (not config.env or .env.txt).
  • It goes in your project folder: the same directory you just created, where the .venv lives and where you run your commands.
  • The python-dotenv package loads it with load_dotenv(), which looks for .env in the folder you run the program from.
  • Because it holds a secret, never commit it to Git (see the note below).

Create a new file named .env in your project folder — in VS Code use File → New File, or run code .env in the terminal — then paste these three lines and replace the placeholders:

.env
OPENAI_API_KEY="paste-your-key-here"
OPENAI_BASE_URL="https://openai.rc.asu.edu/v1"
RC_LLM_MODEL="paste-model-id-here"
Where do the values come from?

Get your API key and a valid model ID from the LLM API guide. The OPENAI_BASE_URL above is already correct for the Research Computing gateway.

  • Use the /v1 base URL, not the full /chat/completions URL, for the Python SDK.
  • Use a model ID that appears in the portal model list for your account.
  • Keep .env out of Git: add a line containing .env to your .gitignore (see Track a New Project with Git).

3. Extract text from a PDF​

Test extraction before involving the model. Put a sample paper named paper.pdf in the folder, then confirm the reader works.

python -c "from pypdf import PdfReader; r = PdfReader('paper.pdf'); print(len(r.pages), 'pages')"

If you see a page count, the extraction step works and you can move on.

4. Ask for the first summarizer​

Name the SDK, the input, and the output you want. Keep the first version to a single readable summary.

You are helping me build a beginner Python CLI that summarizes a research paper using an OpenAI-compatible API.

Project goal:
- Command: python summarize.py paper.pdf
- Read text from the PDF with pypdf.
- Send the text to the chat completions API through the OpenAI Python SDK.
- Print a readable summary to the terminal with rich.
- Read OPENAI_API_KEY, OPENAI_BASE_URL, and RC_LLM_MODEL from a .env file.

Constraints:
- Keep the first version in one file named summarize.py.
- If the extracted text is very long, truncate it to a safe character limit for now.
- Add friendly errors for a missing file, missing API key, or API failure.

Please:
1. Create summarize.py.
2. Explain how the API request is assembled.
3. Show the command to run it on paper.pdf.

5. Ask for structured output​

Consistent sections make summaries easy to compare across papers.

Please improve the summarizer to return consistent sections:

Sections:
- Problem
- Methods
- Key findings
- Limitations
- Why it matters

Constraints:
- Ask the model to use exactly these headings.
- If the paper is long, summarize it in parts and then combine the parts into one final summary.
- Explain how to test it on a long paper.

6. Add one feature of your own​

Choose a single improvement that makes the tool more useful.

Please add one focused feature to the summarizer:

Feature:
- Add a --save option that writes the summary to a markdown file next to the PDF.

Constraints:
- Keep the default terminal output unchanged when --save is not used.
- Keep the code beginner-readable.
- Explain how to test the new option.

More prompts to try​

  • Add a --batch folder option that summarizes every PDF in a folder.
  • Add a --questions option that answers a few specific questions about the paper.
  • Add a short "one-sentence takeaway" line at the top of each summary.

Troubleshooting​

  • If extraction returns almost no text, the PDF may be scanned images. Those need OCR, which is beyond this tutorial.
  • If a PDF is password protected, pypdf will fail. Use an unlocked copy.
  • If the request is rejected for length, lower the truncation limit or use the part-by-part approach from step 5.
  • Always read the summary against the paper. Models can miss or overstate findings.

Next steps​