metadata

title: research-assistant
app_file: src/research_assistant/web/app.py
sdk: gradio
sdk_version: 5.6.0

Research Assistant

This is a Research Assistant that helps in analyzing and simplifying the content present in a research article, such that you don't have to read the whole thing to understand what knowledge is being presented inside the article. This tool takes care of it and provides you the understanding you would need.

How to run?

Step 1:

First install the requirements

pip install -r requirements.txt
pip install -e .

Step 2:

create a file named keys.yaml following the template present in keys_template.yaml Input your api keys inside keys.yaml and save them

Step 3:

Update the contents in config/config.yaml file. The path for your file name, and the search parameters for articles are present inside the config.yaml file. Before every run, if you want to change the serach configuration or summarization parameters, you need to update the config.yaml file.

Step 4:

The Summarization pipeline can be run in 2 ways:

From Command Line Interface as Pip Package:

Step 1 installs the whole repo as a pip installable package in editable mode in your pip. To access the package and get the summary of the file, run the following command:

research --pipeline_name

From running the Main File:

Confirm the Arguments:

To change the model names, filepath to get the summary, filepath to save the summary, make changes in the config/config.yaml file.

Run the following command

python src/research_assistant/main.py --pipeline_name

Different Pipelines:

There are two pipelies available here:

Summarization Pipeline:

Given a paper, this pipeline gives out the summarization. The paper filepath can be set in config/config.yaml. To activate this pipeline, run the following command:

# If you want to use the package version, run the following command
research --summarize_article

#If you directly want to directly compile in CLI, run the following command
python src/research_assistant/main.py --summarize_article

Searching for Articles:

Given a few keywords, and other parameters, this pipeline will crawl Arxiv and get you the artciles that are relevant for you. To activate this pipeline, run the following command

# If you want to use the package version, run the following command
research --search_articles

#If you directly want to directly compile in CLI, run the following command
python src/research_assistant/main.py --search_articles