aryachakraborty/articulus_rag

Articulus-RAG

Develop - Prototype - Assess - Iterate

🌟 Stars	🍴 Forks	🐛 Issues	🔔 Open PRs	🔕 Close PRs

🌍Project Overview

A platform for empowering transparency in media leverages AI-driven chatbots and content from journalism students to provide credible insights on global affairs, addressing gaps in Indian journalism. Inspired by my struggle to find concise information on India's stance on the Russia-Ukraine conflict during an interview preparation, and concerns about biased media coverage in regions like Manipur and Ladakh, the project aims to promote factual reporting and informed discourse. By offering accurate responses to complex queries and fostering a culture of fact-based reporting, it seeks to mitigate the prevalence of biased or incomplete information in Indian media, promoting transparency, accountability, and knowledge dissemination in the digital age.

✨ Features

- 📰 AI-Driven Chatbots: Get accurate, AI-generated responses to your complex queries. - 🗺️ Global Insights: Access reliable information on global affairs with ease. - 📈 Transparency Promotion: Encourage a culture of factual reporting and reduce biased media coverage. - 🔍 Concise Information: Quickly find summarized information on critical issues. - 📊 Real-Time Updates: Stay informed with the latest news and insights.

🌟Acknowledgements

* [HuggingFace](https://github.com/huggingface) * [LlamaIndex](https://github.com/jerryjliu/llama_index) * [Google Gemini](https://ai.google.dev/) * [AI Planet](https://aiplanet.com/)

and the entire OpenSource community.

Our Contributors ❤️

Thank you for contributing to our repository

Show some ❤️ by starring this awesome repository!

articulus_rag's Issues

Addition of Dockerfile

By this issue, I propose to add a Dockerfile to the repository. This will enable users to easily build and run the project in a containerized environment, improving portability and reproducibility.

Please assign this issue to me.

Add GitHub Desktop Contribution Instructions

I am interested in contributing to the project by adding detailed instructions on how to contribute using GitHub Desktop.

I believe that by providing clear and comprehensive guidance, we can encourage more contributors to participate in the project, especially those who prefer using GitHub Desktop for their contributions.

Could you please assign me the issue related to adding GitHub Desktop contribution instructions under gssoc24? I am excited about the opportunity to contribute to the project and help streamline the contribution process for others.

Fixing the typos

Hey @AryaChakraborty,
I found several typos.
Fox ex:- src/llms/azurechat.py line 62 AI assitant should be AI assistant

Assign this to me, I would like to fix them. Kindly add the GSSOC'24 label and level.

[Feat]: Workflow for closing Old PRs

Is your feature request related to a problem? Please describe.
Over time, open pull requests (PRs) can accumulate in a repository, cluttering the interface and making it difficult to focus on active development tasks. Additionally, outdated or abandoned PRs may no longer serve their intended purpose and should be closed to maintain repository cleanliness.

Describe the solution you'd like
Implement a workflow that automatically closes old PRs based on predefined criteria, such as their last update timestamp. By regularly closing PRs that have not been updated within a certain timeframe, the repository can stay organized, and contributors can focus on active and relevant PRs.

What problem is this feature trying to solve?
This feature aims to automate the management of open PRs in a repository, ensuring that outdated or abandoned PRs are closed in a timely manner. By doing so, it helps maintain repository hygiene, improves workflow efficiency, and provides a better experience for both maintainers and contributors.

Missing CONTRIBUTING.md File in Repository

The repository currently lacks a CONTRIBUTING.md file, which is an important resource for guiding potential contributors on how to engage with the project effectively. A CONTRIBUTING.md file outlines the contribution guidelines, coding standards, and procedures for submitting pull requests, thus streamlining the contribution process and ensuring consistency across contributions.

Could you please assign this issue to me under GSSOC 24.

[Feat]: Auto Commenting when an Issue is Closed

Is your feature request related to a problem? Please describe.
Yes, the feature request is related to the problem of lack of communication and acknowledgment when issues are closed in the repository. Contributors may feel neglected or uncertain about the status of their issues if they are closed without any feedback or acknowledgment. This can lead to frustration and a decrease in motivation to contribute further.

Describe the solution you'd like
The solution is to automatically post a comment on the issue whenever it gets closed. This comment should thank the issue creator for their contribution and inform them that their issue has been closed. The message can include the issue number and a friendly greeting to make it more personal. This automation ensures that every closed issue receives a consistent and timely response, improving communication and contributor experience.

What problem is this feature trying to solve?
This feature aims to solve the problem of poor communication and lack of acknowledgment when issues are closed. By automatically commenting on closed issues, it ensures that contributors are informed about the closure and are thanked for their efforts. This helps maintain a positive and engaging community atmosphere, encouraging continued contributions and fostering good relationships between maintainers and contributors.

Fact-Checking AI Platform

1. Fact-Checking AI Platform
Description: Develop an AI-powered platform that can automatically fact-check news articles and statements made by public figures.
Features:
Real-time analysis of news articles and social media posts.
Integration with large fact-checking databases.
User-friendly interface for journalists and the public to verify information.
Impact: Helps combat misinformation and promotes truthful reporting.

Add Code of Conduct

We recommend that every repo has a code of conduct. If you don’t feel comfortable creating your own Code of Conduct from scratch we highly recommend using one of the templates provided by GitHub. If you do use a template, please read through the template and ensure that you can and will abide by the Code of Conduct.

Please follow these instructions on how to add a Code of Conduct.

Sample: https://github.com/Recode-Hive/Stackoverflow-Analysis/blob/main/CODE_OF_CONDUCT.md

Add multilingual support for users.

Users will be able to ask questions or upload files of their choice for context in Indian regional languages. Further, the response they get will also be in the input language thus making it more accessible for the user.

I would like to work on this functionality under GSSoC'24.

Creating Streamlit App

Enhance Logging for Better Debugging

Description:

The current logging mechanism in the project is minimal and does not provide enough information for debugging. Improving the logging can help developers understand the flow and catch issues more efficiently.

Tasks:

1. Implement logging at different levels (info, debug, error).
2. Add logging statements to key functions to trace the execution flow and capture important variables.

Conflict in requirements.txt file

You ask for pydantic==2.7.1,
but beyondllm 0.2.0 depends on pydantic<2 and >=1.10.5.
So, there is a conflict that needs to be resolved.

Improving the Dockerfile with Multi-Stage Builds

Describe the bug

The present Dockerfile implements a single stage build which is inefficient and using Multi-Stage Build can definitely increase performance by reducing image size significantly. This is done by removing the compiler, build artifacts and other unnecessary components from the final image and only leaving behind the executable.

Fix Bugs

Not applicable

Write Documentation

Comments can be provided in the file itself to understand better

Screenshots

None

Additional context

Please do assign me this issue under gssoc'24

[Feat]: Auto Commenting Feat for Issue Creation

Is your feature request related to a problem? Please describe.
Yes, the feature request is related to a problem. When issues are created in a project, it is important to provide immediate acknowledgment and guidance to the issue creator. However, manually commenting on every newly created issue can be time-consuming for maintainers, leading to delays and inconsistency in communication. This can result in contributors feeling ignored or discouraged from further participation.

Describe the solution you'd like
I would like an automated feature that posts a predefined comment on an issue as soon as it is created. This comment could include acknowledgment of the issue, guidelines for further steps, or any other relevant information. The automation should be customizable to accommodate different project workflows and communication styles.

What problem is this feature trying to solve?
This feature aims to address the problem of delayed and inconsistent communication following the creation of issues. By automatically commenting on issues as soon as they are created, it ensures that contributors receive immediate feedback and acknowledgment for their efforts. This fosters a positive and supportive environment for collaboration, encouraging continued participation and engagement from contributors.

Website not deployed

• Chrome

• Error : 404 Page not found

Enhance the Contributing.md

As the instructions to contribute using GitHub Desktop are missing in the current Contributing.md file, I would like to add those detailed instructions.

I believe that by providing clear and comprehensive guidance, we can encourage more contributors to participate in the project, especially those who prefer using GitHub Desktop for their contributions.

Could you please assign me the issue related to adding GitHub Desktop contribution instructions under gssoc24? I am excited about the opportunity to contribute to the project and help streamline the contribution process for others.

Integrate URL Extractor for Content Analysis

Enhance the existing Streamlit app by adding functionality to extract and analyze content from URLs. This feature will allow users to paste a URL and interact with the AI model to ask questions about the content from the provided URL, similar to the current file upload functionality.

I am Participating in GSSOC'24.

updating readme file

Existing README:

• Project statistics (stars, forks, issues, pull requests) are included but not well-integrated.
• Contributors are mentioned briefly at the end.
• The existing README has visual elements such as badges and tables, but they are not effectively integrated to enhance readability.
• The participation in events like GirlScript Summer of Code is mentioned but not detailed.
• The structure of the existing README is somewhat scattered, with various sections and acknowledgements not clearly separated or organized.
  this are the issue that i solved in my pull request

[Feat]: Auto Commenting feature for PR Merged

Is your feature request related to a problem? Please describe.
Yes, the feature request is related to a problem. When pull requests (PRs) are merged in a project, it is often important to provide consistent feedback or notifications to the contributors. Currently, this process can be manual and time-consuming, leading to inconsistent communication and delayed acknowledgments. This can frustrate both maintainers, who have to remember to comment, and contributors, who might feel their efforts are not promptly recognized.

Describe the solution you'd like
To enhance our communication and acknowledgment process, we're implementing an auto-commenting feature for specific events within our project repository. This feature will automatically generate comments under the following circumstances:
PR Merged: Upon the successful merging of a pull request (PR), an auto-comment will be added to the corresponding issue, indicating that the PR has been merged and expressing gratitude to the contributor for their valuable contribution.

What problem is this feature trying to solve?
This feature aims to solve the problem of inconsistent and delayed communication following the merging of PRs. By automating the commenting process, it ensures that contributors receive timely feedback and acknowledgments. It also reduces the administrative burden on maintainers, allowing them to focus more on code reviews and other critical tasks.

[Feat]: Auto Commenting feature for PR Raised

Is your feature request related to a problem? Please describe.
Yes, the feature request is related to a problem. When contributors raise pull requests (PRs) in a project, it is crucial to provide immediate acknowledgment and feedback to encourage collaboration and maintain transparency. However, manually commenting on every PR can be time-consuming for maintainers, leading to delays and inconsistency in communication. This can result in contributors feeling undervalued or discouraged from further participation.

Describe the solution you'd like
This solution introduces a new GitHub Actions workflow that automatically comments on new and updated pull requests. This feature aims to streamline the contribution process by providing contributors with immediate feedback and guidance upon creating or updating their pull requests.

What problem is this feature trying to solve?
This feature aims to address the problem of delayed and inconsistent communication following the raising of PRs. By automatically commenting on PRs as soon as they are raised, it ensures that contributors receive immediate feedback and acknowledgment for their efforts. This fosters a positive and supportive environment for collaboration, encouraging continued participation and engagement from contributors.

Optimize Retrieval Mechanism for RAG Model

Description:

The current retrieval mechanism may not be optimized for speed and relevance, potentially leading to slower responses and less accurate results. Implementing more efficient retrieval algorithms or indexing methods can improve this.

Tasks:

1. Implement a more efficient indexing method like FAISS.
2. Optimize the retrieval queries for better relevance.
3. Profile and benchmark the performance improvements.

missing Installation steps in readme.md file

Describe the feature

missing Installation steps in readme.md file.
i will add how to install the project in the local system and how to clone it

Implement features

Look through the GitHub issues for features. Anything tagged with "enhancement" and "help wanted" is open to whoever wants to implement it.

If you are proposing a feature:

• Explain in detail how it would work.
• Keep the scope as narrow as possible, to make it easier to implement.
• Remember that this is a volunteer-driven project and that contributions are welcome :)

Write Documentation

We can always use more documentation on the web in blog posts, articles, and such.

Screenshots

If applicable, add screenshots to help explain your problem.

Additional context

Add any other context about the problem here.

Rmove unrequired packages from requirements.txt

Describe the bug

While installing the packages from requirements.txt many files create dependency issues and I have noticed most of them are not even the required packages for running the project.

If you are reporting a bug, please include:

• My operating system is Windows 10
• I tried setting up the file in a conda environment but the file already contains conda packages. So please keep that in mind while contributing to this issue
• For your reference here is the bug I am talking about:
  

Add Topics

In GSSoC'24, GitHub Topics will help the discoverability of your project.

I see that you already have great topics on your repository!
I would recommend adding the name of the company like the software you use to build like "vs-code, ghdesktop" to improve your discoverability.

If you are happy with the topics you have, feel free to close this issue. 👍

Improved README.md

The README.md could be better. It could be rewritten in proper markdown format along with details on how to clone the project and how to contribute to the project.

Increase the efficiency of responses

I would like to try and work on different techniques to increase the efficiency of responses from the model. Please assign this to me.

#3

Making a gradio web app and then deploying it on huggingface spaces

Making a gradio web app which provide the functionality to access it via api call and deploy it on the huggingface hub spaces which is open source. It provides v2 16 gb cpu for free use

Implement features

• Making gradio web app which can be deployed further on huggingface hub space very easily and can be accessed freely.
• Gradio web app will allows us to access the app via API call to the endpoint.
• Frontend of the project can be hosted on vercel and ML models can be accessed by api call from gradio seamlessly.

Additional context

I've previously deployed my gradio web app for my project of Dark Pattern Detection which uses a fine tuned BERT model for multi class classification of dark pattern categories .
Link : https://huggingface.co/spaces/4darsh-Dev/dark_pattern_detector_app_v2

Add issues

As the maintainer of a Collaborate repo, keeping Issues up-to-date will help the student community understand what they can do to contribute. Issues should vary by the easy (update documentation) to the difficult (add a new feature). The more involved you are, the more opportunities there are to collaborate.

Recommendations:

Add issues of varying difficulty to the repo often. you must add the tag GSSoC'24, Level 1, Level2, Level 3 good first issue etc.
How we cacluclate the Scores on Leaderboard: Every PR one point
Level 1: 10 points
Level 2: 25 points
Level 3: 45 points
Try to add some documentation issues as well it would be easy for beginner contributor to explore opensource through your repo.
Generate issues even if you plan on solving them, so the repository appears as active.
Contribute/commit often to the repo so it does not go stale.
Reference https://github.com/Recode-Hive/Stackoverflow-Analysis/issues

Enhancing the search algorithm

This app can make use of ranking algorithms

Adding new feature for auto commenting on new PR raised.

Describe the feature

This will add a feature to give instant comment to user after raising a PR

Explanation

When we get comments on pull requests right after they're submitted, it shows us contributors that the admins are paying attention and appreciating our hard work. This helps create a friendly atmosphere where teamwork thrives, making everyone more likely to keep pitching in and staying involved.
This feature aims to address the problem of delayed and inconsistent communication following the raising of PRs
Could you please assign me this issue under GSSOC'24 and appropriate level too

Thank You

Input Validation and Sanitization:

To insure that all incoming data is validated and sanitized to prevent potential security issues such as SQL injection or XSS attacks.

Add PR template

I would like to add a pull request template for this repository. I believe that having a standardized template will help streamline the contribution process, ensuring that all necessary information is included and making it easier for maintainers to review and merge pull requests.

Could you please assign this issue to me under GSSOC'24.

Add templates for issues

Issue templates are very helpful for a collaboration repo. When users identify a bug or want to add a new feature, you can provide templates so you can collect all the pertinent information you need to fix a bug or add a new feature.

We recommend creating a “Report Bug” and “Feature Request” issue template.
you can refer this: https://docs.github.com/en/communities/using-templates-to-encourage-useful-issues-and-pull-requests/configuring-issue-templates-for-your-repository

Some suggested prompts/questions you can add to a “Report Bug” template are:

Briefly describe the bug
What is the expected behavior?
Please provide step by step instructions on how to reproduce the bug
Some suggested prompts/questions you can add to a “Feature Request” issue template are:

Briefly describe your feature request
What problem is this feature trying to solve?
How do we know when the feature is complete?

Reference: https://github.com/Recode-Hive/Stackoverflow-Analysis/issues/new/choose
Click on Get Started button and copy the template to yours.

[FEAT]: Create Issue forms and make the issue options more visually appealing

Currently, there is an issue template for this repo, but no issue form which will help users in contributing.

• I will add Issue Forms to the respective issues to make it easier for the contributor to raise it.

Here is an example of how a Bug Issue Form will look like 👇

• and issue templates:

Enhance Readme.md file

Hey @AryaChakraborty the readme file can be more enhanced and updated , adding more features , guidelines . As Readme file plays an important role in user/Contributor convenience .
Kindly assign this issue to me under GSSoC'24 .

Learn.md

Learn repos should have a LEARN.md file to teach student how to build your project step by step. You can explain how to build your project with text, code snippets, images, or even short (5 minute) long video lessons. As the maintainer of a Learn repo, the LEARN.md file requires you to think critically about how to explain the building of your project and how to also make it engaging. We don't expect you to be an expert teacher, but we would like you to reflect on how difficult it was to get to your level of knowledge, and then provide friendly guidance to help other students to learn.

Reference: https://github.com/Recode-Hive/Stackoverflow-Analysis/blob/main/Learn.md

Creating a PULL_REQUEST_TEMPLATE.md

Creating a pull request template for the project to make this repository suitable for Github community standards.

What will it have ?

1. Brief Description
2. Issue it addresses or closes
3. Checklist for (tested locally, necessary documentation , etc.)
4. Screenshots and Additional notes

Plz Assign it to me under gssoc 24 contributor

Request to update the readme file

I would like to update the readme file by adding setup and installation process like how they can clone the project, how to make PR in project and so on many such things so the contributors can know how to do it. It will help many other who visits the project. Below I've attached the image please refer it.

Girlscript Summer of Code Introduction/Tracking

👋 Hi @AryaChakraborty ,

I am Prince,web developer Girlscript Summer of Code. I'll be collaborating with you on preparing your repo for GSSoC'24 Program

Why are these changes required?
After Analysing last year's contributions and feedback it would be great for students to have a couple of standard readme files on the repo to understand what the project is all about and some issues detailing what they can contribute. This will help you to see increased engagement in your repository as well.

As mentioned students get a chance to learn step by step, how to build this project as well as invite mentors to collaborate and add features to this repo. I will generate issues, which will provide guidance on how to prepare your repo for Girlscript summer of code 2024 on 10th May.

This issue will serve as a tracking issue to track all issues related to GSSoC'24. I recommend creating a new branch for every issue and opening a pull request to track changes so we can effectively collaborate with each other and merge changes when you and I feel like those changes are ready to be merged on your primary branch.

If you have any questions or concerns, please feel free to leave a comment on this issue or any of the other issues that are generated.

I look forward to working with you

• #1
• #2
• #3
• #4
• #5

[Feat]: Workflow for Closing Old Issues

Is your feature request related to a problem? Please describe.
Over time, repositories can accumulate a large number of open issues, including some that may no longer be relevant or actively worked on. Manually closing these old issues can be time-consuming and tedious.

Describe the solution you'd like
I would like a workflow that automatically identifies and closes old issues based on certain criteria, such as no recent activity or being open for a specific duration.

What problem is this feature trying to solve?
This feature aims to automate the process of managing old issues, ensuring that the repository remains organized and focused on relevant tasks. By automatically closing old issues, it reduces manual overhead for repository maintainers and helps keep the issue tracker tidy and up-to-date.

Documentaion :- i will add use techstack in the readme file

Describe the feature

clear mention techstack uses in the project

Implement features

i will ad it readme file

Add issues template for documentation issues

I would like to add a issues template for documentation issues in this repository. I believe that having a standardised template will help streamline the contribution process, ensuring that all necessary information is included and making it easier for maintainers to review issues.

Could you please assign this issue to me under GSSOC'24.

[Feat]: Workflow for closing issues on merging PR linked to that issue

Describe the feature

As the repo maintainers have to manually close an issue after merging a PR linked with that issue, I propose a workflow where the issue linked with a PR which be automatically closed when that PR is merged by the maintainer and efforts will be saved.