Connect with us

Jobs & Careers

Make Sense of a 10K+ Line GitHub Repos Without Reading the Code

Published

on


How I Made Sense of a 10K+ Lines GitHub Repo Without Reading the Code
Image by Author | Canva

 

Navigating and understanding large codebases can be challenging, especially for new developers joining a project or when revisiting older repositories. Traditional methods of understanding code structures involve reading through numerous files and documentation, which can be time-consuming and error-prone. GitDiagram offers a solution by converting GitHub repositories into interactive diagrams, providing a visual representation of the codebase’s architecture. This tool helps in understanding complex systems, and enhancing collaboration among development teams. In this article, I will walk you through the step-by-step process of using GitDiagram locally. So, without any further wait, let’s get started.

 

Step-by-Step Guide to Using GitDiagram Locally

 

Step 1: Clone the GitDiagram repository

git clone https://github.com/ahmedkhaleel2004/gitdiagram.git
cd gitdiagram

 

Step 2: Install Dependencies

This fetches and installs dependencies into node_modules.

 
Before running pnpm install, make sure you have Node.js and pnpm installed globally.

  • To install Node.js, download it from nodejs.org
  • To install pnpm, run the following command:
  •  

 

Step 3: Set Up Environment Variables

 
Edit the .env file to include your OpenAI / Anthropic /OpenRouter API key and, optionally, your GitHub personal access token.

 

Step 4: Start Backend Services

docker-compose up --build -d

 
The FastAPI server will be available at localhost:8000. You will see the following message at the server side.

{"message":"Hello from GitDiagram API!"}

 

Step 5: Initialize the Database

Run the following commands to set up the database:

chmod +x start-database.sh
./start-database.sh
pnpm db:push

 
When prompted to generate a random password, input yes. The Postgres database will start in a container at localhost:5432.
Note: When I tried to run this command, I got this error:

sh: drizzle-kit: command not found
 ELIFECYCLE  Command failed.
 WARN   Local package.json exists, but node_modules missing, did you mean to install?

 
Turns out I hadn’t installed drizzle-kit. So if you see this, just run:

 
After that, pnpm db:push worked fine and gave me this output:

No config path provided, using default 'drizzle.config.ts'
Reading config file '/Users/kanwal/Desktop/gitdiagram/drizzle.config.ts'
Using 'postgres' driver for database querying
[✓] Pulling schema from database...
[✓] Changes applied

 

Step 6: Run the Frontend

 
You can now access the website at localhost:3000 and edit the rate limits defined in backend/app/routers/generate.py in the generate function decorator. Let’s try to visualize the github repo of the fastapi library.

Frontend Interface:
 
Frontend Interface
 

Output:
 
Output

 

Concluding Thoughts

 
This is a great idea and a really useful repository. I’ve personally felt the need for something like this in my own projects, so I appreciate the effort and vision behind it.

That said, offering an unbiased opinion—there’s definitely room for improvement.

One recurring issue I ran into was:

Syntax error in text mermaid version 11.4.

 
According to the project owner ahmedkhaleel2004, this error usually means the LLM generated invalid Mermaid.js syntax.

 

I’ve tried addressing this issue in numerous ways, but ultimately, I find that there is no reliable fix—it’s mostly a limitation of the LLM. If there were a way to validate Mermaid.js code, that would help, but as of now, I’m not sure how.

 

He also noted that the current prompt (in `prompts.py`, specifically the third one that generates Mermaid code) already tries to enforce correct syntax—but it’s not foolproof, and new syntax issues still occur.

A Solution I Found Online That Worked
While digging through the GitHub Issues, I came across a workaround shared by another user that actually worked for me:

 

Add this to the customize diagram prompt:Ignore the syntax issue from Mermaid version 11.4.1 and regenerate the remainder of the diagram.

 

Using that line helped bypass the error. Even though some components might still be missing, it at least produced a partial diagram—enough to give a high-level understanding of the codebase.
 
 

Kanwal Mehreen Kanwal is a machine learning engineer and a technical writer with a profound passion for data science and the intersection of AI with medicine. She co-authored the ebook “Maximizing Productivity with ChatGPT”. As a Google Generation Scholar 2022 for APAC, she champions diversity and academic excellence. She’s also recognized as a Teradata Diversity in Tech Scholar, Mitacs Globalink Research Scholar, and Harvard WeCode Scholar. Kanwal is an ardent advocate for change, having founded FEMCodes to empower women in STEM fields.



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Jobs & Careers

Canva Partners With NCERT to Launch AI-Powered Teacher Training

Published

on


Canva has signed a memorandum of understanding (MoU) with the National Council of Educational Research and Training (NCERT) to launch free teacher training and certification programs hosted on the education ministry’s DIKSHA platform. 

The initiative aims to enhance digital literacy, creativity, and AI proficiency among educators across India, in alignment with the objectives of the National Education Policy (NEP) 2020.

As part of the agreement, Canva will offer Indian teachers free access to its education platform and provide learning materials tailored for visual and collaborative instruction. NCERT will ensure that the course content aligns with the national curriculum and is made regionally accessible. Available in multiple Indian languages, the course will also be broadcast via PM e-Vidya DTH channels to extend its reach beyond internet-enabled classrooms.

The certification program includes training on using Canva’s design tools to create engaging lesson plans, infographics, and presentations. Teachers will also learn to co-create content with students and apply AI tools to improve classroom outcomes. Upon completion, participants will receive a joint certificate from NCERT and Canva.

“This partnership is a powerful step toward equipping educators with practical digital skills that not only save time but spark imagination in every classroom,” Jason Wilmot, head of education at Canva, said in a press statement.

Chandrika Deb, country manager for India at Canva stated, “By delivering this program free of cost, in multiple languages, and through a trusted national platform like NCERT, we are not only advancing digital fluency and creative confidence in classrooms across the country, but also deepening Canva’s long-term commitment to India, which plays a pivotal role in our vision to democratize design and creativity at scale.”

Moreover, the company shared some interesting figures. Canva has seen significant global momentum, with over 100 million students and teachers using its platform. In 2024, over 1 billion designs were created, many powered by Canva’s AI tools like Dream Lab, which enables teachers to generate custom visuals instantly. Teacher usage of AI tools has increased by 50% over the past year, with student engagement rising by 107%.

We may see further developments in this partnership as the training program for teachers progresses over time.



Source link

Continue Reading

Jobs & Careers

Capgemini to Acquire WNS for $3.3 Billion with Focus on Agentic AI

Published

on


Capgemini has announced a definitive agreement to acquire WNS, a mid-sized Indian IT firm, for $3.3 billion in cash. This marks a significant step towards establishing a global leadership position in agentic AI.

The deal, unanimously approved by the boards of both companies, values WNS at $76.50 per share—a premium of 28% over the 90-day average and 17% above the July 3 closing price.

The acquisition is expected to immediately boost Capgemini’s revenue growth and operating margin, with normalised EPS accretion of 4% by 2026, increasing to 7% post-synergies in 2027.

“Enterprises are rapidly adopting generative AI and agentic AI to transform their operations end-to-end. Business process services (BPS) will be the showcase for agentic AI,” Aiman Ezzat, CEO of Capgemini, said. 

“Capgemini’s acquisition of WNS will provide the group with the scale and vertical sector expertise to capture that rapidly emerging strategic opportunity created by the paradigm shift from traditional BPS to agentic AI-powered intelligent operations.”

Pending regulatory approvals, the transaction is expected to close by the end of 2025.

WNS’ integration is expected to strengthen Capgemini’s presence in the US market while unlocking immediate cross-selling opportunities through its combined offerings and clientele. 

WNS, which reported $1.27 billion in revenue for FY25 with an 18.7% operating margin, has consistently delivered a revenue growth of around 9% over the past three fiscal years.

“As a recognised leader in the digital BPS space, we see the next wave of transformation being driven by intelligent, domain-centric operations that unlock strategic value for our clients,” Keshav R Murugesh, CEO of WNS, said. “Organisations that have already digitised are now seeking to reimagine their operating models by embedding AI at the core—shifting from automation to autonomy.”

The companies expect to drive additional revenue synergies between €100 million and €140 million, with cost synergies of up to €70 million annually by the end of 2027. 

“WNS and Capgemini share a bold, future-focused vision for Intelligent Operations. I’m confident that Capgemini is the ideal partner at the right time in WNS’ journey,” Timothy L Main, chairman of WNS’ board of directors, said.

Capgemini, already a major player with over €900 million in GenAI bookings in 2024 and strategic partnerships with Microsoft, Google, AWS, Mistral AI, and NVIDIA, aims to solidify its position as a transformation partner for businesses looking to embed agentic AI at scale.



Source link

Continue Reading

Jobs & Careers

Piyush Goyal Announces Second Tranche of INR 10,000 Cr Deep Tech Fund

Published

on


IIT Madras and its alumni association (IITMAA) held the sixth edition of their global innovation and alumni summit, ‘Sangam 2025’, in Bengaluru on 4 and 5 July. The event brought together over 500 participants, including faculty, alumni, entrepreneurs, investors and students.

Union Commerce and Industry Minister Shri Piyush Goyal, addressing the summit, announced a second tranche of ₹10,000 crore under the government’s ‘Fund of Funds’, this time focused on supporting India’s deep tech ecosystem. “This money goes to promote innovation, absorption of newer technologies and development of contemporary fields,” he said. 

The Minister added that guidelines for the fund are currently being finalised, to direct capital to strengthen the entire technology lifecycle — from early-stage research through to commercial deployment, not just startups.. 

He also referred to the recent Cabinet decision approving $12 billion (₹1 lakh crore) for the Department of Science and Technology in the form of a zero-interest 50-year loan. “It gives us more flexibility to provide equity support, grant support, low-cost support and roll that support forward as technologies get fine-tuned,” he said.

Goyal said the government’s push for indigenous innovation stems from cost advantages as well. “When we work on new technologies in India, our cost is nearly one-sixth, one-seventh of what it would cost in Switzerland or America,” he said.

The Minister underlined the government’s focus on emerging technologies such as artificial intelligence, machine learning, and data analytics. “Today, our policies are structured around a future-ready India… an India that is at the forefront of Artificial Intelligence, Machine Learning, computing and data analytics,” he said.

He also laid out a growth trajectory for the Indian economy. “From the 11th largest GDP in the world, we are today the fifth largest. By the end of Calendar year 2025, or maybe anytime during the year, we will be the fourth-largest GDP in the world. By 2027, we will be the third largest,” Goyal said.

Sangam 2025 featured a pitch fest that saw 20 deep tech and AI startups present to over 250 investors and venture capitalists. Selected startups will also receive institutional support from the IIT Madras Innovation Ecosystem, which has incubated over 500 ventures in the last decade.

Key speakers included Aparna Chennapragada (Chief Product Officer, Microsoft), Srinivas Narayanan (VP Engineering, OpenAI), and Tarun Mehta (Co-founder and CEO, Ather Energy), all IIT Madras alumni. The summit also hosted Kris Gopalakrishnan (Axilor Ventures, Infosys), Dr S. Somanath (former ISRO Chairman) and Bengaluru South MP Tejasvi Surya.

Prof. V. Kamakoti, Director, IIT Madras, said, “IIT Madras is committed to playing a pivotal role in shaping ‘Viksit Bharat 2047’. At the forefront of its agenda are innovation and entrepreneurship, which are key drivers for National progress.”

Ms. Shyamala Rajaram, President of IITMAA, said, “Sangam 2025 is a powerful confluence of IIT Madras and its global alumni — sparking bold conversations on innovation and entrepreneurship.”

Prof. Ashwin Mahalingam, Dean (Alumni and Corporate Relations), IIT Madras, added, “None of this would be possible without the unwavering support of our alumni community. Sangam 2025 embodies the strength of that network.”



Source link

Continue Reading

Trending