Project Info
This project did not submit a demo video on Devpost.
Inspiration
In today's fast-paced tech world, finding the right talent efficiently is crucial. Traditional hiring processes are time-consuming and often biased. We created BharteeAI to revolutionize technical hiring, making it faster, fairer, and more effective.
What it does
BharteeAI is an end-to-end AI-powered interview platform that: Screens resumes using advanced NLP and vector search Conducts real-time video interviews with an AI interviewer Assesses coding skills with an in-browser IDE Generates comprehensive candidate evaluations Provides a seamless experience for both employers and candidates
How we built it
We leveraged cutting-edge technologies to create a robust, scalable solution: Frontend: Reflex (Python-based reactive framework) Backend: Reflex (FastAPI) Database: SingleStore for lightning-fast queries Vector Database: ChromaDB for efficient similarity search AI/ML: Groq for natural language processing Voice Processing: VAPI (Cartesia for TTS, Deepgram for STT) Video Integration: Agora Cloud Storage: AWS S3 Deployment: DigitalOcean App Platform
Challenges we ran into
Integrating multiple AI services seamlessly Ensuring real-time performance for video and coding assessments Balancing AI automation with a human-like interview experience
Accomplishments we're proud of
Created a fully automated yet personalized interview process Developed a scalable architecture capable of handling high-volume hiring Implemented bias-reduction techniques in candidate evaluation
What we learned
The intricacies of AI-human interaction in high-stakes scenarios Optimizing performance in distributed systems Balancing technical assessment with soft skills evaluation
What's next
for BharteeAI Expanding language support for global hiring Integrating more specialized technical assessments Developing an AI training module for interviewers Join us in reshaping the future of technical hiring with BharteeAI!
BharteeAI
BharteeAI is an AI-powered interview platform that helps companies streamline their hiring process by conducting automated technical interviews.
Features
- AI-driven interview questions generation
- Real-time code execution during interviews
- Resume screening and matching
- Video and voice integration for remote interviews
- Comprehensive interview analysis and reporting
Installation
-
Clone the repository:
git clone https://github.com/yourusername/bharteeai.git cd bharteeai -
Create a virtual environment and activate it:
python -m venv venv source venv/bin/activate # On Windows, use `venv\Scripts\activate` -
Install the required packages:
pip install -r requirements.txt -
Set up your environment variables: Copy the
.env.examplefile to.envand fill in your API keys and other configuration details. -
Run the application:
reflex run
Testing
Run the test suite using pytest:
pytest
Deployment
Follow the deployment instructions in the documentation to deploy BharteeAI to your preferred hosting platform.
Contributing
Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Analysis
View
Metric
No commits on this project resolved to a GitHub account.
Technology
- PythonIn code
- SQLIn code
- FastAPIClaimed
2 of 3 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
11 MB
Source files
1,063
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
sahiljagtap08/main-calhacks-bhartee
1,231 files · 13.6 MB · @ c21e83b
Structure
Interface
16 files · 1%Screens, components and styles rendered to the user.
API & routing
3 files · 0%Request entry points: routes, handlers and controllers.
Application logic
1,100 files · 89%Domain rules, services and shared utilities.
+5 moreData & schema
27 files · 2%Schema definitions, migrations and data access.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Python100%
- SQL0%
- Markdown0%
- YAML0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
requirements.txt
pypi · 12- agora-token-builder
- boto3
- chromadb
- clerk_backend_api
- groq
- httpx
- pytest
- pytest-asyncio
- python-dotenv
- reflex
- singlestoredb
- uvicorn
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.