https://github.com/bhuvanmdev/PhoneIT
An application that when deployed can establish a call service, where an AI agent can solve any query of the users using a established RAG pipeline and subsequently the system is centralized using a web platform, for ease of use and monitoring for the service hoster.
https://github.com/bhuvanmdev/PhoneIT
aiml huggingface llms reactjs twilio
Last synced: 3 months ago
JSON representation
An application that when deployed can establish a call service, where an AI agent can solve any query of the users using a established RAG pipeline and subsequently the system is centralized using a web platform, for ease of use and monitoring for the service hoster.
- Host: GitHub
- URL: https://github.com/bhuvanmdev/PhoneIT
- Owner: bhuvanmdev
- License: apache-2.0
- Created: 2024-09-30T16:06:06.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-21T12:46:46.000Z (12 months ago)
- Last Synced: 2025-01-06T00:34:47.400Z (11 months ago)
- Topics: aiml, huggingface, llms, reactjs, twilio
- Language: TypeScript
- Homepage:
- Size: 21 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome_ai_agents - Phoneit - An application that when deployed can establish a call service, where an AI agent can solve any query of the users using a established RA… (Building / Deployment)
README
## PhoneIT
An application that when deployed can establish a call service, where an AI agent can solve any query of the users using an established RAG pipeline. The system is centralized using a web platform for ease of use and monitoring for the service hoster.
## Features
- Utilizes various open-source models like [indictrans2](https://huggingface.co/ai4bharat/indictrans2-en-indic-dist-200M) for multi-lingual efficiency and performance.
- Contains an efficient RAG pipeline ensuring the AI provides factual information via a vector DB(FAISS).
- Integrated with Twilio API.
- Currently the cheapest option in the market as of its creation time.
- The demo video of the application is [here](https://drive.google.com/file/d/1wGkpXcnw34UwOZg-EefB1Ji6S1SCTpBq/view?usp=sharing).
## Installation
### Running Only the Application
1. Create a Python virtual environment (version <= 3.10).
2. Install the required dependencies:
```bash
pip install -r requirements.txt
```
3. Update the required details in the `.env` file present in the same directory.
4. Run the application:
```bash
python final.py
```
### Running with Web Interface
1. Install Node.js and npm.
2. Navigate to the web interface directory:
```bash
cd website
```
3. Install dependencies:
```bash
npm install
```
4. Run the development server:
```bash
npm run dev
```
5. Open [http://localhost:3000](http://localhost:3000) in your browser to see the result.
## Contributing
This project was developed within 1-2 days. Hence, any kind of suggestions and upgrades are appreciated 🙂.
## License
This project is licensed under the Apache 2.0 License.