https://github.com/nav3005/cold_email_generator
Project to implement generation of Cold Mail for Buisness proposals with the use of LLM and Vector Embedding
https://github.com/nav3005/cold_email_generator
Last synced: 9 months ago
JSON representation
Project to implement generation of Cold Mail for Buisness proposals with the use of LLM and Vector Embedding
- Host: GitHub
- URL: https://github.com/nav3005/cold_email_generator
- Owner: Nav3005
- License: apache-2.0
- Created: 2024-09-06T13:22:39.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-09-09T15:28:29.000Z (almost 2 years ago)
- Last Synced: 2024-12-27T12:27:05.135Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 365 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Cold Email Generator
## Overview
The Cold Email Generator leverages LLM to create personalized cold emails with ease. By integrating Llama 3.1, Langchain, Groq and other powerful tools, this project offers a streamlined interface for generating customized emails based on user input and predefined templates.
## Features
- **Automated Email Generation**: Generate cold emails using AI.
- **Customizable Templates**: Tailor the email content to match specific industries or business needs.
- **User-friendly Interface**: Built with Streamlit for an intuitive user experience.
- **API Integration**: Uses Groq API for enhanced language processing.
## Technologies Used
- **Llama 3.1 (LLM)**: Large language model for generating human-like email content.
- **Langchain**: A framework for developing applications powered by language models.
- **Groq API**: Integrates Groq's powerful API to enhance language model capabilities.
- **ChromaDB**: Store vector embeddings for fast retrieval.
- **Jupyter Notebook**: Used for prototyping and experimenting with different AI models.
- **Streamlit**: Web application framework for creating a simple and interactive user interface.
## Architecture Model
## Installation
To get started with this project, follow these steps:
1. **Clone the repository**:
```bash
git clone https://github.com//.git
cd
2. **Create a virtual environment** (optional but recommended):
```bash
python -m venv venv
3. **Activate the virtual environment**:
- On macOS/Linux:
```bash
source venv/bin/activate
```
- On Windows:
```bash
venv\Scripts\activate
```
4. **Set up the Groq API key**:
- Obtain your API key from [Groq](https://console.groq.com/docs/quickstart) and set it as an environment variable:
```bash
export GROQ_API_KEY=your_api_key
```
5. **Run the Streamlit app**:
```bash
streamlit run app.py
## References:
- [ChatGroq](https://python.langchain.com/v0.2/docs/integrations/chat/groq/)
- [Vector Database](https://www.qwak.com/post/utilizing-llms-with-embedding-stores#:~:text=Vector%20embeddings%20are%20essential%20in,in%20a%20high%2Ddimensional%20space.)
- [LLM Embedding](https://pub.aimind.so/llm-embeddings-explained-simply-f7536d3d0e4b)
- [Python Environment](https://pypi.org/project/python-dotenv/)