Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/markphamm/alcon-chatbot
Alcon Financial Analysis: Interactive dashboard with RAG-powered chatbot for Alcon's competitive financial insights.
https://github.com/markphamm/alcon-chatbot
financial pygwalker rag streamlit
Last synced: 3 months ago
JSON representation
Alcon Financial Analysis: Interactive dashboard with RAG-powered chatbot for Alcon's competitive financial insights.
- Host: GitHub
- URL: https://github.com/markphamm/alcon-chatbot
- Owner: MarkPhamm
- Created: 2024-10-05T04:37:02.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-10-18T03:48:38.000Z (3 months ago)
- Last Synced: 2024-10-18T05:33:10.617Z (3 months ago)
- Topics: financial, pygwalker, rag, streamlit
- Language: Python
- Homepage: https://alcon-chatbot.streamlit.app/
- Size: 170 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Alcon Financial Competitors Analysis App
## Overview
This Streamlit application provides a comprehensive financial analysis tool for Alcon and its competitors. It offers various features including financial data visualization, a chatbot for queries, and configuration management.
## Features
1. **Financial Data Visualization**
- Income Statement Analysis (Annual and Quarterly)
- Balance Sheet Analysis (Annual and Quarterly)
- Cash Flow Analysis (Annual and Quarterly)
- Interactive charts using Plotly and Pygwalker
2. **RAG-powered Chatbot**
- AI-powered assistant for financial queries
- Utilizes OpenAI's GPT model and Chroma vector database for retrieval-augmented generation
- Provides context-aware responses based on up-to-date financial data
- **RAG Architecture**
4. **Configuration Management**
- Add or remove ticker symbols for analysis
- Run ETL (Extract, Transform, Load) pipeline
- Populate Vector Database for enhanced chatbot performance
## Installation
1. Clone the repository:
```
git clone [repository-url]
```
2. Navigate to the project directory:
```
cd [project-directory]
```
3. Create a virtual environment:
```
python -m venv .venv
```
4. Activate the virtual environment:
- On Windows:
```
.venv\Scripts\activate
```
- On macOS and Linux:
```
source .venv/bin/activate
```
5. Install required dependencies:
```
pip install -r requirements.txt
```
6. Set up environment variables:
- Create a `.env` file in the root directory
- Add your OpenAI API key:
```
OPENAI_API_KEY=your_api_key_here
```
## Usage
1. Run the Streamlit app:
```
streamlit run app.py
```
2. Navigate through different sections using the sidebar:
- Income Statement
- Balance Sheet
- Cash Flow
- Chatbot
- Configs
3. In the visualization sections, you can:
- Select specific companies for comparison
- Choose between annual and quarterly data
- Create custom charts using Plotly or Pygwalker
4. Use the Chatbot for financial queries related to the loaded data
5. In the Configs section, you can:
- Add or remove ticker symbols
- Run the ETL pipeline to update data
- Populate the vector database for improved chatbot responses
## Data Sources
The application uses financial data stored in CSV files:
- `annually_income_statement.csv`
- `annually_balance_sheet.csv`
- `annually_cash_flow.csv`
- `quarterly_income_statement.csv`
- `quarterly_balance_sheet.csv`
- `quarterly_cash_flow.csv`
## Dependencies
- Streamlit
- OpenAI
- LangChain
- Pandas
- Plotly
- Pygwalker
- Chroma
## Customization
You can modify the `config.py` file to change the list of tracked tickers and update the color theme for visualizations.
## Note
Ensure that you have the necessary permissions and comply with the terms of service for all data sources and APIs used in this application.