https://github.com/thomasjanssen-tech/data-analyst-ai-agent
Build an AI Agent which analyses .CSV files you provide it.
https://github.com/thomasjanssen-tech/data-analyst-ai-agent
agent ai langchain llm openai streamlit
Last synced: 2 months ago
JSON representation
Build an AI Agent which analyses .CSV files you provide it.
- Host: GitHub
- URL: https://github.com/thomasjanssen-tech/data-analyst-ai-agent
- Owner: ThomasJanssen-tech
- Created: 2025-03-07T11:17:39.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-07T11:22:08.000Z (over 1 year ago)
- Last Synced: 2025-03-07T12:27:29.835Z (over 1 year ago)
- Topics: agent, ai, langchain, llm, openai, streamlit
- Language: Python
- Homepage: https://thomasjanssen.tech/
- Size: 1.03 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: readme.md
Awesome Lists containing this project
README
Build an AI Agent Data Analyst
Watch the full tutorial on my YouTube Channel
Prerequisites
- Python 3.11+
Installation
1. Clone the repository:
```
git clone https://github.com/ThomasJanssen-tech/Data-Analyst-AI-Agent.git
cd Data Analyst AI Agent
```
2. Create a virtual environment
```
python -m venv venv
```
3. Activate the virtual environment
```
venv\Scripts\Activate
(or on Mac): source venv/bin/activate
```
4. Install libraries
```
pip install -r requirements.txt
```
5. Create accounts
- Create an API key for OpenAI: https://platform.openai.com/api-keys
6. Add API keys to .env file
- Rename .env.example to .env
- Add the API key for OpenAI to the .env file
Executing the scripts
- Open a terminal in VS Code
- Execute the following command:
```
streamlit run main.py
```
Sources
While making this video, I used the following sources:
- https://www.kaggle.com/code/iyadmahdy/identifying-key-features-for-diabetes-prediction
- https://www.digilab.co.uk/posts/build-an-ai-data-assistant-with-streamlit-langchain-and-openai
- https://python.langchain.com/api_reference/experimental/agents/langchain_experimental.agents.agent_toolkits.pandas.base.create_pandas_dataframe_agent.html