sinaptik-ai/pandas-aiPublic

NotificationsYou must be signed in to change notification settings
Fork2.3k
Star23.2k

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

License

View license

23.2k stars 2.3k forks Branches Tags Activity

Star

Notifications

You must be signed in to change notification settings

Branches Tags

Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 1,416 Commits
.github		.github
assets		assets
docs		docs
ee		ee
examples		examples
extensions		extensions
pandasai		pandasai
tests		tests
.env.example		.env.example
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
.sourcery.yaml		.sourcery.yaml
CITATION.cff		CITATION.cff
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
Makefile		Makefile
README.md		README.md
docker-compose.yml		docker-compose.yml
ignore-words.txt		ignore-words.txt
poetry.lock		poetry.lock
poetry.toml		poetry.toml
pyproject.toml		pyproject.toml
pytest.ini		pytest.ini

Repository files navigation

PandasAI is a Python library that makes it easy to ask questions to your data in natural language. It helps non-technical users to interact with their data in a more natural way, and it helps technical users to save time, and effort when working with data.

🔧 Getting started

You can find the full documentation for PandasAIhere.

📚 Using the library

Python Requirements

Python version3.8+ <=3.11

📦 Installation

You can install the PandasAI library using pip or poetry.

With pip:

pip install pandasaipip install pandasai-litellm

With poetry:

poetry add pandasaipoetry add pandasai-litellm

💻 Usage

Ask questions

importpandasaiaspaifrompandasai_litellm.litellmimportLiteLLM# Initialize LiteLLM with your OpenAI modelllm=LiteLLM(model="gpt-4.1-mini",api_key="YOUR_OPENAI_API_KEY")# Configure PandasAI to use this LLMpai.config.set({"llm":llm})# Load your datadf=pai.read_csv("data/companies.csv")response=df.chat("What is the average revenue by region?")print(response)

Or you can ask more complex questions:

df.chat("What is the total sales for the top 3 countries by sales?")

The total sales for the top 3 countries by sales is 16500.

Visualize charts

You can also ask PandasAI to generate charts for you:

df.chat("Plot the histogram of countries showing for each one the gdp. Use different colors for each bar",)

Multiple DataFrames

You can also pass in multiple dataframes to PandasAI and ask questions relating them.

importpandasaiaspaifrompandasai_litellm.litellmimportLiteLLM# Initialize LiteLLM with your OpenAI modelllm=LiteLLM(model="gpt-4.1-mini",api_key="YOUR_OPENAI_API_KEY")# Configure PandasAI to use this LLMpai.config.set({"llm":llm})employees_data= {'EmployeeID': [1,2,3,4,5],'Name': ['John','Emma','Liam','Olivia','William'],'Department': ['HR','Sales','IT','Marketing','Finance']}salaries_data= {'EmployeeID': [1,2,3,4,5],'Salary': [5000,6000,4500,7000,5500]}employees_df=pai.DataFrame(employees_data)salaries_df=pai.DataFrame(salaries_data)pai.chat("Who gets paid the most?",employees_df,salaries_df)

Olivia gets paid the most.

Docker Sandbox

You can run PandasAI in a Docker sandbox, providing a secure, isolated environment to execute code safely and mitigate the risk of malicious attacks.

Python Requirements

pip install"pandasai-docker"

Usage

importpandasaiaspaifrompandasai_dockerimportDockerSandboxfrompandasai_litellm.litellmimportLiteLLM# Initialize LiteLLM with your OpenAI modelllm=LiteLLM(model="gpt-4.1-mini",api_key="YOUR_OPENAI_API_KEY")# Configure PandasAI to use this LLMpai.config.set({"llm":llm})# Initialize the sandboxsandbox=DockerSandbox()sandbox.start()employees_data= {'EmployeeID': [1,2,3,4,5],'Name': ['John','Emma','Liam','Olivia','William'],'Department': ['HR','Sales','IT','Marketing','Finance']}salaries_data= {'EmployeeID': [1,2,3,4,5],'Salary': [5000,6000,4500,7000,5500]}employees_df=pai.DataFrame(employees_data)salaries_df=pai.DataFrame(salaries_data)pai.chat("Who gets paid the most?",employees_df,salaries_df,sandbox=sandbox)# Don't forget to stop the sandbox when donesandbox.stop()

Olivia gets paid the most.

You can find more examples in theexamples directory.

📜 License

PandasAI is available under the MIT expat license, except for thepandasai/ee directory of this repository, which has itslicense here.

If you are interested in managed PandasAI Cloud or self-hosted Enterprise Offering,contact us.

Resources

Docs for comprehensive documentation
Examples for example notebooks
Discord for discussion with the community and PandasAI team

🤝 Contributing

Contributions are welcome! Please check the outstanding issues and feel free to open a pull request.For more information, please check out thecontributing guidelines.