| Name | pandasai JSON |
| Version |
3.0.0
JSON |
| download |
| home_page | None |
| Summary | Chat with your database (SQL, CSV, pandas, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG. |
| upload_time | 2025-10-07 08:22:56 |
| maintainer | None |
| docs_url | None |
| author | Gabriele Venturi |
| requires_python | <3.12,>=3.8 |
| license | MIT |
| keywords |
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 
[](https://pypi.org/project/pandasai/)
[](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/ci-core.yml/badge.svg)
[](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/cd.yml/badge.svg)
[](https://codecov.io/gh/sinaptik-ai/pandas-ai)
[](https://discord.gg/KYKj9F2FRH)
[](https://pepy.tech/project/pandasai) [](https://opensource.org/licenses/MIT)
[](https://colab.research.google.com/drive/1ZnO-njhL7TBOYPZaqvMvGtsjckZKrv2E?usp=sharing)
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 PandasAI [here](https://docs.pandas-ai.com/).
## 📚 Using the library
### Python Requirements
Python version `3.8+ <=3.11`
### 📦 Installation
You can install the PandasAI library using pip or poetry.
With pip:
```bash
pip install pandasai
pip install pandasai-litellm
```
With poetry:
```bash
poetry add pandasai
poetry add pandasai-litellm
```
### 💻 Usage
#### Ask questions
```python
import pandasai as pai
from pandasai_litellm.litellm import LiteLLM
# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
# Configure PandasAI to use this LLM
pai.config.set({
"llm": llm
})
# Load your data
df = 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:
```python
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:
```python
df.chat(
"Plot the histogram of countries showing for each one the gd. Use different colors for each bar",
)
```
#### Multiple DataFrames
You can also pass in multiple dataframes to PandasAI and ask questions relating them.
```python
import pandasai as pai
from pandasai_litellm.litellm import LiteLLM
# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
# Configure PandasAI to use this LLM
pai.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
```bash
pip install "pandasai-docker"
```
##### Usage
```python
import pandasai as pai
from pandasai_docker import DockerSandbox
from pandasai_litellm.litellm import LiteLLM
# Initialize LiteLLM with your OpenAI model
llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
# Configure PandasAI to use this LLM
pai.config.set({
"llm": llm
})
# Initialize the sandbox
sandbox = 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 done
sandbox.stop()
```
```
Olivia gets paid the most.
```
You can find more examples in the [examples](examples) directory.
## 📜 License
PandasAI is available under the MIT expat license, except for the `pandasai/ee` directory of this repository, which has its [license here](https://github.com/sinaptik-ai/pandas-ai/blob/main/ee/LICENSE).
If you are interested in managed PandasAI Cloud or self-hosted Enterprise Offering, [contact us](https://pandas-ai.com).
## Resources
- [Docs](https://docs.pandas-ai.com/) for comprehensive documentation
- [Examples](examples) for example notebooks
- [Discord](https://discord.gg/KYKj9F2FRH) 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 the [contributing guidelines](CONTRIBUTING.md).
### Thank you!
[](https://github.com/sinaptik-ai/pandas-ai/graphs/contributors)
Raw data
{
"_id": null,
"home_page": null,
"name": "pandasai",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.12,>=3.8",
"maintainer_email": null,
"keywords": null,
"author": "Gabriele Venturi",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/fb/28/6e98c3c5ece389e223103efcc540708800e0db8c3764d38fb596dfd729fb/pandasai-3.0.0.tar.gz",
"platform": null,
"description": "# \n\n[](https://pypi.org/project/pandasai/)\n[](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/ci-core.yml/badge.svg)\n[](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/cd.yml/badge.svg)\n[](https://codecov.io/gh/sinaptik-ai/pandas-ai)\n[](https://discord.gg/KYKj9F2FRH)\n[](https://pepy.tech/project/pandasai) [](https://opensource.org/licenses/MIT)\n[](https://colab.research.google.com/drive/1ZnO-njhL7TBOYPZaqvMvGtsjckZKrv2E?usp=sharing)\n\nPandasAI 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.\n\n# \ud83d\udd27 Getting started\n\nYou can find the full documentation for PandasAI [here](https://docs.pandas-ai.com/).\n\n\n## \ud83d\udcda Using the library\n\n### Python Requirements\n\nPython version `3.8+ <=3.11`\n\n### \ud83d\udce6 Installation\n\nYou can install the PandasAI library using pip or poetry.\n\nWith pip:\n\n```bash\npip install pandasai\npip install pandasai-litellm\n```\n\nWith poetry:\n\n```bash\npoetry add pandasai\npoetry add pandasai-litellm\n```\n\n### \ud83d\udcbb Usage\n\n#### Ask questions\n\n```python\nimport pandasai as pai\nfrom pandasai_litellm.litellm import LiteLLM\n\n# Initialize LiteLLM with your OpenAI model\nllm = LiteLLM(model=\"gpt-4.1-mini\", api_key=\"YOUR_OPENAI_API_KEY\")\n\n# Configure PandasAI to use this LLM\npai.config.set({\n \"llm\": llm\n})\n\n# Load your data\ndf = pai.read_csv(\"data/companies.csv\")\n\nresponse = df.chat(\"What is the average revenue by region?\")\nprint(response)\n```\n\n---\n\nOr you can ask more complex questions:\n\n```python\ndf.chat(\n \"What is the total sales for the top 3 countries by sales?\"\n)\n```\n\n```\nThe total sales for the top 3 countries by sales is 16500.\n```\n\n#### Visualize charts\n\nYou can also ask PandasAI to generate charts for you:\n\n```python\ndf.chat(\n \"Plot the histogram of countries showing for each one the gd. Use different colors for each bar\",\n)\n```\n\n\n\n#### Multiple DataFrames\n\nYou can also pass in multiple dataframes to PandasAI and ask questions relating them.\n\n```python\nimport pandasai as pai\nfrom pandasai_litellm.litellm import LiteLLM\n\n# Initialize LiteLLM with your OpenAI model\nllm = LiteLLM(model=\"gpt-4.1-mini\", api_key=\"YOUR_OPENAI_API_KEY\")\n\n# Configure PandasAI to use this LLM\npai.config.set({\n \"llm\": llm\n})\n\nemployees_data = {\n 'EmployeeID': [1, 2, 3, 4, 5],\n 'Name': ['John', 'Emma', 'Liam', 'Olivia', 'William'],\n 'Department': ['HR', 'Sales', 'IT', 'Marketing', 'Finance']\n}\n\nsalaries_data = {\n 'EmployeeID': [1, 2, 3, 4, 5],\n 'Salary': [5000, 6000, 4500, 7000, 5500]\n}\n\nemployees_df = pai.DataFrame(employees_data)\nsalaries_df = pai.DataFrame(salaries_data)\n\n\npai.chat(\"Who gets paid the most?\", employees_df, salaries_df)\n```\n\n```\nOlivia gets paid the most.\n```\n\n#### Docker Sandbox\n\nYou can run PandasAI in a Docker sandbox, providing a secure, isolated environment to execute code safely and mitigate the risk of malicious attacks.\n\n##### Python Requirements\n\n```bash\npip install \"pandasai-docker\"\n```\n\n##### Usage\n\n```python\nimport pandasai as pai\nfrom pandasai_docker import DockerSandbox\nfrom pandasai_litellm.litellm import LiteLLM\n\n# Initialize LiteLLM with your OpenAI model\nllm = LiteLLM(model=\"gpt-4.1-mini\", api_key=\"YOUR_OPENAI_API_KEY\")\n\n# Configure PandasAI to use this LLM\npai.config.set({\n \"llm\": llm\n})\n\n# Initialize the sandbox\nsandbox = DockerSandbox()\nsandbox.start()\n\nemployees_data = {\n 'EmployeeID': [1, 2, 3, 4, 5],\n 'Name': ['John', 'Emma', 'Liam', 'Olivia', 'William'],\n 'Department': ['HR', 'Sales', 'IT', 'Marketing', 'Finance']\n}\n\nsalaries_data = {\n 'EmployeeID': [1, 2, 3, 4, 5],\n 'Salary': [5000, 6000, 4500, 7000, 5500]\n}\n\nemployees_df = pai.DataFrame(employees_data)\nsalaries_df = pai.DataFrame(salaries_data)\n\npai.chat(\"Who gets paid the most?\", employees_df, salaries_df, sandbox=sandbox)\n\n# Don't forget to stop the sandbox when done\nsandbox.stop()\n```\n\n```\nOlivia gets paid the most.\n```\n\nYou can find more examples in the [examples](examples) directory.\n\n## \ud83d\udcdc License\n\nPandasAI is available under the MIT expat license, except for the `pandasai/ee` directory of this repository, which has its [license here](https://github.com/sinaptik-ai/pandas-ai/blob/main/ee/LICENSE).\n\nIf you are interested in managed PandasAI Cloud or self-hosted Enterprise Offering, [contact us](https://pandas-ai.com).\n\n## Resources\n\n- [Docs](https://docs.pandas-ai.com/) for comprehensive documentation\n- [Examples](examples) for example notebooks\n- [Discord](https://discord.gg/KYKj9F2FRH) for discussion with the community and PandasAI team\n\n## \ud83e\udd1d Contributing\n\nContributions are welcome! Please check the outstanding issues and feel free to open a pull request.\nFor more information, please check out the [contributing guidelines](CONTRIBUTING.md).\n\n### Thank you!\n\n[](https://github.com/sinaptik-ai/pandas-ai/graphs/contributors)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Chat with your database (SQL, CSV, pandas, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.",
"version": "3.0.0",
"project_urls": {
"Documentation": "https://docs.pandas-ai.com/",
"Repository": "https://github.com/sinaptik-ai/pandas-ai"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7acf1dba25c504810d946aacd6e4b2fb9c4a415a88d1850a8a4788a2c8599e24",
"md5": "bbde9a93f8c4b40a87b084c86a62f222",
"sha256": "1d37629f2450dfe25b47b437f581ce7ca88c4ea321f9a9c8c1eaf4e82ed52ebf"
},
"downloads": -1,
"filename": "pandasai-3.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bbde9a93f8c4b40a87b084c86a62f222",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.12,>=3.8",
"size": 83162,
"upload_time": "2025-10-07T08:22:55",
"upload_time_iso_8601": "2025-10-07T08:22:55.304430Z",
"url": "https://files.pythonhosted.org/packages/7a/cf/1dba25c504810d946aacd6e4b2fb9c4a415a88d1850a8a4788a2c8599e24/pandasai-3.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "fb286e98c3c5ece389e223103efcc540708800e0db8c3764d38fb596dfd729fb",
"md5": "e6b4c2480ee528f9c3974d8bd24a7736",
"sha256": "f1bac4e98085dad4cc5072a86287143bccf7b651b8b0459a82bdc20a93f427c9"
},
"downloads": -1,
"filename": "pandasai-3.0.0.tar.gz",
"has_sig": false,
"md5_digest": "e6b4c2480ee528f9c3974d8bd24a7736",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.8",
"size": 55278,
"upload_time": "2025-10-07T08:22:56",
"upload_time_iso_8601": "2025-10-07T08:22:56.522938Z",
"url": "https://files.pythonhosted.org/packages/fb/28/6e98c3c5ece389e223103efcc540708800e0db8c3764d38fb596dfd729fb/pandasai-3.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-07 08:22:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "sinaptik-ai",
"github_project": "pandas-ai",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "pandasai"
}
