pandas-ai
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Science Score: 54.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
1 of 106 committers (0.9%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (15.3%) to scientific vocabulary
Keywords
Keywords from Contributors
Repository
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Basic Info
- Host: GitHub
- Owner: sinaptik-ai
- License: other
- Language: Python
- Default Branch: main
- Homepage: https://pandas-ai.com
- Size: 54.8 MB
Statistics
- Stars: 21,955
- Watchers: 168
- Forks: 2,135
- Open Issues: 23
- Releases: 196
Topics
Metadata Files
README.md
PandasAI is a Python platform 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.
You can either decide to use PandasAI in your Jupyter notebooks, Streamlit apps, or use the client and server architecture from the repo.
📚 Using the library
Python Requirements
Python version 3.8+ <3.12
📦 Installation
You can install the PandasAI library using pip or poetry.
With pip:
bash
pip install "pandasai>=3.0.0b2"
With poetry:
bash
poetry add "pandasai>=3.0.0b2"
💻 Usage
Ask questions
```python import pandasai as pai from pandasai_openai.openai import OpenAI
llm = OpenAI("OPENAIAPI_KEY")
pai.config.set({ "llm": llm })
Sample DataFrame
df = pai.DataFrame({ "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"], "revenue": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000] })
df.chat('Which are the top 5 countries by sales?') ```
China, United States, Japan, Germany, Australia
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_openai.openai import OpenAI
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] }
llm = OpenAI("OPENAIAPI_KEY")
pai.config.set({ "llm": llm })
employeesdf = pai.DataFrame(employeesdata) salariesdf = pai.DataFrame(salariesdata)
pai.chat("Who gets paid the most?", employeesdf, salariesdf) ```
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 pandasaidocker import DockerSandbox from pandasaiopenai.openai import OpenAI
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] }
llm = OpenAI("OPENAIAPI_KEY")
pai.config.set({ "llm": llm })
employeesdf = pai.DataFrame(employeesdata) salariesdf = pai.DataFrame(salariesdata)
pai.chat("Who gets paid the most?", employeesdf, salariesdf, 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 directory.
📜 License
PandasAI is available under the MIT expat license, except for the pandasai/ee directory of this repository, which has its license here.
If you are interested in managed PandasAI Cloud or self-hosted Enterprise Offering, contact us.
Resources
Beta Notice
Release v3 is currently in beta. The following documentation and examples reflect the features and functionality in progress and may change before the final release.
- 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 the contributing guidelines.
Thank you!
Owner
- Name: PandasAI
- Login: Sinaptik-AI
- Kind: organization
- Website: https://pandas-ai.com
- Repositories: 1
- Profile: https://github.com/Sinaptik-AI
Citation (CITATION.cff)
cff-version: 1.2.0 date-released: 2023-04-29 message: "If you use this software, please cite it as below." title: "PandasAI: the conversational data analysis framework" abstract: "PandasAI is a python library that makes it easy to ask questions to your data in natural language." url: "https://github.com/sinaptik-ai/pandas-ai" authors: - family-names: "Venturi" given-names: "Gabriele" affiliation: "Sinaptik" license: MIT
Committers
Last synced: 9 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Gabriele Venturi | l****i@g****m | 666 |
| Arslan Saleem | k****8@g****m | 185 |
| Raoul Scalise | 3****l | 50 |
| Massimiliano Pronesti | m****i@g****m | 47 |
| Ihor | 3****9 | 34 |
| Henrique Branco | h****o@g****m | 25 |
| Jonathan Biemond | 1****d | 14 |
| Sanchit Bhavsar | 3****n | 13 |
| Shahrukh Khan | s****u@g****m | 12 |
| Cheng Wai | 1****o | 10 |
| josephsinaptik | g****e@s****i | 10 |
| Lorenzobattistela | l****h@g****m | 9 |
| Milind Lalwani | m****i@M****l | 9 |
| Johnson A | 5****7 | 5 |
| Oral Ersoy Dokumacı | o****i@g****m | 5 |
| Tanmay patil | 7****3 | 5 |
| Avelino | a****n@g****m | 4 |
| Victor Del Carpio | v****g@g****m | 4 |
| ma-raza | a****4@g****m | 4 |
| Hanchung Lee | l****g@g****m | 4 |
| milind-sinaptik | 1****k | 3 |
| goriri | g****i@1****m | 3 |
| dohertychristopher4 | 4****4 | 3 |
| Gaurang Pawar | 5****1 | 3 |
| yzaparto | y****3@g****m | 2 |
| sourcery-ai[bot] | 5****] | 2 |
| rekwet | 3****t | 2 |
| mintlify[bot] | 1****] | 2 |
| kukushking | k****n@g****m | 2 |
| dSupertramp | s****o@g****m | 2 |
| and 76 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 6 months ago
All Time
- Total issues: 525
- Total pull requests: 567
- Average time to close issues: 3 months
- Average time to close pull requests: 14 days
- Total issue authors: 366
- Total pull request authors: 107
- Average comments per issue: 2.47
- Average comments per pull request: 0.85
- Merged pull requests: 370
- Bot issues: 0
- Bot pull requests: 8
Past Year
- Issues: 204
- Pull requests: 353
- Average time to close issues: 20 days
- Average time to close pull requests: 4 days
- Issue authors: 151
- Pull request authors: 44
- Average comments per issue: 1.36
- Average comments per pull request: 0.49
- Merged pull requests: 234
- Bot issues: 0
- Bot pull requests: 8
Top Authors
Issue Authors
- gventuri (10)
- anilmadishetty2498 (10)
- Alan-zhong (9)
- metalshanked (7)
- gDanzel (7)
- PavelAgurov (7)
- ssling0817 (6)
- johnfelipe (5)
- lwdnxu (5)
- HenriqueAJNB (5)
- via007 (4)
- prasum (4)
- Yekai97 (4)
- tytung2020 (4)
- vpurandara (4)
Pull Request Authors
- ArslanSaleem (163)
- scaliseraoul (105)
- gventuri (24)
- gdcsinaptik (21)
- shahrukh802 (18)
- matteocacciola (16)
- chengwaikoo (10)
- HenriqueAJNB (8)
- mspronesti (8)
- nehcneb (6)
- codebeaver-ai[bot] (6)
- christophfroeschl (6)
- oedokumaci (5)
- prasum (4)
- Muhammad-Adam1 (4)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 20
-
Total downloads:
- pypi 18,946 last-month
-
Total dependent packages: 0
(may contain duplicates) -
Total dependent repositories: 0
(may contain duplicates) - Total versions: 83
- Total maintainers: 2
pypi.org: jcloudai-litellm
LiteLLM integration for PandasAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.0.3
published 6 months ago
Rankings
Maintainers (1)
pypi.org: jcloudai
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.
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 1.0.5
published 6 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-litellm
LiteLLM integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.0.1
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-docker
- Documentation: https://docs.getpanda.ai/v3/privacy-security
- License: MIT
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-huggingface
Hugging Face integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-oracle
Oracle connector integration for PandaAI
- Documentation: https://docs.getpanda.ai/v3/data-ingestion
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-snowflake
Snowflake connector integration for PandaAI
- Documentation: https://docs.getpanda.ai/v3/data-ingestion
- License: Proprietary
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-databricks
Databricks connector integration for PandaAI
- Documentation: https://docs.getpanda.ai/v3/data-ingestion
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-bigquery
Google BigQuery connector integration for PandaAI
- Documentation: https://docs.getpanda.ai/v3/data-ingestion
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-local
Local LLM integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-langchain
Langchain integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-bedrock
AWS Bedrock integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-ibm
IBM integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-openai
OpenAI integration for PandasAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.6
published 8 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-google
Google integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: MIT
-
Latest release: 0.1.5
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-lancedb
LanceDB integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-pinecone
Pinecone integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-chromadb
ChromaDB integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-qdrant
Qdrant integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago
Rankings
Maintainers (1)
pypi.org: pandasai-milvus
Milvus integration for PandaAI
- Documentation: https://docs.getpanda.ai/
- License: Proprietary
-
Latest release: 0.1.4
published 12 months ago