{"data":{"slug":"sinaptik-ai-pandas-ai","name":"pandas-ai","tagline":"Chat with your database or your datalake using LLMs and RAG.","github_url":"https://github.com/sinaptik-ai/pandas-ai","owner":"sinaptik-ai","repo":"pandas-ai","owner_avatar_url":"https://avatars.githubusercontent.com/u/154438448?v=4","primary_language":"Python","stars":23746,"forks":2342,"topics":["ai","csv","data","data-analysis","data-science","data-visualization","database","datalake","gpt-4","llm","pandas","sql","text-to-sql"],"archived":false,"github_pushed_at":"2025-10-28T10:02:13+00:00","maintenance_label":"Slowing","stars_delta_30d":90,"url":"https://www.graphcanon.com/tools/sinaptik-ai-pandas-ai","markdown_url":"https://www.graphcanon.com/tools/sinaptik-ai-pandas-ai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sinaptik-ai-pandas-ai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sinaptik-ai-pandas-ai","description":"Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.","homepage_url":"https://pandas-ai.com","license":"Other","open_issues":22,"watchers":166,"ai_summary":"PandasAI enables conversational data analysis on databases (SQL) and datalakes (CSV, Parquet), leveraging Large Language Models (LLMs).","readme_excerpt":"# 🔧 Getting started\n\nYou can find the full documentation for PandasAI [here](https://docs.pandas-ai.com/).\n\n---\n\n### Python Requirements\n\nPython version `3.8+ <=3.11`\n\n---\n\n### 📦 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---\n\n## 📜 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).","github_created_at":"2023-04-22T12:58:01+00:00","created_at":"2026-07-07T17:32:52.544205+00:00","updated_at":"2026-08-17T00:01:37.415987+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"csv","name":"csv"},{"slug":"data-analysis","name":"data-analysis"},{"slug":"database","name":"database"},{"slug":"datalake","name":"datalake"},{"slug":"llm","name":"llm"},{"slug":"pandas","name":"pandas"},{"slug":"sql","name":"sql"}],"trust":{"provenance":{"is_fork":false,"github_id":631258918,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T00:01:36.605Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":292,"last_release_at":"2025-10-07T08:22:13Z","stars_delta_30d":90,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:59:47.101Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T00:01:37.064Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-08-17T00:01:37.064Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-17T00:01:37.064Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-17T00:01:37.064Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-08-17T00:01:37.064Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-17T00:01:37.064Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"unknown","summary":"Pricing details for using pandas-ai, especially those related to the integration of external LLM services like GPT-4, are unclear based on available information."},"requirements":null,"constraints":{"pricing_model":"unknown"},"when_to_use":["- When you need to perform complex data analysis tasks interactively through natural language commands.","- For rapid prototyping involving SQL queries or manipulating CSV/Parquet files without deep coding expertise.","- To leverage GPT-4's capabilities directly within a Python environment for sophisticated text-to-SQL translation.","- If your workflow benefits from having an AI-driven tool to translate conversational requests into database queries and data transformations."],"when_not_to_use":["- When you require advanced, custom SQL features that cannot be effectively translated from natural language commands.","- For applications where precise control over every aspect of query formulation is necessary due to performance or security concerns.","- In scenarios that demand real-time analytical capabilities beyond the conversational analysis offered by PandasAI.","- If your data operations are better managed through traditional programming techniques and you do not see significant value in conversational data querying."],"source":"enrich:decision_facts","observed_at":"2026-07-11T13:49:43.982Z"},"constraint_facets":{"pricing_model":"unknown"},"decision_summary":[{"label":"Pricing","value":"unknown - Pricing details for using pandas-ai, especially those related to the integration of external LLM services like GPT-4, are unclear based on available information."},{"label":"Adopt for","value":"PandasAI is a Python library that allows users to interact conversationally with databases (SQL) and data lakes (CSV, Parquet), leveraging large language models (LLMs) for improved accessibility and efficiency in data wr"}]}}