# sinaptik-ai/pandas-ai

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

Repository: https://github.com/sinaptik-ai/pandas-ai
Canonical: https://ross.abutalabs.com/products/pandas-ai
Homepage: https://pandas-ai.com
Language: Python
License: NOASSERTION
License Family: other
Topics: llm, pandas, ai, data-analysis, data-science, gpt-4, csv, data, sql, database, datalake, data-visualization, text-to-sql
Last push: 2025-10-28T10:02:13+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 49, release rhythm 51, longevity 87
- inputs: {"age_days": 1229, "days_push": 309, "days_rel": 330, "gap_med": 27, "n_releases_24m": 8}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23772, forks 2343 (observed 2026-08-28T04:11:35.355234+00:00)

## What it is
PandasAI is a Python library that lets users query data in SQL, CSV, or parquet format using natural language, powered by LLMs and RAG. It generates answers and charts conversationally, making data analysis accessible to non-technical users.

## Use cases
- ask questions about a csv in plain english
- chat with my sql database using natural language
- generate charts from data by describing them
- text-to-sql querying for non-technical users
- analyze parquet files conversationally
- query multiple dataframes with natural language

## When to choose
- you want conversational data analysis over tabular data
- non-technical stakeholders need to query data without SQL
- you want LLM-generated charts and answers from pandas-compatible sources

## When to avoid
- you need deterministic, auditable SQL without LLM involvement
- your data cannot be shared with third-party LLM APIs
- you need sub-millisecond query performance

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, rag, data-visualization, nlp, data-science
- domain: data-science, analytics, large-language-models, databases, data-visualization
- platform: python, cross-platform
- tags: text-to-sql, conversational-analytics, pandas, natural-language-querying, csv, parquet, sql

## Member repositories
- sinaptik-ai/pandas-ai (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:35.355234+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:20.714870+00:00, confidence not recorded.
  - readme: https://github.com/sinaptik-ai/pandas-ai (fetched 2026-08-28T04:11:35.355234+00:00, sha 8ba6db54b5bd)
  - homepage: https://pandas-ai.com (fetched 2026-08-29T07:53:55.814683+00:00, sha a15b751d903d)
- Data as of 2026-08-30T08:39:29.467469+00:00.