PandasAI

PandasAI is a Python library for people who want to ask questions about their data in plain language. It works with SQL databases, CSV and parquet data, and can answer questions across multiple pandas DataFrames. Developers can use it in their own applications; analysts can use conversational queries to reduce the code they write for individual questions.

The library generates charts as well as answers, so a question can produce a visual result without a separate charting task. It uses LLMs and retrieval-augmented generation for conversational analysis. A Docker sandbox provides an isolated environment for executing analysis code, which matters when generated code runs against your data.

The same team offers Annie, a separate hosted business intelligence app. It targets business users who want analysis without writing SQL or Python. Annie turns questions into charts and shareable dashboards, supports follow-up questions, and produces executive summaries and PDF exports. Its analysis capabilities include trends, forecasting, anomaly detection and root cause analysis.

Deployment differs between the products. The Python library can run in your own environment, while Annie has a hosted offering and deployment options for on-premise systems, private VPCs and air-gapped environments. Annie also supports custom LLM integration.