---
id: pandasai-litellm
version: "0.0.1"
license: MIT
license_treatment: permissive
maintenance: aging
---

# pandasai-litellm — LiteLLM integration for PandaAI

License: permissive · Maintenance: aging · Downloads: 81.1K/mo

## What it is and what it does

pandasai-litellm is a bridge between pandasai and litellm, allowing you to ask natural-language questions about your data using any language model that litellm can route to. Instead of writing pandas code or SQL, you configure a LiteLLM instance with your chosen model and API key, then call methods like `df.chat()` to query dataframes conversationally. The package handles translation of natural language into executable pandas operations and can generate charts on request.

It depends on pandasai (the core data-querying engine) and litellm (the multi-provider LLM abstraction layer). The package is minimal—just the integration glue—and installs with low friction. However, it has not been updated since its 0.0.1 release, and requires Python 3.8 to 3.11, which may limit adoption on newer environments.

Use it for:

- Enable non-technical users to explore CSV or dataframe data by asking questions in plain English without learning pandas syntax.
- Quickly prototype data analysis workflows by chatting with your data instead of writing boilerplate pandas code.
- Generate exploratory visualizations by describing them in natural language.
- Analyze multiple related dataframes together by asking cross-dataset questions in a single query.
- Switch between LLM providers without changing your pandasai code, leveraging litellm's routing.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates LiteLLM with PandasAI to enable natural-language queries against dataframes using any LLM provider that LiteLLM supports.

Yes, if you want to use pandasai with a non-OpenAI LLM provider or need litellm's multi-provider routing. The package is lightweight and permissively licensed. However, the 0.0.1 version and absence of updates since release suggest early-stage maturity; verify compatibility with your target Python version and litellm setup before committing to production use.

## Install

pip install pandasai-litellm
uv add pandasai-litellm
poetry add pandasai-litellm

## Installing pandasai-litellm

Before you install: Low install friction; a pure-Python wheel with only two runtime dependencies (pandasai and litellm). Maintenance status is aging—no updates since initial release on 2025-03-11.

License in practice: MIT permissive license; you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.

Quickstart:

pip install pandasai pandasai-litellm

import pandasai as pai
from pandasai_litellm.litellm import LiteLLM

llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
pai.config.set({"llm": llm})
df = pai.read_csv("data/companies.csv")
response = df.chat("What is the average revenue by region?")
print(response)

Requires Python 3.8 to 3.11; does not support Python 3.12 or later.

Verify before relying:

- Whether LiteLLM integration is feature-complete relative to other PandasAI LLM backends.
- Stability and breaking-change risk given the 0.0.1 version and lack of updates since release.
- Production readiness and whether the package is actively maintained.

## Package facts

- License: MIT (permissive)
- Python support: capped_below_current
- Install friction: low
- Maintenance: aging
- Downloads: 81.1K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

natural language dataframe queries, litellm pandas integration, ask questions to data, llm-powered data analysis, dataframe chat interface, multi-provider llm pandas, conversational data exploration, natural-language-interface, llm-integration, data-exploration

[View on SkillFed](https://skillfed.io/packages/pandasai-litellm) · [View on PyPI](https://pypi.org/project/pandasai-litellm/)