# Fenic

> Fenic is a semantic DataFrame engine: PySpark/SQL plus AI operators — extract, classify, embed, and semantic joins — that turn structured and unstructured data into typed, reusable, inspectable pipelines for humans and agents.

Fenic is an open-source Python library that brings LLM inference into the DataFrame model as first-class column operations. Built on a Polars-based engine with Rust extensions, it lets you process documents, logs, and transcripts into typed rows using the same API you would use for ordinary structured data.

## Install

```
pip install fenic  # Python 3.10+
```

## Key URLs

- Website: https://fenic.ai
- Full brief (self-contained): https://fenic.ai/llms-full.txt
- Agent instructions: https://fenic.ai/agents.md
- Blog: https://fenic.ai/blog
- Blog archive (LLM-friendly index): https://fenic.ai/blog/llms.txt
- RSS feed: https://fenic.ai/feed.xml
- Documentation: https://docs.fenic.ai
- Quickstart: https://docs.fenic.ai/latest/#quickstart
- Source code (GitHub): https://github.com/typedef-ai/fenic
- Examples: https://github.com/typedef-ai/fenic-examples
- Community (Discord): https://discord.gg/GdqF3J7huR

## Recent writing

- 2026-07-17 — [Why and how we extended Polars with Rust expression plugins for fenic](https://fenic.ai/blog/extending-polars-with-rust-expression-plugins)
- 2025-12-19 — [fenic 0.7.0: Gemini 3 Flash, Granular Thinking Levels — plus session and docs improvements](https://fenic.ai/blog/fenic-0-7-0-gemini-3-flash-granular-thinking-levels-plus-session-and-docs-improvements)
- 2025-12-04 — [fenic 0.6.0: LLM Caching, New Models, DataFrame Ops — plus PDF and Agent upgrades](https://fenic.ai/blog/fenic-0-6-0-llm-caching-new-models-dataframe-ops-plus-pdf-and-agent-upgrades)
- 2025-12-03 — [Why we built fenic](https://fenic.ai/blog/why-we-built-fenic)

## What Fenic is not

Fenic is a semantic DataFrame engine — not an agent framework or orchestration
runtime, not a memory store or vector database, and not a semantic/metrics layer
for BI. It makes no distributed, Spark-scale, real-time, or streaming claims.