README.md

---
title: CatLLM - Survey Response Summarizer
emoji: 🐱
colorFrom: yellow
colorTo: yellow
sdk: streamlit
sdk_version: "1.32.0"
app_file: app.py
pinned: false
license: gpl-3.0
short_description: Summarize survey responses and PDFs using LLMs
---

# CatLLM - Survey Response Summarizer

A web interface for the [catllm](https://github.com/chrissoria/cat-llm) Python package. Summarize survey responses and PDF documents using various LLM providers.

## How to Use

1. **Upload Your Data**: Upload a CSV, Excel file, or PDF documents
2. **Select Column** (for text): Choose the column containing the text responses to summarize
3. **Add Context**: Describe your data and optionally add focus/instructions
4. **Choose a Model**: Select your preferred LLM (free models available!)
5. **Click Summarize**: View and download results with generated summaries

## Features

- **Text Summarization**: Summarize survey responses, feedback, or any text data
- **PDF Summarization**: Extract and summarize content from PDF documents
- **Customizable**: Add focus areas, max length limits, and custom instructions
- **Methodology Report**: Download a PDF report documenting your summarization process

## Supported Models

| Provider | Models |
|----------|--------|
| **OpenAI** | gpt-4.1, gpt-4o, gpt-4o-mini |
| **Anthropic** | claude-sonnet-4.5, claude-opus-4, claude-3.5-haiku |
| **Google** | gemini-2.5-pro, gemini-2.5-flash |
| **Mistral** | mistral-large-latest |
| **Free Models** | Qwen3 235B, DeepSeek V3.1, Llama 3.3 70B |

## Privacy

Your API key is **never stored**. It is only used for the current summarization request and is not logged or saved.

## Related

- [CatLLM Survey Classifier](https://huggingface.co/spaces/CatLLM/survey-classifier) - Classify survey responses into categories
- [catllm on PyPI](https://pypi.org/project/cat-llm/)
- [GitHub Repository](https://github.com/chrissoria/cat-llm)