---
title: "raptor"
type: "tool"
slug: "parthsarthi03-raptor"
canonical_url: "https://www.graphcanon.com/tools/parthsarthi03-raptor"
github_url: "https://github.com/parthsarthi03/raptor"
homepage_url: "https://arxiv.org/abs/2401.18059"
stars: 1721
forks: 230
primary_language: "Python"
license: "MIT"
categories: ["llm-frameworks", "ai-agents"]
tags: ["clustering", "agents", "llm", "machine-learning", "rag", "retrieval", "framework", "language-model"]
updated_at: "2026-07-07T18:46:07.928893+00:00"
---

# raptor

> Recursive Abstractive Processing for Tree-Organized Retrieval (RAPTOR)

A recursive framework to enhance retrieval-augmented generation models using tree-based data organization.

## Facts

- Repository: https://github.com/parthsarthi03/raptor
- Homepage: https://arxiv.org/abs/2401.18059
- Stars: 1,721 · Forks: 230 · Open issues: 45 · Watchers: 20
- Primary language: Python
- License: MIT
- Last pushed: 2024-09-03T08:34:31+00:00

## Categories

- [LLM Frameworks](/categories/llm-frameworks.md)
- [AI Agents](/categories/ai-agents.md)

## Tags

clustering, agents, llm, machine-learning, rag, retrieval, framework, language-model

## Related tools

- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (★ 226,962)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (★ 210,880)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (★ 185,417)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (★ 175,659)
- [prompts.chat](/tools/f-prompts-chat.md) - The world's largest open-source prompt library for AI (★ 165,019)
- [transformers](/tools/huggingface-transformers.md) - 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models (★ 162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (★ 151,298)
- [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (★ 148,070)

## README (excerpt)

```text
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="raptor_dark.png">
  <img alt="Shows an illustrated sun in light color mode and a moon with stars in dark color mode." src="raptor.jpg">
</picture>

## RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

**RAPTOR** introduces a novel approach to retrieval-augmented language models by constructing a recursive tree structure from documents. This allows for more efficient and context-aware information retrieval across large texts, addressing common limitations in traditional language models. 



For detailed methodologies and implementations, refer to the original paper:

- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://arxiv.org/abs/2401.18059)




## Installation

Before using RAPTOR, ensure Python 3.8+ is installed. Clone the RAPTOR repository and install necessary dependencies:

```bash
git clone https://github.com/parthsarthi03/raptor.git
cd raptor
pip install -r requirements.txt
```

## Basic Usage

To get started with RAPTOR, follow these steps:

### Setting Up RAPTOR

First, set your OpenAI API key and initialize the RAPTOR configuration:

```python
import os
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

from raptor import RetrievalAugmentation

# Initialize with default configuration. For advanced configurations, check the documentation. [WIP]
RA = RetrievalAugmentation()
```

### Adding Documents to the Tree

Add your text documents to RAPTOR for indexing:

```python
with open('sample.txt', 'r') as file:
    text = file.read()
RA.add_documents(text)
```

### Answering Questions

You can now use RAPTOR to answer questions based on the indexed documents:

```python
question = "How did Cinderella reach her happy ending?"
answer = RA.answer_question(question=question)
print("Answer: ", answer)
```

### Saving and Loading the Tree

Save the constructed tree to a specified path:

```python
SAVE_PATH = "demo/cinderella"
RA.save(SAVE_PATH)
```

Load the saved tree back into RAPTOR:

```python
RA = RetrievalAugmentation(tree=SAVE_PATH)
answer = RA.answer_question(question=question)
```


### Extending RAPTOR with other Models

RAPTOR is designed to be flexible and allows you to integrate any models for summarization, question-answering (QA), and embedding generation. Here is how to extend RAPTOR with your own models:

#### Custom Summarization Model

If you wish to use a different language model for summarization, you can do so by extending the `BaseSummarizationModel` class. Implement the `summarize` method to integrate your custom summarization logic:

```python
from raptor import BaseSummarizationModel

class CustomSummarizationModel(BaseSummarizationModel):
    def __init__(self):
        # Initialize your model here
        pass

    def summarize(self, context, max_tokens=150):
        # Implement your summarization logic here
        # Return the summary as a string
        summary = "Your summary here"
        return summary
```

#### Custom QA Model

For custom QA models, extend the `BaseQAModel` class and implement the `answer_question` method. This method should return the best answer found by your model given a context and a question:

```python
from raptor import BaseQAModel

class CustomQAModel(BaseQAModel):
    def __init__(self):
        # Initialize your model here
        pass

    def answer_question(self, context, question):
        # Implement your QA logic here
        # Return the answer as a string
        answer = "Your answer here"
        return answer
```

#### Custom Embedding Model

To use a different embedding model, extend the `BaseEmbeddingModel` class. Implement the `create_embedding` method, which should return a vector representation of the input text:

```python
from raptor import BaseEmbeddingModel

class CustomEmbeddingModel(BaseEmbeddingModel):
    def __init__(self):
        # Initialize your model here
        pass

    def create_embedding(self, text):
        # Im
```

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/tools/parthsarthi03-raptor`](/api/graphcanon/tools/parthsarthi03-raptor)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_