PHPackages neuron-core/raptor-retrieval - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Utility & Helpers](/categories/utility) 4. / 5. neuron-core/raptor-retrieval ActiveLibrary[Utility & Helpers](/categories/utility) neuron-core/raptor-retrieval ============================ Recursive Abstractive Processing for Tree-Organized Retrieval 3.0.0(2mo ago)93.0k↓41.2%4[1 issues](https://github.com/neuron-core/raptor-retrieval/issues)[1 PRs](https://github.com/neuron-core/raptor-retrieval/pulls)MITPHPPHP ^8.1 Since Sep 12Pushed 2mo agoCompare [ Source](https://github.com/neuron-core/raptor-retrieval)[ Packagist](https://packagist.org/packages/neuron-core/raptor-retrieval)[ RSS](/packages/neuron-core-raptor-retrieval/feed)WikiDiscussions main Synced 1mo ago READMEChangelog (7)Dependencies (6)Versions (9)Used By (0) Recursive Abstractive Processing for Tree-Organized Retrieval ============================================================= [](#recursive-abstractive-processing-for-tree-organized-retrieval) This module implements the RAPTOR retrieval strategy for the [Neuron PHP AI framework](https://neuron-ai.dev). The Problem with Traditional Retrieval -------------------------------------- [](#the-problem-with-traditional-retrieval) Most retrieval-augmented models work by breaking down documents into small chunks and retrieving only the most relevant ones. However, this approach has some limitations: - **Loss of Context**: Retrieving only small, isolated chunks may miss the bigger picture, especially for documents with long contexts. - **Difficulty in Multi-Step Reasoning**: Some questions require information from multiple sections of a document. **Use RAPTOR when:** - Users ask open-ended questions that require comprehensive coverage - Your domain involves complex topics where context matters as much as facts - You need to handle queries about themes, trends, or relationships across documents **Stick with traditional RAG when:** - Users primarily need quick, specific fact retrieval - Processing speed and token efficiency are critical constraints Check out the example in the [examples](./examples/raptor.php) folder. Requirements ------------ [](#requirements) - PHP: ^8.1 - Neuron: ^2.0 Install RAPTOR retrieval ------------------------ [](#install-raptor-retrieval) Install the latest version of the package: ``` composer require neuron-core/raptor-retreival ``` How to use RAPTOR in your agent ------------------------------- [](#how-to-use-raptor-in-your-agent) Or use the RAPTOR component directly into the agent. RAPTOR needs a vector store, an embedding provider and uses an LLM to perform the summarization: ``` use NeuronAI\RAG\Retrieval\RetrievalInterface; use NeuronCore\RaptorRetrieval\RaptorRetrieval; class WorkoutTipsAgent extends RAG { protected function retrieval(): RetrievalInterface { return new RaptorRetrieval( $this->resolveVectorStore(), $this->resolveEmbeddingsProvider(), $this->resolveProvider(), // Used for summarization ); } protected function embeddings(): EmbeddingsProviderInterface { return new ... } protected function vectorStore(): VectorStoreInterface { return new ... } } ``` Clustering strategy ------------------- [](#clustering-strategy) RAPTOR algorithm uses a clustering strategy to group the retrieved documents into clusters. Choose based on your content characteristics: ### Similarity Clustering (default) [](#similarity-clustering-default) Groups documents with clear thematic boundaries. Best for already well-organized content with distinct topics. **Use Similarity Clustering when:** - You have heterogeneous content with clear topic boundaries - Your documents have distinct themes that don't overlap much - Performance is important (faster processing) ``` use NeuronAI\RAG\Retrieval\RetrievalInterface; use NeuronCore\RaptorRetrieval\RaptorRetrieval; use NeuronCore\RaptorRetrieval\Clustering\SimilarityClustering; class WorkoutTipsAgent extends RAG { protected function retrieval(): RetrievalInterface { return new RaptorRetrieval( $this->resolveVectorStore(), $this->resolveEmbeddingsProvider(), $this->resolveProvider(), // Used for summarization new SimilarityClustering() ); } protected function embeddings(): EmbeddingsProviderInterface { return new ... } protected function vectorStore(): VectorStoreInterface { return new ... } } ``` ### Gaussian Mixture Clustering [](#gaussian-mixture-clustering) Handles overlapping topics where documents may belong to multiple themes simultaneously. Useful for research papers, news articles, or any content where topics naturally blend together rather than having sharp boundaries. **Use GMM when:** - Documents may relate to multiple topics simultaneously - You want the algorithm to discover the "natural" number of clusters in your data - You're dealing with research papers, news, or complex content where multiple topics blend ``` use NeuronAI\RAG\Retrieval\RetrievalInterface; use NeuronCore\RaptorRetrieval\RaptorRetrieval; use NeuronCore\RaptorRetrieval\Clustering\GaussianMixtureClustering; class WorkoutTipsAgent extends RAG { protected function retrieval(): RetrievalInterface { return new RaptorRetrieval( $this->resolveVectorStore(), $this->resolveEmbeddingsProvider(), $this->resolveProvider(), // Used for summarization new GaussianMixtureClustering() ); } protected function embeddings(): EmbeddingsProviderInterface { return new ... } protected function vectorStore(): VectorStoreInterface { return new ... } } ``` What is Neuron? --------------- [](#what-is-neuron) Neuron is a PHP framework for creating and orchestrating AI Agents. It allows you to integrate AI entities in your existing PHP applications with a powerful and flexible architecture. We provide tools for the entire agentic application development lifecycle, from LLM interfaces, to data loading, to multi-agent orchestration, to monitoring and debugging. In addition, we provide tutorials and other educational content to help you get started using AI Agents in your projects. **[Go to the official documentation](https://docs.neuron-ai.dev/)** [**Video Tutorial**](https://www.youtube.com/watch?v=oSA1bP_j41w) [![Neuron & Inspector](./docs/youtube.png)](https://www.youtube.com/watch?v=oSA1bP_j41w) ### Health Score 46 — FairBetter than 93% of packages Maintenance82 Actively maintained with recent releases Popularity30 Limited adoption so far Community8 Small or concentrated contributor base Maturity50 Maturing project, gaining track record Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Every ~23 days Recently: every ~37 days Total 8 Last Release 82d ago Major Versions 1.0.3 → 2.0.02025-10-21 2.x-dev → 3.0.02026-02-25 ### Community Maintainers ![](https://www.gravatar.com/avatar/320345fbe48c7cff2b3a25992c8207e959ae7817fb2fb97bb176dc6e559aacf5?d=identicon)[valerione](/maintainers/valerione) --- Top Contributors [![ilvalerione](https://avatars.githubusercontent.com/u/13559278?v=4)](https://github.com/ilvalerione "ilvalerione (23 commits)") --- Tags agentagentic-aiagentic-workflowaiai-agentai-agentsai-frameworkembeddingllmphpragrag-chatbotrag-pipelinevector-databasevector-search ### Code Quality TestsPHPUnit Static AnalysisPHPStan, Rector Code StylePHP CS Fixer Type Coverage Yes ### Embed Badge ![Health badge](/badges/neuron-core-raptor-retrieval/health.svg) ``` [![Health](https://phpackages.com/badges/neuron-core-raptor-retrieval/health.svg)](https://phpackages.com/packages/neuron-core-raptor-retrieval) ``` ### Alternatives [saikiran/geohash Geohash Algorithm to encode geographic coordinates to a string of letters and digits 44456.6k3](/packages/saikiran-geohash) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)