检索器
一个检索器是一个接口，可以根据非结构化的查询返回文档。它比向量存储更为通用。 检索器不需要能够存储文档，只需能够返回（或检索）它们即可。 检索器可以从向量存储创建，但也足够广泛以包括维基百科搜索和Amazon Kendra。
检索器接受一个字符串查询作为输入，并返回一个包含文档的列表作为输出。
对于如何使用检索器的具体说明，请参见这里的相关指南。
请注意，所有的向量存储都可以被转换为检索器。 参阅向量存储集成文档以了解可用的向量存储。 本页面列出了通过继承BaseRetriever实现的自定义检索器。
带您自己的文档
以下检索器允许您索引和搜索自定义文档集。
外部索引
以下检索器将在外部索引（例如，从互联网数据构建）中进行搜索。
| 检索器 | 来源 | 包 |
|---|---|---|
| ArxivRetriever | Scholarly articles on arxiv.org | langchain_community |
| TavilySearchAPIRetriever | Internet search | langchain_community |
| WikipediaRetriever | Wikipedia articles | langchain_community |
所有检索器
| 名称 | 描述 |
|---|---|
| Activeloop Deep Memory | Activeloop Deep Memory is a suite of tools that enables you to optimi... |
| Amazon Kendra | Amazon Kendra is an intelligent search service provided by Amazon Web... |
| Arcee | Arcee helps with the development of the SLMs—small, specialized, secu... |
| Arxiv | arXiv is an open-access archive for 2 million scholarly articles in t... |
| AskNews | AskNews infuses any LLM with the latest global news (or historical ne... |
| Azure AI Search | Azure AI Search (formerly known as Azure Cognitive Search) is a Micro... |
| Bedrock (Knowledge Bases) | This guide will help you getting started with the AWS Knowledge Bases... |
| BM25 | BM25 (Wikipedia) also known as the Okapi BM25, is a ranking function ... |
| Box | This will help you getting started with the Box retriever. For detail... |
| BREEBS (Open Knowledge) | BREEBS is an open collaborative knowledge platform. |
| Chaindesk | Chaindesk platform brings data from anywhere (Datsources: Text, PDF, ... |
| ChatGPT plugin | OpenAI plugins connect ChatGPT to third-party applications. These plu... |
| Cognee | This will help you getting started with the Cognee retriever. For det... |
| Cohere reranker | Cohere is a Canadian startup that provides natural language processin... |
| Cohere RAG | Cohere is a Canadian startup that provides natural language processin... |
| Contextual AI Reranker | Contextual AI's Instruction-Following Reranker is the world's first r... |
| Dappier | Dappier connects any LLM or your Agentic AI to real-time, rights-clea... |
| DocArray | DocArray is a versatile, open-source tool for managing your multi-mod... |
| Dria | Dria is a hub of public RAG models for developers to both contribute ... |
| ElasticSearch BM25 | Elasticsearch is a distributed, RESTful search and analytics engine. ... |
| Elasticsearch | Elasticsearch is a distributed, RESTful search and analytics engine. ... |
| Embedchain | Embedchain is a RAG framework to create data pipelines. It loads, ind... |
| FlashRank reranker | FlashRank is the Ultra-lite & Super-fast Python library to add re-ran... |
| Fleet AI Context | Fleet AI Context is a dataset of high-quality embeddings of the top 1... |
| Galaxia | Galaxia is GraphRAG solution, which automates document processing, kn... |
| Google Drive | This notebook covers how to retrieve documents from Google Drive. |
| Google Vertex AI Search | Google Vertex AI Search (formerly known as Enterprise Search on Gener... |
| Graph RAG | Graph traversal over any Vector Store using document metadata. |
| IBM watsonx.ai | WatsonxRerank is a wrapper for IBM watsonx.ai foundation models. |
| JaguarDB Vector Database | [JaguarDB Vector Database](http://www.jaguardb.com/windex.html |
| Kay.ai | Kai Data API built for RAG 🕵️ We are curating the world's largest da... |
| Kinetica Vectorstore based Retriever | Kinetica is a database with integrated support for vector similarity ... |
| kNN | In statistics, the k-nearest neighbours algorithm (k-NN) is a non-par... |
| LinkupSearchRetriever | Linkup provides an API to connect LLMs to the web and the Linkup Prem... |
| LLMLingua Document Compressor | LLMLingua utilizes a compact, well-trained language model (e.g., GPT2... |
| LOTR (Merger Retriever) | Lord of the Retrievers (LOTR), also known as MergerRetriever, takes a... |
| Metal | Metal is a managed service for ML Embeddings. |
| Milvus Hybrid Search | Milvus is an open-source vector database built to power embedding sim... |
| NanoPQ (Product Quantization) | Product Quantization algorithm (k-NN) in brief is a quantization algo... |
| needle | Needle Retriever |
| Nimble | NimbleSearchRetriever enables developers to build RAG applications an... |
| Outline | Outline is an open-source collaborative knowledge base platform desig... |
| Permit | Permit is an access control platform that provides fine-grained, real... |
| Pinecone Hybrid Search | Pinecone is a vector database with broad functionality. |
| Pinecone Rerank | This notebook shows how to use PineconeRerank for two-stage vector re... |
| PubMed | PubMed® by The National Center for Biotechnology Information, Nationa... |
| Qdrant Sparse Vector | Qdrant is an open-source, high-performance vector search engine/datab... |
| RAGatouille | RAGatouille makes it as simple as can be to use ColBERT! |
| RePhraseQuery | RePhraseQuery is a simple retriever that applies an LLM between the u... |
| Rememberizer | Rememberizer is a knowledge enhancement service for AI applications c... |
| SEC filing | SEC filing is a financial statement or other formal document submitte... |
| Self-querying retrievers | |
| SVM | Support vector machines (SVMs) are a set of supervised learning metho... |
| TavilySearchAPI | Tavily's Search API is a search engine built specifically for AI agen... |
| TF-IDF | TF-IDF means term-frequency times inverse document-frequency. |
| **NeuralDB** | NeuralDB is a CPU-friendly and fine-tunable retrieval engine develope... |
| ValyuContext | Valyu allows AI applications and agents to search the internet and pr... |
| Vectorize | This notebook shows how to use the LangChain Vectorize retriever. |
| Vespa | Vespa is a fully featured search engine and vector database. It suppo... |
| Wikipedia | Overview |
| You.com | you.com API is a suite of tools designed to help developers ground th... |
| Zep Cloud | Retriever Example for Zep Cloud |
| Zep Open Source | Retriever Example for Zep |
| Zilliz Cloud Pipeline | Zilliz Cloud Pipelines transform your unstructured data to a searchab... |
| Zotero | This will help you getting started with the Zotero retriever. For det... |