Retriever integrations

A retriever is an interface that returns documents given an unstructured query. It is more general than a vector store. A retriever does not need to be able to store documents, only to return (or retrieve) them. Retrievers can be created from vector stores, but are also broad enough to include other sources. Retrievers accept a string query as input and return a list of Document objects as output. Note that all vector stores can be cast to retrievers. Refer to the vector store integration docs for available vector stores. This page lists custom retrievers, implemented via subclassing BaseRetriever.

Bring-your-own documents

The below retrievers allow you to index and search a custom corpus of documents.

Retriever	Self-host	Cloud offering	Package
`AmazonKnowledgeBasesRetriever`	❌	✅	`langchain-aws`
`ElasticsearchRetriever`	✅	✅	`langchain-elasticsearch`
`MemstateRetriever`	❌	✅	`langchain-memstate`
`NVIDIARAGRetriever`	✅	❌	`langchain-nvidia-ai-endpoints`
`VertexAISearchRetriever`	❌	✅	`langchain-google-community`

External index

The below retrievers will search over an external index (e.g., constructed from Internet data or similar).

Retriever	Source	Package
`ParallelSearchRetriever`	Internet search via the Parallel Search API	`langchain-parallel`
`PerplexitySearchRetriever`	Internet search via the Perplexity Search API	`langchain-perplexity`
`YouRetriever`	Internet search	`langchain-youdotcom`

All retrievers

Retriever	Self-host	Cloud offering	Package
`AmazonKnowledgeBasesRetriever`	❌	✅	`langchain-aws`
`Google drive`			`langchain-google-community`
`VertexAISearchRetriever`	❌	✅	`langchain-google-community`
`Pinecone rerank`			`langchain-pinecone`
`Cohere RAG`			`langchain-cohere`
`Cohere reranker`			`langchain-cohere`
`NVIDIARAGRetriever`	✅	❌	`langchain-nvidia-ai-endpoints`
`WatsonxRerank`			`langchain-ibm`
`ElasticsearchRetriever`	✅	✅	`langchain-elasticsearch`
`PerplexitySearchRetriever`	❌	✅	`langchain-perplexity`
`Graph RAG`			`langchain-graph-retriever`
`Ragatouille`			`ragatouille`
`Self Querying with SAP HANA Cloud Vector Engine`			`langchain-hana`
`M3Retriever`	✅	❌	`m3-memory`
`LinkupSearchRetriever`			`langchain-linkup`
`Nebius`			`langchain-nebius`
`ParallelSearchRetriever`	❌	✅	`langchain-parallel`
`Nimble Extract`			`langchain-nimble`
`Nimble Search`			`langchain-nimble`
`YouRetriever`	❌	✅	`langchain-youdotcom`
`PerseusVaultRetriever`	✅	❌	`langchain-perseus-vault`
`SynapRetriever`			`maximem-synap-langchain`
`Contextual AI reranker`			`langchain-contextual`
`Sourcey`			`langchain-sourcey`
`Valyucontext`			`langchain-valyu`
`BoxRetriever`			`langchain-box`
`Dappier`			`langchain-dappier`
`SpiceDB Retriever`			`langchain-spicedb`
`MemstateRetriever`	❌	✅	`langchain-memstate`
`HighSNRDocumentCompressor`	❌	✅	`langchain-highsnr`
`Kinetica vectorstore based retriever`			`langchain-kinetica`
`EgnyteRetriever`			`egnyte-langchain-connector`
`Galaxia`			`langchain-galaxia-retriever`
`Permit`			`langchain-permit`
`VectorizeRetriever`			`langchain-vectorize`
`Cognee`			`langchain-cognee`
`AgentMail`			`langchain-agentmail`
`Zotero`			`langchain-zotero-retriever`
`EngramRetriever`			`langchain-engram`
`Greennode`			`langchain-greennode`
`Perigon`			`langchain-perigon`
`IMAP`			`langchain-imap`