Langchain parent document retriever Functions. This can either be the whole raw document OR a larger chunk. default_get_input () How to use the Parent Document Retriever - Google Colab Sign in During retrieval, it first fetches the small chunks but then looks up the parent ids for those chunks and returns those larger documents. document_compressors. Retriever that combines embedding similarity with recency in retrieving values. class langchain. default_get_input () How to use the Parent Document Retriever - Google Colab Sign in. During retrieval, it first fetches the small chunks but then looks up the parent ids for those chunks and returns those larger documents. During retrieval, it first fetches the small chunks but then looks up the parent ids for those chunks and returns those larger documents. parent_document_retriever. retrievers. Retriever that uses a vector store and an LLM to generate the vector store queries. Retrieve small chunks then retrieve their parent documents. chain_extract. Given a query, use an LLM to re-phrase it. The small chunks are embedded, then on retrieval, the original "parent" documents are retrieved. retrievers. Note that "parent document" refers to the document that a small chunk originated from. A type of document retriever that splits input documents into smaller chunks while separately storing and preserving the original documents. When splitting documents for retrieval, there are often conflicting desires: You may want to have small documents, so that their embeddings can most During retrieval, it first fetches the small chunks but then looks up the parent ids for those chunks and returns those larger documents. ParentDocumentRetriever [source] ¶ Bases: MultiVectorRetriever. The Parent Document Retriever allows you to: (1) retrieve the full document a specific chunk originated from, or (2) pre-define a larger “parent” chunk, for each smaller chunk associated with that parent. API Reference: ParentDocumentRetriever. ybh hiaiz xknot rjbjw muzzc wnmms zgk ayxaax pfh dxwh