> When the retriever infers filters from a users query and applies those filters to the underlying data https://python.langchain.com/docs/modules/data_connection/retrievers/self_query https://python.langchain.com/docs/integrations/retrievers/self_query/?ref=blog.langchain.dev * https://twitter.com/HardKothari/status/1717549379056275563 * https://twitter.com/HardKothari/status/1719338506151940550 * 案例 Langchain HTMLHeaderTextSplitter 加上 [[Self-Querying Retriever]] * https://blog.langchain.dev/a-chunk-by-any-other-name/ * elasticsearch https://twitter.com/LangChainAI/status/1725517090646282738 * https://blog.langchain.dev/query-construction/ 中定義 Text-to-metadata-filter * https://python.langchain.com/v0.1/docs/use_cases/query_analysis/techniques/structuring/ ## Llamaindex 叫做 Auto-Retriever https://docs.llamaindex.ai/en/stable/examples/vector_stores/chroma_auto_retriever.html https://twitter.com/llama_index/status/1733289204380311703 https://twitter.com/jerryjliu0/status/1737516362451554696