langchainã®ã‚¢ãƒƒãƒ—デートã§è¿½åŠ ã•ã‚ŒãŸ"Contextual Compression Retriever"を使用ã—ã¦,200ページ超ã®webページをèªã¿ã“ã¾ã›ãŸQ&Aボットを作æˆã™ã‚‹ - QiitaUnstructuredURLLoaderã§ãƒ›ãƒ¼ãƒ ページã®å†…容をèªã¿ã“ã¿ã€textsplitterã§é©åˆ‡ãªã‚µã‚¤ã‚ºã«ãƒ†ã‚ストを分割ã—ã¾ã™ã€‚ ãã®å¾Œã€OpenAIEmbeddingsを使用ã—ã¦ã€åŸ‹ã‚è¾¼ã¿ã‚’作æˆã—ã¾ã™ã€‚ ãã®åŸ‹ã‚è¾¼ã¿ã‚’EmbeddingsFilterを用ã„ã¦ãƒ•ã‚£ãƒ«ã‚¿ãƒªãƒ³ã‚°ã—ã¾ã™ã€‚ (EmbeddingsFilter Making an extra LLM call over each retrieved document is expensive and slow. The EmbeddingsFilter provides a cheaper and faster option by embedding the documents and query and only returning those documents which have sufficiently simil
{{#tags}}- {{label}}
{{/tags}}