From 5985551abaf9418c1c37ef9fd6db39a6c9c94d69 Mon Sep 17 00:00:00 2001
From: sigoden <sigoden@gmail.com>
Date: Wed, 26 Jun 2024 21:51:06 +0800
Subject: feat: rag load websites (#655)

---
 config.example.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'config.example.yaml')

diff --git a/config.example.yaml b/config.example.yaml
index 286bb83..52b311c 100644
--- a/config.example.yaml
+++ b/config.example.yaml
@@ -53,8 +53,10 @@ rag_min_score_rerank: 0                     # Specifies the minimum relevance sc
 rag_document_loaders:
   # You can add more loaders, here is the syntax:
   # <file-extension>: <command-to-load-the-file>
-  pdf: 'pdftotext $1 -'                     # Load .pdf file 
+  pdf: 'pdftotext $1 -'                     # Load .pdf file, see https://poppler.freedesktop.org
   docx: 'pandoc --to plain $1'              # Load .docx file
+  url: 'curl -fsSL $1'                      # Load url
+  # recursive_url: 'crawler $1 $2'          # Load websites
 
 # Defines the query structure using variables like __CONTEXT__ and __INPUT__ to tailor searches to specific needs
 rag_template: |
-- 
cgit v1.2.3