diff options
| author | sigoden <sigoden@gmail.com> | 2024-06-27 12:30:09 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-27 12:30:09 +0800 |
| commit | f82524fd154a1bf4a7277db868147afdb0cd507a (patch) | |
| tree | 2fd588377d63b47b4ae1a051a0e363a9737f3f8f /config.example.yaml | |
| parent | 33a0049a81103c1f6c5639b9cec43cb14a9ef367 (diff) | |
| download | aichat-f82524fd154a1bf4a7277db868147afdb0cd507a.tar.gz | |
feat: implement native rag url loader (#660)
Diffstat (limited to 'config.example.yaml')
| -rw-r--r-- | config.example.yaml | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/config.example.yaml b/config.example.yaml index 262f41b..c7c5375 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -51,11 +51,12 @@ rag_min_score_keyword_search: 0 # Specifies the minimum relevance sc rag_min_score_rerank: 0 # Specifies the minimum relevance score for reranking # Defines document loaders rag_document_loaders: - # You can add more loaders, here is the syntax: - # <file-extension>: <command-to-load-the-file> + # You can add custom loaders using the following syntax: + # <file-extension>: <command-to-load-the-file> + # Note: Use `$1` for input filepath and `$2` for output filepath. If `$2` is not provided, output to stdout. 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 + # xlsx: 'ssconvert $1 $2' # Load .xlsx file # recursive_url: 'crawler $1 $2' # Load websites # Defines the query structure using variables like __CONTEXT__ and __INPUT__ to tailor searches to specific needs |