27 lines
1.1 KiB
YAML
27 lines
1.1 KiB
YAML
- data_path: "https://sasales2caiprd.blob.core.chinacloudapi.cn/doc-landing-cat-usermanual-prd?sp=racwdl&st=2025-08-27T06:26:11Z&se=2035-08-27T14:41:11Z&spr=https&sv=2024-11-04&sr=c&sig=7GVqfbWPM5VDRW8crTeR06KsSPX%2BuuDLjN7ceqBuLCE%3D"
|
|
datasource_name: "cat-usermanual-prd"
|
|
data_dir: ""
|
|
base_path: "/app/run_tmp"
|
|
process_file_num: 0
|
|
process_file_last_modify: "2025-06-24 00:00:00"
|
|
chunk_size: 2048
|
|
token_overlap: 128
|
|
index_schemas:
|
|
- index_name: "index-cat-usermanual-chunk-prd"
|
|
data_type: ["chunk"]
|
|
field_type: "append"
|
|
upload_batch_size: 50
|
|
fields: ["filepath", "title"]
|
|
full_metadata_vector_fields: ["full_headers", "doc_metadata"]
|
|
semantic_config_name: "default"
|
|
vector_config_name: "vectorSearchProfile"
|
|
update_by_field: "filepath"
|
|
vector_fields:
|
|
- field: "contentVector"
|
|
append_fields: ["content"]
|
|
- field: "full_metadata_vector"
|
|
append_fields: ["full_headers", "doc_metadata"]
|
|
merge_fields:
|
|
- key: "doc_metadata"
|
|
fields: ["title"]
|
|
full_metadata_vector_fields: ["full_headers", "doc_metadata"] |