AI_POC/catonline_ai
11
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
Ye Shijie
2025-09-26 17:15:54 +08:00
commit db0e5965ec
211 changed files with 40437 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
vw-document-ai-indexer/deploy/dev-abroad/config.yaml Normal file
View File

@@ -0,0 +1,50 @@
- data_path: "https://sasales2caiprd.blob.core.chinacloudapi.cn/doc-landing-cat-abroad-prd?sp=rl&st=2025-08-02T08:25:56Z&se=2125-08-02T16:40:56Z&spr=https&sv=2024-11-04&sr=c&sig=lJui2%2BOs8V%2BdzCkjchQCR7ITWT28tJ0HAq8bIhkkM%2Bk%3D"
datasource_name: "cat-standard-regulation-oversea"
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: 256
index_schemas:
- index_name: "index-catonline-chunk-oversea"
data_type: ["metadata", "document", "chunk"]
upload_batch_size: 50
fields: ["filepath","timestamp","file_Name","file_Url","file_Type","entity_Attribute","standard_Id","standard_Code","standard_Title_Cn","standard_Title_En","domain_Name","standard_State_Name","type_Name","publish_Date","draft_type_name","qc_Abroad_Professional_Fields","applicable_Models","standard_Type_Name","technical_Field_Name","create_Time","update_Time","version_Id","version_Name","version_Parent_id","version_Parent_Name","technical_Series_No","implementation_Date","version_Publish_Date","newFlag_State","publish_Status_Text","implementation_Status_Text","new_Car_Implementation_Status_Text","production_Car_Implementation_Status_Text","production_Car_Implementation_Str"]
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"]
- index_name: "index-catonline-document-oversea"
data_type: ["document", "metadata"]
key_fields: ["filepath"]
upload_batch_size: 1
fields: ["filepath","timestamp","file_Name","file_Url","file_Type","entity_Attribute","standard_Id","standard_Code","standard_Title_Cn","standard_Title_En","domain_Name","standard_State_Name","type_Name","publish_Date","draft_type_name","qc_Abroad_Professional_Fields","applicable_Models","standard_Type_Name","technical_Field_Name","create_Time","update_Time","version_Id","version_Name","version_Parent_id","version_Parent_Name","technical_Series_No","implementation_Date","version_Publish_Date","newFlag_State","publish_Status_Text","implementation_Status_Text","new_Car_Implementation_Status_Text","production_Car_Implementation_Status_Text","production_Car_Implementation_Str"]
merge_content_fields: ["content"]
full_metadata_vector_fields: ["doc_metadata"]
semantic_config_name: "default"
vector_config_name: "vectorSearchProfile"
update_by_field: "filepath"
vector_fields:
- field: "full_metadata_vector"
append_fields: ["doc_metadata"]
- index_name: "index-catonline-standard-regulation-oversea"
data_type: ["metadata"]
key_fields: ["standard_Id"]
upload_batch_size: 1
fields: ["filepath","timestamp","file_Name","file_Url","file_Type","entity_Attribute","standard_Id","standard_Code","standard_Title_Cn","standard_Title_En","domain_Name","standard_State_Name","type_Name","publish_Date","draft_type_name","qc_Abroad_Professional_Fields","applicable_Models","standard_Type_Name","technical_Field_Name","create_Time","update_Time","version_Id","version_Name","version_Parent_id","version_Parent_Name","technical_Series_No","implementation_Date","version_Publish_Date","newFlag_State","publish_Status_Text","implementation_Status_Text","new_Car_Implementation_Status_Text","production_Car_Implementation_Status_Text","production_Car_Implementation_Str"]
vector_config_name: "vectorSearchProfile"
full_metadata_vector_fields: ["doc_metadata"]
semantic_config_name: "default"
update_by_field: "standard_Id"
vector_fields:
- field: "full_metadata_vector"
append_fields: ["doc_metadata"]
merge_fields:
- key: "doc_metadata"
fields: ["file_Name","entity_Attribute","standard_Code","standard_Title_Cn","standard_Title_En","domain_Name","standard_State_Name","type_Name","draft_type_name","qc_Abroad_Professional_Fields","applicable_Models","standard_Type_Name","technical_Field_Name","version_Name","version_Parent_Name","technical_Series_No","newFlag_State","publish_Status_Text","implementation_Status_Text","new_Car_Implementation_Status_Text","production_Car_Implementation_Status_Text","production_Car_Implementation_Str " ]