File tree 1 file changed +17
-1
lines changed
1 file changed +17
-1
lines changed Original file line number Diff line number Diff line change @@ -90,6 +90,21 @@ def __call__(self, _markdown: str) -> ManualInfo:
90
90
]
91
91
)
92
92
93
+ class CleanUpManual (cocoindex .op .FunctionSpec ):
94
+ """Clean up manual information."""
95
+
96
+
97
+
98
+ @cocoindex .op .executor_class ()
99
+ class CleanUpManualExecutor :
100
+ """Executor for CleanUpManual."""
101
+
102
+ spec : CleanUpManual
103
+
104
+ def __call__ (self , manual_info : ManualInfo ) -> ManualInfo | None :
105
+ # TODO: Clean up
106
+ return manual_info
107
+
93
108
@cocoindex .flow_def (name = "ManualExtraction" )
94
109
def manual_extraction_flow (flow_builder : cocoindex .FlowBuilder , data_scope : cocoindex .DataScope ):
95
110
"""
@@ -101,7 +116,8 @@ def manual_extraction_flow(flow_builder: cocoindex.FlowBuilder, data_scope: coco
101
116
102
117
with data_scope ["documents" ].row () as doc :
103
118
doc ["markdown" ] = doc ["content" ].transform (PdfToMarkdown ())
104
- doc ["manual_info" ] = doc ["markdown" ].transform (ExtractManual ())
119
+ doc ["raw_manual_info" ] = doc ["markdown" ].transform (ExtractManual ())
120
+ doc ["manual_info" ] = doc ["raw_manual_info" ].transform (CleanUpManual ())
105
121
manual_infos .collect (filename = doc ["filename" ], manual_info = doc ["manual_info" ])
106
122
107
123
manual_infos .export (
You can’t perform that action at this time.
0 commit comments