47 lines
2.4 KiB
Plaintext
47 lines
2.4 KiB
Plaintext
|
|
Instructions:
|
||
|
|
Please read the image carefully.
|
||
|
|
1. Identify the text in the PDF page image.
|
||
|
|
The text will be as output with key: "text".
|
||
|
|
2. Identify and format the all of tables in the PDF page image.
|
||
|
|
Table contents should be as markdown format,
|
||
|
|
ensuring the table structure and contents are exactly as in the PDF page image.
|
||
|
|
The format should be: |Column1|Column2|\n|---|---|\n|Row1Col1|Row1Col2|
|
||
|
|
Each cell in the table(s) should be in the proper position of relevant row and column.
|
||
|
|
The markdown table(s) will be as output with key: "table_contents".
|
||
|
|
3. Extract data from upon parsed text and table(s) contents.
|
||
|
|
3.1 The upon parsed text and table(s) contents as context.
|
||
|
|
3.2 Data Extraction from parsed table contents
|
||
|
|
Maybe there are TER, performance fees data in the parsed table(s) contents.
|
||
|
|
The TER reported name could be:Total Expense Ratio, TER, Annualised TER including performance fees,etc.
|
||
|
|
The performance fees reported name could be:performance fees, performance fees ratio, etc.
|
||
|
|
If exist both of "TER including performance fees" and "TER excluding performance fees", the performance fees should be:
|
||
|
|
TER including performance fees - TER excluding performance fees.
|
||
|
|
The TER and performance fees value is percentage number, it means the value should be less than 100.
|
||
|
|
Most of cases, the data is in the table(s) of context.
|
||
|
|
|
||
|
|
3.3 Fund name/ share class name extraction from upon context
|
||
|
|
Please extract fund name and share class name from the context.
|
||
|
|
If can't find fund name or share class name from table contents,
|
||
|
|
please try to find them from parsed text contents.
|
||
|
|
|
||
|
|
3.4 Output
|
||
|
|
If possible, please extract fund name, share class name, TER or performance fees value as the output.
|
||
|
|
One fund could be with multiple share classes and relevant TER or performance fees values.
|
||
|
|
The output should be JSON format, the format is like:
|
||
|
|
{
|
||
|
|
"text": "text from image",
|
||
|
|
"table_contents": ["|Column1|Column2|\n|---|---|\n|Row1Col1|Row1Col2|"],
|
||
|
|
"data":
|
||
|
|
[{
|
||
|
|
"fund name": "fund 1",
|
||
|
|
"share data": [{"share name": "share 1", "ter": 1.23, "performance fees": 0.2},{"share name": "share 2", "ter": 2.56, "performance fees": 1.2}]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"fund name": "fund 2",
|
||
|
|
"share data": [{"share name": "share a", "ter": 1.16, "performance fees": 0.5},{"share name": "share b", "ter": 1.45, "performance fees": 1.1}]
|
||
|
|
}]
|
||
|
|
}
|
||
|
|
Only output JSON data.
|
||
|
|
If can't find share class name in context, please output empty JSON data: []
|
||
|
|
|
||
|
|
Answer:
|