Blade He
932870f406
support split text for this case: outputs over 4K tokens.
2024-09-16 12:03:13 -05:00
Blade He
0f6dbd27eb
optimize instructions for performance fees.
2024-09-13 16:10:44 -05:00
Blade He
e17414173a
update to get more precise results
2024-09-12 16:00:49 -05:00
Blade He
d56ac9482e
Adjust for output example format
2024-09-11 09:24:36 -05:00
Blade He
878383a72c
support extract the continuous page(s) for not missing next page data which without table header.
2024-09-06 16:29:35 -05:00
Blade He
1caf552065
support extract data by ChatGPT4o.
...
The instructions is generated dynamically.
2024-09-05 17:22:26 -05:00
Blade He
f81e2862f3
update prompts to extract TOR, OGC, TER, Performance fees data.
2024-08-30 16:37:00 -05:00
Blade He
63da030fe1
update general prompts
2024-08-29 17:05:58 -05:00
Blade He
134b365b68
Try to generate general prompts for LUX English AR
...
- Support output fund name ,share name, TER, performance fees, OGC
- Only output data point and value which can be found in page text.
- Output fund level data and share level data separately.
- List part of special cases to fit cases as many as possible.
2024-08-28 16:44:19 -05:00
Blade He
32676728f6
optimize prompts
2024-08-28 10:21:26 -05:00
Blade He
15720d8bfd
1. Text-and-image all in one chat function by ChatGPT4o
...
2. many experiments for extracting data by two ways:
page text or page image.
2024-08-26 17:17:39 -05:00
Blade He
843f588015
support chat with image by ChatGPT4o
2024-08-26 11:19:07 -05:00
Blade He
fa46b45ad5
support output tables as markdown format from pdf documents
2024-08-19 15:49:45 -05:00