a8810519f8
optimize instructions configuration
...
optimize drilldown part logic
2025-02-04 15:29:24 -06:00
db0827435b
supplement EMEA AR configuration files
2025-01-16 11:30:44 -06:00
9f0e77a11e
support load configurations by doc_source parameter
2025-01-16 11:17:48 -06:00
91c86bb983
update AUS Prospectus relevant configuration
2025-01-08 17:40:57 -06:00
0a867dcf07
complete configuration for AUS Prospectus
2025-01-07 16:25:13 -06:00
9348e32caa
support more performance fee keywords
2025-01-06 13:14:20 -06:00
309bb714f6
fix issue for parsing data via Vision Function.
2024-12-11 16:49:04 -06:00
d673a99e21
switch back to extract data from image stream directly, instead of getting text from image stream as the first step, then extract data from extracted text.
...
The reason is: the quality of getting text from image steam is not good enough.
2024-12-10 16:17:47 -06:00
75ea5e70de
1. support fetch data from messy-code page by ChatGPT4o Vision function.
...
2. multilingual share features configuration
2024-12-09 17:47:42 -06:00
d79b05885d
optimize prompts for TOR
2024-12-06 14:50:34 -06:00
a25991e2bb
1. Set TOR reported name priority
...
2. Optimize investment mapping logic
2024-12-06 09:54:43 -06:00
70362b554f
Fix issue for "The last fund name of previous PDF page" logic:
...
If current page fund name starts with "The last fund name of previous PDF page" and with more contents below, then remove "The last fund name of previous PDF page".
2024-12-04 16:57:52 -06:00
a11a99fdc3
1. Optimize instructions: not to fetch the data with "up to" statement.
...
2. Add exception handler in function.
2024-12-03 11:27:28 -06:00
352886ade2
update instructions for TER, OGC, Performance Fees
2024-12-02 11:45:19 -06:00
843bbbd13f
dynamic loading instructions for multilingual.
2024-11-20 17:00:22 -06:00
067d89e0f9
Add datapoint_reportedname.json for dynamic loading reported names based on document language.
2024-11-19 16:49:15 -06:00
a42c0b5c2b
optimize retrieve fund instructions
2024-11-13 10:25:08 -06:00
7a41b03634
1. optimize instructions for fund name
...
2. optimize drilldown logic
2024-11-12 17:01:10 -06:00
2645d528b1
support output data point reported name
2024-10-29 16:47:45 -05:00
fa763f4f14
1. optimize instructions
...
2. optimize mapping algorithm
2024-10-24 16:24:21 -05:00
53dadf61f4
optimize keywords/ instructions for special cases documents.
2024-10-23 16:56:43 -05:00
171f3b6d1f
optimize for OGC data extraction.
2024-10-23 16:07:54 -05:00
03365227b9
optimize instructions
2024-10-21 11:04:53 -05:00
8b651f374c
optimize instructions
2024-10-14 09:12:05 -05:00
92a26cd262
optimize configuration
2024-10-11 12:16:34 -05:00
aa2c2332ae
optimize for more cases
2024-10-08 17:16:01 -05:00
8496c7b5ed
optimize instructions
...
optimize metrics algorithm
2024-09-20 16:46:44 -05:00
91530d6089
add more description for Performance Fees calculation rules
2024-09-20 11:58:48 -05:00
40bcce4404
instructions: explicitly announce, not to collect data which value with -, *, **, N/A, N/A%, N/A %, NONE
2024-09-20 10:26:18 -05:00
48dc8690c3
support extract data by pdf page image
2024-09-19 16:29:26 -05:00
98e86a6cfd
realize to calculate data extraction metrics.
2024-09-18 17:10:54 -05:00
932870f406
support split text for this case: outputs over 4K tokens.
2024-09-16 12:03:13 -05:00
0f6dbd27eb
optimize instructions for performance fees.
2024-09-13 16:10:44 -05:00
e17414173a
update to get more precise results
2024-09-12 16:00:49 -05:00
d56ac9482e
Adjust for output example format
2024-09-11 09:24:36 -05:00
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
1caf552065
support extract data by ChatGPT4o.
...
The instructions is generated dynamically.
2024-09-05 17:22:26 -05:00
f81e2862f3
update prompts to extract TOR, OGC, TER, Performance fees data.
2024-08-30 16:37:00 -05:00
63da030fe1
update general prompts
2024-08-29 17:05:58 -05:00
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
32676728f6
optimize prompts
2024-08-28 10:21:26 -05:00
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
843f588015
support chat with image by ChatGPT4o
2024-08-26 11:19:07 -05:00
fa46b45ad5
support output tables as markdown format from pdf documents
2024-08-19 15:49:45 -05:00
Blade He