Merged in feature/daip2-33-optimize-exhibit-start-prompt (pull request #343)

Feature/daip2 33 optimize exhibit start prompt

* Updated Exhibit Check prompt

* Updated prompt, reorg

* Switch to claude 3 haiku for new exhibit check prompt


Approved-by: Alex Galarce
This commit is contained in:
Katon Minhas
2025-01-06 21:08:56 +00:00
parent 3740588efa
commit 8c3c674e75
4 changed files with 33 additions and 25 deletions
@@ -10,6 +10,7 @@ import smart_chunking_funcs
import string_funcs
import valid
from valid import DERIVED_INDICATOR_FIELDS
from regex_patterns import PIPE_PATTERN
def clean_newlines(contract_text: str) -> str:
@@ -299,3 +300,15 @@ def filter_quick_review(text_dict):
or "COVER SHEET" in page_text.upper()
}
def get_exhibit_pages(text_dict, filename):
exhibit_pages = []
for page_num, page in text_dict.items():
prompt = prompts.EXHIBIT_CHECK(page[0:100])
claude_answer_raw = claude_funcs.invoke_claude(
prompt, config.MODEL_ID_CLAUDE3_HAIKU, filename, max_tokens=10
)
claude_answer_extracted = re.findall(pattern=PIPE_PATTERN, string=claude_answer_raw)[-1]
if "Y" in claude_answer_extracted:
exhibit_pages.append(page_num)
return exhibit_pages