jacob-mathison/doczyai-pipelines
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Activity

Merged in hotfix/agreement_name (pull request #321)

Browse Source 
apply agreement name hotfix only on missing

* apply agreement name hotfix only on missing


Approved-by: Katon Minhas
This commit is contained in:
Mayank Aamseek
2024-12-06 15:29:30 +00:00
committed by Katon Minhas
parent 47a01e13f0
commit c532aec3e9
1 changed files with 25 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fieldExtraction/src/cnc_hotfix.py
+25 -17
View File
@@ -642,30 +642,38 @@ def clean_agreement_name(df: pd.DataFrame,
If agreement name is not found, it runs on the context selected based on keywords.
"""
contract_title_chunk_dict = dict(itertools.islice(text_dict.items(), 5))
question = prompts.AC_DICT["CONTRACT_TITLE"]
df["Agreement Name (Contract Title)_corrected"] = df['Agreement Name (Contract Title)']
agreement_df = df[(df['Agreement Name (Contract Title)'].isna())|(df['Agreement Name (Contract Title)'].astype(str).str.len() < 5)]
agreement_df['Filename'] = agreement_df['Contract Name']
contract_list = agreement_df['Filename'].to_list()
contract_list = list(set(contract_list))
# process the contract
if contract_name in contract_list:
contract_title_chunk_dict = dict(itertools.islice(text_dict.items(), 5))
question = prompts.AC_DICT["CONTRACT_TITLE"]
context = "\n".join(
[contract_title_chunk_dict[str(page_num)] for page_num in contract_title_chunk_dict.keys()]
)
prompt = prompts.AC_SINGLE_FIELD_TEMPLATE(context, question)
prompt_answer_raw = claude_funcs.invoke_claude(
prompt, config.MODEL_ID_CLAUDE35_SONNET, contract_name, 8192)
if prompt_answer_raw == "N/A":
agreement_keywords = ["AGREEMENT", "AMENDMENT", "ADDENDUM", "PROVIDER", "CONTRACT", "MEMORANDUM", "LETTER", "REQUEST", "EFFECTIVE"]
page_list = ac_smart_chunking.chunk_hierarchical(
text_dict, agreement_keywords, False
)
context = "\n".join(
[text_dict[str(page_num)] for page_num in page_list]
[contract_title_chunk_dict[str(page_num)] for page_num in contract_title_chunk_dict.keys()]
)
prompt = prompts.AC_SINGLE_FIELD_TEMPLATE(context, question)
prompt_answer_raw = claude_funcs.invoke_claude(
prompt, config.MODEL_ID_CLAUDE35_SONNET, contract_name, 8192)
df.loc[df['Contract Name'] == contract_name, 'Agreement Name (Contract Title)_corrected'] = prompt_answer_raw
if prompt_answer_raw == "N/A":
agreement_keywords = ["AGREEMENT", "AMENDMENT", "ADDENDUM", "PROVIDER", "CONTRACT", "MEMORANDUM", "LETTER", "REQUEST", "EFFECTIVE"]
page_list = ac_smart_chunking.chunk_hierarchical(
text_dict, agreement_keywords, False
)
context = "\n".join(
[text_dict[str(page_num)] for page_num in page_list]
)
prompt = prompts.AC_SINGLE_FIELD_TEMPLATE(context, question)
prompt_answer_raw = claude_funcs.invoke_claude(
prompt, config.MODEL_ID_CLAUDE35_SONNET, contract_name, 8192)
df.loc[df['Contract Name'] == contract_name, 'Agreement Name (Contract Title)_corrected'] = prompt_answer_raw
return df