text

langchain_pipeline.py

@@ -1,5 +1,5 @@
 import os
-from pdfminer.high_level import extract_text
+from pdfminer import high_level
 from langchain_astradb import AstraDBVectorStore
 from langchain_core.prompts import PromptTemplate
 from langchain_openai import OpenAIEmbeddings
@@ -25,7 +25,12 @@ def model_names():
     return models.keys()
 
 def pipeline(file, model_name, balance_type, apsn_transactions, max_fees_per_day, min_overdrawn_fee, min_transaction_overdraft):
-    disclosure_text = extract_text(file)
+    disclosure_text = high_level.extract_text(file)
+    
+    # Read the legal cases context from the text file
+    with open("all Text OCR.txt", "r") as f:
+        legal_cases_context = f.read()
+
     astra = AstraDBVectorStore(
         api_endpoint=ASTRA_DB_API_ENDPOINT,
         token=ASTRA_DB_APPLICATION_TOKEN,
@@ -37,44 +42,25 @@ def pipeline(file, model_name, balance_type, apsn_transactions, max_fees_per_day
 
     prompt = PromptTemplate.from_template(
         """
-    law context:
-
-     United State Dealt a 26 a are Vini
-liability for Wells Fargo's violations of the
-"fraudulent" prong of California's Unfair
-Competition Law is affirmed, and we remand for
-the district court to determine what relief, if any, is
-appropriate and consistent with this opinion.
-10 In lisht of the decision to vacate thel
-parties' arguments as to the amount of
-restitution awarded, prejudgment interest,
-and punitive damages.
-AFFIRMED in part, REVERSED in part, and
-REMANDED. Each party shall pay its own fees
-on appeal.
-15
-
-casetext
-Gutierrez v. Wells Fargo Bank, NA
-704 F.3d 712 (9th Cir. 2012)
---------
+        law context:
+        {context}
 
-above are several cases and a bank disclosure. Using the cases, please provide changes to the disclosure and keep as much formatting as possible and to ensure there are no legal contradictions between the content of the disclosure and the cases and please provide reasoning for each proposed change. Please also integrate the bank's policies into the disclosure. In the first sentence, please include a reference to the account agreement "for more information on overdrafts" and a placeholder for a URL. Available balance or ledger balance should replace money in the first sentence.
-Here are the answers to the bank's policy questions:
-Do you charge on available balance or ledger balance?: {balance_type}
-Do you charge for APSN transactions?: {apsn_transactions}
-How many overdraft fees per day can be charged?: {max_fees_per_day}
-What is the minimum amount overdrawn to incur a fee?: {min_overdrawn_fee}
-What is the minimum transaction amount to trigger an overdraft?: {min_transaction_overdraft}
+        above are several cases and a bank disclosure. Using the cases, please provide changes to the disclosure and keep as much formatting as possible and to ensure there are no legal contradictions between the content of the disclosure and the cases and please provide reasoning for each proposed change. Please also integrate the bank's policies into the disclosure. In the first sentence, please include a reference to the account agreement "for more information on overdrafts" and a placeholder for a URL. Available balance or ledger balance should replace money in the first sentence.
+        Here are the answers to the bank's policy questions:
+        Do you charge on available balance or ledger balance?: {balance_type}
+        Do you charge for APSN transactions?: {apsn_transactions}
+        How many overdraft fees per day can be charged?: {max_fees_per_day}
+        What is the minimum amount overdrawn to incur a fee?: {min_overdrawn_fee}
+        What is the minimum transaction amount to trigger an overdraft?: {min_transaction_overdraft}
 
-Please output in the following format: 
-{{entire disclosure text with exact formatting as original document}}
-------
-{{reasons_for_changes}}
+        Please output in the following format: 
+        {{entire disclosure text}}
+        ------
+        {{reasons_for_changes}}
         """
     )
     val = prompt.format(
-        context=related_docs,
+        context=legal_cases_context,
         disclosure=disclosure_text,
         balance_type=balance_type,
         apsn_transactions=apsn_transactions,