pipeline

langchain_pipeline.py

@@ -4,7 +4,6 @@ from pdf2docx import Converter
 from io import BytesIO
 import fitz  # PyMuPDF
 import re
-from tempfile import NamedTemporaryFile
 from langchain_core.prompts import PromptTemplate
 from langchain_openai import OpenAIEmbeddings
 from langchain_anthropic import ChatAnthropic
@@ -119,8 +118,14 @@ def create_redlined_word_doc(formatted_text, changes, output_path):
     doc.save(output_path)
     print(f"Redlined document saved to {output_path}")
 
-def pipeline(file, model_name, balance_type, apsn_transactions, max_fees_per_day, min_overdrawn_fee, min_transaction_overdraft):
-    disclosure_text = high_level.extract_text(file)
+def pipeline(uploaded_file, model_name, balance_type, apsn_transactions, max_fees_per_day, min_overdrawn_fee, min_transaction_overdraft):
+    # Save the uploaded file to a temporary file
+    with NamedTemporaryFile(delete=False, suffix='.pdf') as tmp:
+        tmp.write(uploaded_file.read())
+        tmp_path = tmp.name
+
+    # Extract text from the uploaded file
+    disclosure_text = high_level.extract_text(tmp_path)
 
     prompt_template = """
     law context:
@@ -180,7 +185,7 @@ reasons for changes citing caselaw
     if not os.path.exists(output_directory):
         os.makedirs(output_directory)
 
-    formatted_text = extract_text_with_formatting(file)
+    formatted_text = extract_text_with_formatting(tmp_path)
 
     create_redlined_word_doc(formatted_text, changes, output_path)