new updates for spacy

app.py

@@ -2,6 +2,9 @@ import gradio as gr
 import re
 from mailparser import parse_from_string
 from bs4 import BeautifulSoup
+import spacy
+
+nlp = spacy.load("en_core_web_sm")
 
 def accept_mail(email_content):
     email = parse_from_string(email_content)
@@ -15,39 +18,52 @@ def clean_email(email):
     return cleaned_text
 
 def remove_special_characters(text):
-    pattern = r'[=_-]+' 
-    
+    pattern = r'[=_-]+'
     cleaned_text = re.sub(pattern, '', text)
     return cleaned_text
 
-def present(email_content):
+def extract_entities(text, labels):
+    doc = nlp(text)
+    entities = []
+    for ent in doc.ents:
+        if ent.label_ in labels:
+            entities.append((ent.text, ent.label_))
+    return entities
+
+def present(email_content, labels):
     email = accept_mail(email_content)
     cleaned_text = clean_email(email)
     further_cleaned_text = remove_special_characters(cleaned_text)
+    entities = extract_entities(further_cleaned_text, labels)
+    entity_info = '\n'.join([f"{text}: {label}" for text, label in entities])
+    
     email_info = {
         "Subject": email.subject,
         "From": email.from_,
         "To": email.to,
         "Date": email.date,
-        # "Message ID": email.message_id,
-        # "Headers": str(email.headers),
-        "Cleaned Body": further_cleaned_text
+        "Cleaned Body": further_cleaned_text,
+        "Extracted Entities": entity_info
     }
     return [email_info[key] for key in email_info]
 
+labels = ["PERSON", "PRODUCT", "DEAL", "ORDER", "ORDER PAYMENT METHOD", "STORE", "LEGAL ENTITY", "MERCHANT", "FINANCIAL TRANSACTION", "UNCATEGORIZED", "DATE"]
+
 demo = gr.Interface(
     fn=present, 
-    inputs="text", 
+    inputs=[
+        gr.components.Textbox(label="Email Content"),
+        gr.components.CheckboxGroup(label="Labels to Detect", choices=labels, default=labels)
+    ],
     outputs=[
         gr.components.Textbox(label="Subject"),
         gr.components.Textbox(label="From"),
         gr.components.Textbox(label="To"),
         gr.components.Textbox(label="Date"),
-        # gr.components.Textbox(label="Message ID"),
-        # gr.components.Textbox(label="Headers"),
-        gr.components.Textbox(label="Cleaned Body")
+        gr.components.Textbox(label="Cleaned Body"),
+        gr.components.Textbox(label="Extracted Entities")
     ],
     title="Email Info",
-    description="Enter the email content below to view its details."
+    description="Enter the email content below to view its details and detected entities."
 )
 demo.launch()

requirements.txt

@@ -2,3 +2,5 @@ gliner
 mail-parser
 gradio
 beautifulsoup4
+spacy>=3.0
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz

spaces.yml

@@ -0,0 +1,4 @@
+# spaces.yml
+pip:
+  - spacy>=3.0
+  - https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz