more fixes

app.py

@@ -1,10 +1,14 @@
 import gradio as gr
-import re
-import os
+
 from mailparser import parse_from_string
 from bs4 import BeautifulSoup
 from gliner import GLiNER
+from typing import Dict, Union, List
+
 import spacy
+import re
+import os
+
 
 nlp = spacy.load("en_core_web_sm")
 _MODEL = {}
@@ -48,6 +52,26 @@ def get_model(model_name: str = None):
 
     return _MODEL[model_name]
 
+def parse_query(sentences: List[str], labels: Union[str, list], threshold: float = 0.3, nested_ner: bool = False, model_name: str = None) -> List[Dict[str, Union[str, list]]]:
+    model = get_model(model_name)
+
+    if isinstance(labels, str):
+        labels = [i.strip() for i in labels.split(",")]
+
+    results = []
+
+    for sentence in sentences:
+        _entities = model.predict_entities(sentence, labels, threshold=threshold)
+
+        entities = []
+
+        for entity in _entities:
+            entities.append(entity)
+
+        results.append({"sentence": sentence, "entities": entities})
+
+    return results
+
 def present(email_content, labels):
     email = accept_mail(email_content)
     cleaned_text = clean_email(email)
@@ -55,13 +79,15 @@ def present(email_content, labels):
     sentence_list = get_sentences(further_cleaned_text)
     # entity_info = '\n'.join([f"{text}: {label}" for text, label in entities])
     
+    result = parse_query(sentence_list, labels, threshold=0.3, nested_ner=False, model_name="urchade/gliner_base")
+
     email_info = {
         "Subject": email.subject,
         "From": email.from_,
         "To": email.to,
         "Date": email.date,
         "Cleaned Body": further_cleaned_text,
-        # "Extracted Entities": entity_info
+        "Extracted Entities": result
     }
     return [email_info[key] for key in email_info]
 
@@ -81,7 +107,7 @@ demo = gr.Interface(
         gr.components.Textbox(label="To"),
         gr.components.Textbox(label="Date"),
         gr.components.Textbox(label="Cleaned Body"),
-        # gr.components.Textbox(label="Extracted Entities")
+        gr.components.Textbox(label="Extracted Entities")
     ],
     title="Email Info",
     description="Enter the email content below to view its details and detected entities."

requirements.txt

@@ -2,5 +2,5 @@ gliner
 mail-parser
 gradio
 beautifulsoup4
-spacy>=3.1.3
+spacy==3.0.6
 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

@@ -1,4 +1,4 @@
 # spaces.yml
 pip:
-  - spacy==3.1.3
-  - https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.1.0/en_core_web_sm-3.1.0.tar.gz
+  - spacy==3.0.6
+  - https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0.tar.gz