full

app.py

@@ -1,4 +1,7 @@
 import streamlit as st
+from flair.data import Sentence
+from flair.models import SequenceTagger
+import re 
 import logging
 
 # Render Streamlit page
@@ -9,8 +12,51 @@ st.markdown(
 # Configure logger
 logging.basicConfig(format="\n%(asctime)s\n%(message)s", level=logging.INFO, force=True)
 
+# # Define functions
 def anonymise_text(text: str, metadata: str = "", white_listed_words: str = ""):
-    st.session_state.text_anon = "this is anonymised"
+    """anonymise text"""
+    if st.session_state.n_requests >= 5:
+        st.session_state.text_error = "Too many requests. Please wait a few seconds before anonymising more text."
+        logging.info(f"Session request limit reached: {st.session_state.n_requests}")
+        st.session_state.n_requests = 1
+        return
+
+    st.session_state.text = ""
+    st.session_state.text_error = ""
+
+    if not text:
+        st.session_state.text_error = "Please enter your text"
+        return
+
+    with text_spinner_placeholder:
+        with st.spinner("Please wait while your text is being anonymised..."):
+            
+            # flagged = openai.moderate(prompt)
+            # if flagged:
+            #     st.session_state.text_error = "Input flagged as inappropriate."
+            #     logging.info(f"Topic: {topic}{mood_output}{style_output}\n")
+            #     return
+            
+            # else:
+            # load tagger
+            tagger = SequenceTagger.load("flair/ner-english-large")
+            sentence = Sentence(text)
+            # predict NER tags
+            tagger.predict(sentence)
+            # iterate over entities and redact
+            enitities=[e.text for e in sentence.get_spans('ner')]
+            regex = re.compile('|'.join(map(re.escape, enitities)))
+            text_anon = regex.sub("<PID>", text)
+            
+            st.session_state.text_error = ""
+            st.session_state.n_requests += 1
+            st.session_state.text_anon = text_anon
+            logging.info(
+                f"text: {text}{metadata}{white_listed_words}\n"
+                f"text anonymised: {st.session_state.text_anon}"
+            )
+# def anonymise_text(text: str, metadata: str = "", white_listed_words: str = ""):
+#     st.session_state.text_anon = "this is anonymised"
 
 if "text" not in st.session_state:
     st.session_state.text = ""

requirements.txt

@@ -1,2 +1 @@
-transformers
 flair==0.11