Initial commit

main.py

@@ -0,0 +1,41 @@
+import gradio as gr
+import spacy
+from transformers import pipeline
+import boto3
+nlp = spacy.load("en_core_web_sm")
+ner_pipeline = pipeline("ner", model="Jean-Baptiste/roberta-large-ner-english", aggregation_strategy="simple", grouped_entities=True)
+
+
+def greet(model_type, text):
+    if model_type == "Spacy":
+        doc = nlp(text)
+
+        pos_tokens = []
+
+        for token in doc:
+            if token.ent_type_ != "":
+                pos_tokens.append((token.text, token.ent_type_))
+            else:
+                pos_tokens.append((token.text, None))
+        return pos_tokens
+    elif model_type == "Roberta":
+        output = ner_pipeline(text)
+        print(output)
+        return {"text": text, "entities": [
+            {"word": entity["word"], "entity": entity["entity_group"], "start": entity['start'],
+             'end': entity['end']}
+            for entity in output]}
+    elif model_type == "AWS Comprehend":
+        client = boto3.client('comprehend')
+        response = client.detect_entities(
+                Text=text, LanguageCode='en')
+        print(response)
+        return {"text": text, "entities": [{"word": entity["Text"], "entity": entity["Type"], "start": entity['BeginOffset'], 'end': entity['EndOffset']}
+                                           for entity in response["Entities"]]}
+
+
+demo = gr.Interface(fn=greet, inputs=[gr.Radio(["Spacy", "Roberta", "AWS Comprehend"]), "text"],
+                    outputs="highlight", title="Key Matcher",
+                    description=f"Find the best match for a key from the list of ",)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+spacy
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl
+transformers
+boto3