Update app.py

app.py

@@ -6,3 +6,88 @@ from sentence_transformers.util import semantic_search
 import pandas as pd
 import requests
 
+#Import corpus embeddings
+corpus_ger = pd.read_json('JoBeer/corpus_embed_ger_model5.json')
+corpus_eng = pd.read_json('JoBeer/corpus_embed_eng_mboth.json')
+corpus_fr = pd.read_json('JoBeer/corpus_embed_fr_Sahajtomar.json')
+
+#Import models
+model_ger = SentenceTransformer('JoBeer/model5')
+model_eng = SentenceTransformer('mboth/distil-eng-quora-sentence')
+model_fr = SentenceTransformer('Sahajtomar/french_semantic')
+
+#Definition of search function
+def predict(name, description, language, classCode='nofilter', top_k=10):
+  #language detection
+  if language == 'german':
+    model = model_ger
+    corpus = corpus_ger
+  if language == 'english':
+    model = model_eng
+    corpus = corpus_eng
+  if language == 'french':
+    model = model_fr
+    corpus = corpus_fr
+
+  text = name + '; ' + description #Verkettung name und description
+  query_embedding = model.encode(text, convert_to_tensor=True) #Erzeugung Query Embedding
+
+  #Filterung ECLASS Corpus
+  if classCode == 'nofilter':
+    corpus_filtered = corpus
+
+  else:
+    url = f'https://bcon2-api.azurewebsites.net/api/eclass?codedname={classCode}'
+    response = requests.get(url) #http request um auf Filter API zuzugreifen
+    lines = response.text.split('\n')
+    properties_filtered_list = [line[-21:-1] for line in lines]
+    corpus_filtered = corpus[corpus['irdi'].isin(properties_filtered_list)] #Der ECLASS Corpus wird mit Hilfe der Liste gefiltert
+    corpus_filtered.reset_index(drop=True,inplace=True) #Index wird zurückgesetzt
+
+  #Umwandlung corpus Embeddings in Tensor
+  corpus_embeddings = torch.Tensor(corpus_filtered["Embeddings"])
+
+  #Einspeisung Modell
+  output = sentence_transformers.util.semantic_search(query_embedding, corpus_embeddings, top_k = top_k)
+
+  #Auslesen der Modellausgabe
+  preferedNames = []
+  definitions = []
+  irdis = []
+  scores = []
+  for i in range(0,top_k):
+    preferedNames.append(corpus_filtered.iloc[output[0][i].get('corpus_id'),1])
+    definitions.append(corpus_filtered.iloc[output[0][i].get('corpus_id'),2])
+    irdis.append(corpus_filtered.iloc[output[0][i].get('corpus_id'),0])
+    scores.append(output[0][i].get('score'))
+
+  predictions = pd.DataFrame({'preferedName' : preferedNames, 'definition' : definitions, 'irdi' : irdis,'score' : scores,})
+  return predictions
+
+#gradio user interface
+with gr.Blocks() as demo:
+  with gr.Row():
+    gr.Markdown("""# ECLASS-Search-Demo
+      This is a semantic search application that maps unknown product properties to the ECLASS standard. It is created by ECLASS e.V. in collaboration with the GART-labortory of the cologne university of applied science.""") #This demo provides a semantic search application for ECLASS features.
+
+  with gr.Row():
+    #inputs
+    name_tx = gr.Textbox(label="Name:",placeholder="Name of the Property", lines=1)
+    description_tx = gr.Textbox(label="Description:", placeholder="Description of the Property", lines=1)
+
+  with gr.Row():
+    #inputs
+    classcode_tx = gr.Textbox(value='nofilter', label="Filter with ECLASS ClassCode", placeholder="type nofilter", lines=1)
+    top_k_nu = gr.Number(value=10, label="Number of Matches")
+    language_drop = gr.Dropdown(["german", "english","french"], value='german', label="Select language")
+
+  #button
+  search = gr.Button("search")
+
+  #output
+  prediction_df = gr.Dataframe(headers = ['preferedName', 'definition', 'irdi', 'score']) #value = predictions,
+
+  #Hinterlegt Search-Function für button "search"
+  search.click(fn=predict, inputs=[name_tx,description_tx,language_drop,classcode_tx,top_k_nu], outputs=prediction_df)
+
+demo.launch(debug=True)