refactor infos

app.py

@@ -5,7 +5,6 @@ st.set_page_config(
     page_title="Hello",
     page_icon="👋",
 )
-st.info(f"Speicherauslastung vor imports: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
 
 st.write("# Willkommen zum Event-Daten-Extraktions-Tool! 👋")
 st.write("""

pages/5_Playground.py

@@ -1,13 +1,6 @@
-
 import logging
-import os
-import sys
-import gc
-import psutil
 import streamlit as st
 import pandas as pd
-st.info(f"Speicherauslastung vor imports: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
-
 
 from src.configuration.config import SessionStateConfig
 from src.nlp.playground.textsummarization import SumySummarizer
@@ -76,9 +69,6 @@ def clear_st_cache():
 db = init_connection()
 data = init_data()
 
-st.info(f"Speicherauslastung: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
-
-
 with st.expander("Large Language Models"):
     with st.form("Settings LLM"):
         count = st.number_input("Wie viele Veranstaltungen sollen gestest werden?", step=1)
@@ -165,7 +155,6 @@ with st.expander("Titel Extraktion"):
     if submit_title_extr:
         init_session_state("title_extractor", TitleExtractor())
         title_extractor = st.session_state.title_extractor
-        st.info(f"Speicherauslastung: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
 
         for event in data:
             text = normalize_data(event["data"])
@@ -191,7 +180,6 @@ with st.expander("Textsummarization"):
     if submit_textsummarization:
         init_session_state(SessionStateConfig.SUMY_SUMMARIZER, SumySummarizer())
         sumy_summarizer = st.session_state[SessionStateConfig.SUMY_SUMMARIZER]
-        st.info(f"Speicherauslastung: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
         for event in data:
             try:
                 md = normalize_data(event["data"])

src/nlp/playground/llm.py

@@ -15,7 +15,6 @@ class QwenLlmHandler:
             token=os.getenv("INFERENCE_API_TOKEN"),
         )
         st.info("Using LLM Qwen/Qwen2.5-Coder-32B-Instruct via inference API")
-        st.info(f"Speicherauslastung: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
 
 
 

src/nlp/playground/ner.py

@@ -9,8 +9,7 @@ LABELS = ["eventTitle", "eventLocation", "date", "time", "street", "city"]
 class GlinerHandler:
     def __init__(self, model_name="urchade/gliner_multi-v2.1"):
         self.model = GLiNER.from_pretrained(model_name)
-        st.info("Loaded Model Gliner")
-        st.info(f"Speicherauslastung vor imports: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
+        st.info("Using NER Model Gliner")
 
     def extract_entities(self, text, labels=None, threshold=0.3):
         if labels is None:

src/nlp/playground/pipelines/description_extractor.py

@@ -17,7 +17,6 @@ class DescriptionExtractor:
         if SessionStateConfig.SUMY_SUMMARIZER not in st.session_state:
             st.session_state[SessionStateConfig.SUMY_SUMMARIZER] = SumySummarizer()
         sumy_summary = st.session_state[SessionStateConfig.SUMY_SUMMARIZER].summarize(text)
-        st.info("Loaded Sumy Summarizer Model")
         st.info(f"{psutil.virtual_memory()}")
         description = []
         for element in md_analyzer:

src/nlp/playground/textclassification.py

@@ -138,9 +138,7 @@ class ZeroShotClassifier:
         self.classifier = pipeline(
             task="zero-shot-classification",
             model="Sahajtomar/German_Zeroshot")
-        st.info("Loaded Model Sahajtomar/German_Zeroshot")
-        st.info(
-            f"Speicherauslastung vor imports: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
+        st.info("Using ZeroShotClassification with Model Sahajtomar/German_Zeroshot")
 
     def classify(self, text, mode: ClassifierMode):
         predictions = self.classifier(text, mode.labels, hypothesis_template=mode.hypothesis_template)

src/nlp/playground/textsummarization.py

@@ -26,9 +26,7 @@ class SumySummarizer:
         stemmer = Stemmer(self.LANGUAGE)
 
         summarizer = Summarizer(stemmer)
-        st.info("Loaded Model Sumy Summarizer")
-        st.info(
-            f"Speicherauslastung vor imports: {psutil.virtual_memory().percent}%. Keys in Cache: {[k for k in st.session_state]}")
+        st.info("Using Textsummarization Model Sumy Summarizer")
         summarizer.stop_words = get_stop_words(self.LANGUAGE)
 
         summary = summarizer(parser.document, self.SENTENCES_COUNT)