EMERAC

app.py

@@ -47,7 +47,7 @@ def load_data(url):
     return df
 
 
-st.title('Sociology Paragraph Search')
+st.title('Sociology EMERAC')
 
 st.write('This project is a work-in-progress that searches the text of recently-published articles from a few sociology journals and retrieves the most relevant paragraphs.')
 
@@ -70,7 +70,7 @@ notes = f'''Notes:
 * The most relevant paragraph to your search is returned first, along with up to four other related paragraphs from that article.
 * The most relevant sentence within each paragraph, as determined by math, is displayed. Click on it to see the full paragraph.
 * The results are not exhaustive, and seem to drift off even when you suspect there are more relevant articles :man-shrugging:.
-* The dataset currently includes articles published in the last five years in *Mobilization*, *Social Forces*, *Social Problems*, *Sociology of Race and Ethnicity*, *Gender and Society*, *Socius*, *JHSB*, *Annual Review of Sociology*, and the *American Sociological Review*.
+* The dataset currently includes {no_of_graphs:,} paragraphs from {no_of_articles:,} published in the last five years in *Mobilization*, *Social Forces*, *Social Problems*, *Sociology of Race and Ethnicity*, *Gender and Society*, *Socius*, *JHSB*, *Annual Review of Sociology*, and the *American Sociological Review*.
 * Behind the scenes, the semantic search uses [text embeddings](https://www.sbert.net) with a [retrieve & re-rank](https://colab.research.google.com/github/UKPLab/sentence-transformers/blob/master/examples/applications/retrieve_rerank/retrieve_rerank_simple_wikipedia.ipynb) process to find the best matches.
 * Let [me](mailto:neal.caren@unc.edu) know what you think or it looks broken.
 '''
@@ -167,3 +167,4 @@ if search_query!='':
         bi_encoder = sent_trans_load()
         cross_encoder = sent_cross_load()
         search(search_query)
+        st.markdown('![EMERAC](emerac.png)')

requirements.txt

@@ -3,4 +3,3 @@ torch
 pandas
 nltk
 gdown
-streamlit