bwconrad commited on
Commit
ff372e6
1 Parent(s): 30cb752

Add description

Browse files
Files changed (1) hide show
  1. app.py +13 -1
app.py CHANGED
@@ -36,10 +36,22 @@ def add_descriptions_to_results(results: pd.DataFrame):
36
 
37
  # Input UI
38
  st.title("Manga Semantic Search")
 
 
 
 
 
 
 
 
 
 
39
  query = st.text_input(
40
  "Enter a description of the manga you are searching for:",
41
  value="",
42
  )
 
 
43
  embeddings_path = st.selectbox("Embeddings Corpus", os.listdir("embeddings"))
44
  top_k = st.number_input(
45
  "Number of results", value=5, min_value=1, max_value=100, step=1
@@ -75,7 +87,7 @@ if st.button("Search"):
75
  "'Number of results' should be less than or equal to 'Number of number of initialy retrieved series'"
76
  )
77
  else:
78
- # Load embedddings and corresponding data table
79
  with open(embeddings_path, "rb") as f:
80
  data, corpus_embeddings = pickle.load(f).values()
81
 
 
36
 
37
  # Input UI
38
  st.title("Manga Semantic Search")
39
+ st.markdown(
40
+ """
41
+ An application to search for manga series using text descriptions of it's content. Find the name of a series based on a vague recollection about its story.
42
+ Performs a semantic retrieve and re-rank search using Sentence Transform models.
43
+ Source code for this application can be found in the repo [here](https://github.com/bwconrad/manga-semantic-search).
44
+
45
+ __Note__: The current database only includes the top-1000 manga series on AniList.
46
+ """
47
+ )
48
+
49
  query = st.text_input(
50
  "Enter a description of the manga you are searching for:",
51
  value="",
52
  )
53
+
54
+
55
  embeddings_path = st.selectbox("Embeddings Corpus", os.listdir("embeddings"))
56
  top_k = st.number_input(
57
  "Number of results", value=5, min_value=1, max_value=100, step=1
 
87
  "'Number of results' should be less than or equal to 'Number of number of initialy retrieved series'"
88
  )
89
  else:
90
+ # Load embeddings and corresponding data table
91
  with open(embeddings_path, "rb") as f:
92
  data, corpus_embeddings = pickle.load(f).values()
93