👜 baseline

README.md

@@ -1,37 +1,13 @@
 ---
-title: X Language Search Ancient With Modern Words
-emoji: 🐠
-colorFrom: purple
+title: Cross language search
+emoji: ⚔️
+colorFrom: indigo
 colorTo: purple
 sdk: streamlit
 app_file: app.py
 pinned: false
 ---
+# Cross Language Search
+> Search ancient books with modern words
 
-# Configuration
 
-`title`: _string_
-Display title for the Space
-
-`emoji`: _string_
-Space emoji (emoji-only character allowed)
-
-`colorFrom`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`colorTo`: _string_
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
-
-`sdk`: _string_
-Can be either `gradio`, `streamlit`, or `static`
-
-`sdk_version` : _string_
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
-
-`app_file`: _string_
-Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
-Path is relative to the root of the repository.
-
-`pinned`: _boolean_
-Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,45 @@
+import streamlit as st
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from forgebox.cosine import CosineSearch
+import numpy as np
+
+TAG = "raynardj/xlsearch-cross-lang-search-zh-vs-classicical-cn"
+
+@st.cache(allow_output_mutation=True)
+def load_encoder():
+    with st.spinner(f"Loading Transformer:{TAG}"):
+        encoder = SentenceTransformer(TAG)
+    return encoder
+
+encoder = load_encoder()
+
+@st.cache(allow_output_mutation=True)
+def load_book():
+    with st.spinner(f"📚 Loading Book..."):
+        df = pd.read_csv("grand_historian.csv")
+    return list(df.sentence)
+
+all_lines = load_book()
+
+@st.cache(allow_output_mutation=True)
+def encode_book():
+    with st.spinner(f"Encoding sentences for book《Records of the Grand Historian》"):
+        vec = encoder.encode(all_lines, batch_size=64, show_progress_bar=True)
+        cosine = CosineSearch(vec)
+    return cosine
+
+cosine = encode_book()
+
+def search(text):
+    enc = encoder.encode(text) # encode the search key
+    order = cosine(enc) # distance array
+    sentence_df = pd.DataFrame({"sentence":np.array(all_lines)[order[:5]]})
+    return sentence_df
+
+keyword = st.text_input("用白话搜", "")
+if st.button("搜索"):
+    if keyword:
+        with st.spinner(f"🔍 Searching for {keyword}"):
+            df = search(keyword)
+            st.table(df)

requirements.txt

@@ -0,0 +1,5 @@
+torch==1.7.1
+sentence-transformers==2.1.0
+transformers==4.12.3
+pandas==1.3.5
+forgebox==0.4.20