update app.py

app.py

@@ -2,37 +2,41 @@ import json
 
 import gradio as gr
 import pandas as pd
-from pyserini.search.lucene import LuceneSearcher
 
-searcher = LuceneSearcher("indexes/docs")
-searcher.set_language("ja")
 
+def read_json(file_name):
+    with open(file_name, "r") as f:
+        json_data = json.load(f)
+    return json_data
 
-def show_search_results(query):
-    search_results = searcher.search(query, k=100)
 
-    data = {"project_name": [], "description": []}
-    for result in search_results:
-        docid = result.docid
-        doc = searcher.doc(docid)
-        data_json = json.loads(doc.raw())
+json_file = "awesome-japanese-nlp-resources-search.json"
+json_data = read_json(json_file)
+data = {"project_name": [], "source": [], "description": []}
+
+for data_json in json_data:
+    url = data_json["url"]
+    description = data_json["description"]
+    project_name = data_json["project_name"]
+    source = data_json["source"]
+    data["project_name"].append(f"[{project_name}]({url})")
+    data["source"].append(source)
+    data["description"].append(description)
 
-        url = data_json["url"]
-        description = data_json["description"]
-        project_name = data_json["project_name"]
+data = pd.DataFrame(data)
 
-        data["project_name"].append(f"[{project_name}]({url})")
-        data["description"].append(description)
 
-    data = pd.DataFrame(data)
-    return data
+def show_search_results(query):
+    contained = data["description"].str.contains(query)
+    df_search = data[contained]
+    return df_search
 
 
 with gr.Blocks() as demo:
     gr.Markdown(
         """
     # Awesome Japanese NLP resources search 🔎
-    You can search for open-source software from [500+ Japanese NLP repositories](https://github.com/taishi-i/awesome-japanese-nlp-resources).
+    You can search for open-source software from [1000+ Japanese NLP repositories](https://github.com/taishi-i/awesome-japanese-nlp-resources).
     """
     )
 

packages.txt

@@ -1 +0,0 @@
-default-jdk

requirements.txt

@@ -1,4 +1 @@
-pyserini
-faiss-cpu
-torch
-altair<5
+pandas