debug

.gitignore

@@ -1,4 +1,5 @@
 venv
 test.py
 .config.json
-__pycache__
+__pycache__
+.idea

lrt/lrt.py

@@ -3,6 +3,9 @@ from typing import List
 import textdistance as td
 from .utils import UnionFind, ArticleList
 from .academic_query import AcademicQuery
+import streamlit as st
+from tokenizers import Tokenizer
+
 
 class LiteratureResearchTool:
     def __init__(self, cluster_config: Configuration = None):
@@ -45,7 +48,6 @@ class LiteratureResearchTool:
                  platforms: List[str] = ['IEEE', 'Arxiv', 'Paper with Code'],
                  best_k: int = 5,
                  loading_ctx_manager = None,
-                 decorator: callable = None
                  ):
 
 
@@ -68,27 +70,57 @@ class LiteratureResearchTool:
                              end_year: int,
                              best_k: int = 5
                              ) -> (ClusterList,ArticleList):
-        if platforn_name == 'IEEE':
-            articles = ArticleList.parse_ieee_articles(self.literature_search.ieee(query,start_year,end_year,num_papers)) # ArticleList
-            abstracts = articles.getAbstracts() # List[str]
+
+        @st.cache(hash_funcs={Tokenizer: Tokenizer.__hash__})
+        def ieee_process(
+                query: str,
+                num_papers: int,
+                start_year: int,
+                end_year: int,
+                best_k: int = 5
+        ):
+            articles = ArticleList.parse_ieee_articles(
+            self.literature_search.ieee(query, start_year, end_year, num_papers))  # ArticleList
+            abstracts = articles.getAbstracts()  # List[str]
             clusters = self.cluster_pipeline(abstracts, best_k=best_k)
             clusters = self.__postprocess_clusters__(clusters)
-            return clusters,articles
-        elif platforn_name == 'Arxiv':
+            return clusters, articles
+
+        @st.cache(hash_funcs={Tokenizer: Tokenizer.__hash__})
+        def arxiv_process(
+                query: str,
+                num_papers: int,
+                best_k: int = 5
+        ):
             articles = ArticleList.parse_arxiv_articles(
-                self.literature_search.arxiv(query, num_papers))  # ArticleList
+            self.literature_search.arxiv(query, num_papers))  # ArticleList
             abstracts = articles.getAbstracts()  # List[str]
-            clusters = self.cluster_pipeline(abstracts,best_k=best_k)
+            clusters = self.cluster_pipeline(abstracts, best_k=best_k)
             clusters = self.__postprocess_clusters__(clusters)
             return clusters, articles
-        elif platforn_name == 'Paper with Code':
+
+        @st.cache(hash_funcs={Tokenizer: Tokenizer.__hash__})
+        def pwc_process(
+                query: str,
+                num_papers: int,
+                best_k: int = 5
+        ):
             articles = ArticleList.parse_pwc_articles(
-                self.literature_search.paper_with_code(query, num_papers))  # ArticleList
+            self.literature_search.paper_with_code(query, num_papers))  # ArticleList
             abstracts = articles.getAbstracts()  # List[str]
-            clusters = self.cluster_pipeline(abstracts,best_k=best_k)
+            clusters = self.cluster_pipeline(abstracts, best_k=best_k)
             clusters = self.__postprocess_clusters__(clusters)
             return clusters, articles
 
+        if platforn_name == 'IEEE':
+            return ieee_process(query,num_papers,start_year,end_year,best_k)
+        elif platforn_name == 'Arxiv':
+            return arxiv_process(query,num_papers,best_k)
+        elif platforn_name == 'Paper with Code':
+            return pwc_process(query,num_papers,best_k)
+        else:
+            raise RuntimeError('This platform is not supported. Please open an issue on the GitHub.')
+
 
 
 

widgets/body.py

@@ -60,8 +60,9 @@ def render_body(platforms, num_papers, num_papers_preview, query_input, show_pre
 
 
         # lrt results
-        generator =  baseline_lrt(query_input,num_papers,start_year,end_year,platforms, best_k=k,loading_ctx_manager= st.spinner,
-                     decorator= st.cache)
+        generator =  baseline_lrt(query_input,num_papers,start_year,end_year,platforms, best_k=k,
+                                  # loading_ctx_manager= st.spinner,
+                                  )
         for plat in platforms:
             clusters, articles = next(generator)
             print(clusters)

widgets/sidebar.py

@@ -38,13 +38,13 @@ def render_sidebar():
         'IEEE',
         # 'Google Scholar',
         'Arxiv',
-        'PaperWithCode'
+        'Paper with Code'
     ], default=[
         # 'Elvsier',
         'IEEE',
         # 'Google Scholar',
         'Arxiv',
-        'PaperWithCode'
+        'Paper with Code'
     ])