Update app.py

app.py

@@ -56,17 +56,16 @@ def generate(title, abstract):
     This is for summarization
     '''
     tooShortForKeyword = False
-    with open("data/sample-data.jsonl", "r") as f:
-        obj = [json.loads(l) for l in f]
-        doc = ""
-        if len(obj[0]["target"]) > 1:
-            doc += obj[0]["title"] + ". " + obj[0]["target"][0] + " "  + obj[0]["target"][1]
-        elif len(obj[0]["target"]) == 1:
-            tooShortForKeyword = True
-            doc += obj[0]["title"] + ". " + obj[0]["target"][0]
-        else:
-            tooShortForKeyword = True
-            doc += obj[0]["title"]
+ obj = newline
+    doc = ""
+    if len(obj["target"]) > 1:
+        doc += obj["title"] + ". " + obj["target"][0] + " "  + obj["target"][1]
+    elif len(obj["target"]) == 1:
+        tooShortForKeyword = True
+        doc += obj["title"] + ". " + obj["target"][0]
+    else:
+        tooShortForKeyword = True
+        doc += obj["title"]
     text = doc
     prompt = """
     Can you explain the main idea of what is being studied in the following paragraph for someone who is not familiar with the topic. Comment on areas of application.:
@@ -85,8 +84,6 @@ def generate(title, abstract):
         index_response += 10
     end_response = output.rfind('.') + 1
     response = output[index_response:end_response]
-    with open("data/guanacoSummaryOutput.txt", "w") as f2:
-        f2.write(response)
     print('Plain Language Summary Created.')
 
     '''
@@ -94,26 +91,25 @@ def generate(title, abstract):
     '''
     # the document is the title and first two sentences of the abstract. 
 
-    with open("data/sample-data.jsonl", "r") as f:
-        obj = [json.loads(l) for l in f]
-        doc = ""
-        if len(obj[0]["target"]) > 1:
-            doc += obj[0]["title"] + ". " + obj[0]["target"][0] + " "  + obj[0]["target"][1]
-            kw_model = KeyBERT(model="all-MiniLM-L6-v2")
-            vectorizer = KeyphraseCountVectorizer()
-            top_n = 2
-            keywords = kw_model.extract_keywords(doc, stop_words="english", top_n = top_n, vectorizer=vectorizer, use_mmr=True)
-            my_keywords = []
-            for i in range(top_n):
-                add = True
-                for j in range(top_n):
-                    if i != j:
-                        if keywords[i][0] in keywords[j][0]:
-                            add = False
-                if add:
-                    my_keywords.append(keywords[i][0])
-            for entry in my_keywords:
-                print(entry)
+   obj = newline
+    doc = ""
+    if len(obj["target"]) > 1:
+        doc += obj["title"] + ". " + obj["target"][0] + " "  + obj["target"][1]
+        kw_model = KeyBERT(model="all-MiniLM-L6-v2")
+        vectorizer = KeyphraseCountVectorizer()
+        top_n = 2
+        keywords = kw_model.extract_keywords(doc, stop_words="english", top_n = top_n, vectorizer=vectorizer, use_mmr=True)
+        my_keywords = []
+        for i in range(top_n):
+            add = True
+            for j in range(top_n):
+                if i != j:
+                    if keywords[i][0] in keywords[j][0]:
+                        add = False
+            if add:
+                my_keywords.append(keywords[i][0])
+        for entry in my_keywords:
+            print(entry)
     '''
     This is for feeding the keyphrases into Guanaco.
     '''
@@ -136,8 +132,6 @@ def generate(title, abstract):
         index_response = output.find("### Assistant: ") + 15
         end_response = output.rfind('.') + 1
         responseTwo = output[index_response:end_response]
-        with open("data/guanacoElaborationOutput.txt", "w") as f2:
-            f2.write(responseTwo)
     print('Keyphrase elaboration ran.')
     return keyword_string, responseTwo, response