Update app.py

app.py

@@ -21,7 +21,7 @@ def load_summarizer():
 
 @st.cache_resource(show_spinner=False)
 def load_text_generator():
-    # For demonstration, we load a text-generation model such as GPT-2
+    # For demonstration, we load a text-generation model such as GPT-2.
     generator = pipeline("text-generation", model="gpt2")
     return generator
 
@@ -40,7 +40,7 @@ def generate_ideas_with_hf(prompt):
 def generate_ideas_with_openai(prompt, api_key):
     """
     Generates research ideas using OpenAI's GPT‑3.5 model with streaming.
-    This function uses the latest OpenAI SDK v1.0 which supports asynchronous API calls.
+    This function uses the latest OpenAI SDK v1.0 and asynchronous API calls.
     """
     openai.api_key = api_key
     output_text = ""
@@ -139,13 +139,13 @@ paper_abstract = st.text_area("Enter the research paper abstract:", height=200)
 if st.button("Generate Ideas"):
     if paper_abstract.strip():
         st.subheader("Summarized Abstract")
-        # Use the Hugging Face summarizer to capture key points
+        # Summarize the abstract to capture its key points
         summary = summarizer(paper_abstract, max_length=100, min_length=30, do_sample=False)
         summary_text = summary[0]['summary_text']
         st.write(summary_text)
         
         st.subheader("Generated Research Ideas")
-        # Build a combined prompt based on the abstract and its summary
+        # Build a combined prompt with the abstract and its summary
         prompt = (
             f"Based on the following research paper abstract, generate innovative and promising research ideas for future work.\n\n"
             f"Paper Abstract:\n{paper_abstract}\n\n"
@@ -169,8 +169,9 @@ if st.button("Generate Ideas"):
 # --- Section 3: Knowledge Graph Visualization ---
 st.header("Knowledge Graph Visualization")
 st.markdown(
-    "Simulate a knowledge graph by entering paper details and their citation relationships in CSV format: **PaperID,Title,CitedPaperIDs** (CitedPaperIDs separated by ';').\n\n"
-    "Example:\n\n`1,Paper A,2;3`\n`2,Paper B,`\n`3,Paper C,2`"
+    "Simulate a knowledge graph by entering paper details and their citation relationships in CSV format:\n\n"
+    "**PaperID,Title,CitedPaperIDs** (CitedPaperIDs separated by ';').\n\n"
+    "Example:\n\n```\n1,Paper A,2;3\n2,Paper B,\n3,Paper C,2\n```"
 )
 papers_csv = st.text_area("Enter paper details in CSV format:", height=150)
 
@@ -189,15 +190,17 @@ if st.button("Generate Knowledge Graph"):
             # Build a directed graph using NetworkX
             G = nx.DiGraph()
             for paper in data:
-                G.add_node(paper["paper_id"], title=paper["title"])
+                # Ensure each node has a 'title' key, even if it's an empty string.
+                G.add_node(paper["paper_id"], title=paper.get("title", ""))
                 for cited in paper["cited"]:
                     G.add_edge(paper["paper_id"], cited)
             
             st.subheader("Knowledge Graph")
             # Create an interactive visualization using Pyvis
             net = Network(height="500px", width="100%", directed=True)
+            # Use get() to avoid KeyError and provide a fallback label.
             for node, node_data in G.nodes(data=True):
-                net.add_node(node, label=node_data["title"])
+                net.add_node(node, label=node_data.get("title", str(node)))
             for source, target in G.edges():
                 net.add_edge(source, target)
             # Save the interactive visualization to an HTML file and embed it in Streamlit