render Graph from adjacency matrix

use G from cosine similarity to populate network

app.py

@@ -21,11 +21,17 @@ embeddings = model.encode(sentences, convert_to_tensor=True)
 #Compute cosine-similarities
 cosine_scores = util.cos_sim(embeddings, embeddings)
 
+# creating adjacency matrix
+A = np.zeroes((len(sentences),len(sentences)))
+
 #Output the pairs with their score
 for i in range(len(sentences)):
     for j in range(i):
         st.write("{} \t\t {} \t\t Score: {:.4f}".format(sentences[i], sentences[j], cosine_scores[i][j]))
+        M[i][j] = cosine_scores[i][j]
+        M[j][i] = cosine_scores[i][j]
 
+#G = nx.from_numpy_array(A)
 G = nx.from_numpy_array(cosine_scores.numpy())
 
 
@@ -56,7 +62,7 @@ from streamlit_agraph import agraph, Node, Edge, Config
 # First create a graph using the Barabasi-Albert model
 n = 2000
 m = 2
-G = nx.generators.barabasi_albert_graph(n, m, seed=2023)
+#G = nx.generators.barabasi_albert_graph(n, m, seed=2023)
 
 # Then find the node with the largest degree; 
 # This node's egonet will be the focus of this example.