Create abc

abc

@@ -0,0 +1,32 @@
+from sentence_transformers import SentenceTransformer, util
+print("import done")
+# Input chunks
+retrieved_chunks = [
+    "The Eiffel Tower is a landmark in Paris.",
+    "Paris is the capital of France.",
+    "The Louvre is also in Paris.",
+    "Eiffel Tower was built in 1889.",
+    "It is a famous tourist spot."
+]
+
+relevant_chunks = [
+    "The Eiffel Tower is a landmark in Paris.",
+    "Eiffel Tower was built in 1889."
+]
+
+# Load sentence transformer model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Compute embeddings
+retrieved_embeddings = model.encode(retrieved_chunks, convert_to_tensor=True)
+relevant_embeddings = model.encode(relevant_chunks, convert_to_tensor=True)
+
+# Calculate pairwise cosine similarities
+cosine_sim_matrix = util.cos_sim(retrieved_embeddings, relevant_embeddings)
+
+# Print similarity matrix
+print("Cosine Similarity Matrix (rows: retrieved, columns: relevant):\n")
+for i, retrieved in enumerate(retrieved_chunks):
+    for j, relevant in enumerate(relevant_chunks):
+        score = cosine_sim_matrix[i][j].item()
+        print(f"Similarity between:\n  Retrieved: \"{retrieved}\"\n  Relevant : \"{relevant}\"\n  Score    : {score:.4f}\n")