Add application file

README.md

@@ -1,8 +1,8 @@
 ---
 title: Quotes
-emoji: 🏢
-colorFrom: purple
-colorTo: purple
+emoji: 🪶
+colorFrom: green
+colorTo: blue
 sdk: streamlit
 sdk_version: 1.28.1
 app_file: app.py

app.py

@@ -0,0 +1,57 @@
+import streamlit as st
+from sentence_transformers import SentenceTransformer
+import datasets
+
+x = st.slider('Select a value')
+st.write(x, 'squared is', x * x)
+
+st.sidebar.text_input("Type your quote here")
+
+dataset = datasets.load_dataset('A-Roucher/english_historical_quotes')['train']
+
+model_name = "sentence-transformers/all-MiniLM-L6-v2" # BAAI/bge-small-en-v1.5" # "Cohere/Cohere-embed-english-light-v3.0" # "sentence-transformers/all-MiniLM-L6-v2"
+
+encoder = SentenceTransformer(model_name)
+embeddings = encoder.encode(
+    dataset["quote"],
+    batch_size=8,
+    show_progress_bar=True,
+    convert_to_numpy=True,
+    normalize_embeddings=True,
+)
+
+dataset_embeddings = datasets.Dataset.from_dict({"embeddings": embeddings})
+dataset_embeddings.add_faiss_index(column="embeddings")
+
+# dataset_embeddings.save_faiss_index('embeddings', 'output/index_alone.faiss')
+
+# import faiss
+
+# index = faiss.read_index('index_alone.faiss')
+
+sentence = "Knowledge of history is power."
+sentence_embedding = encoder.encode([sentence])
+# scores, samples = dataset_embeddings.search(
+#     sentence_embedding, k=10
+# )
+
+from sentence_transformers.util import semantic_search
+
+# hits = semantic_search(sentence_embedding, dataset_embeddings[:, :], top_k=5)
+author_indexes = range(1000)
+hits = semantic_search(sentence_embedding, dataset_embeddings[author_indexes, :], top_k=5)
+
+list_hits = [author_indexes[i['corpus_id']] for i in hits[0]]
+st.write(dataset_embeddings.select([12676, 4967, 2612, 8884, 4797]))
+
+
+
+# sentence_embedding = model.encode([sentence])
+# scores, sample_indexes = QUOTES_INDEX.search(
+#     sentence_embedding, k=k
+# )
+# quotes = QUOTES_DATASET.iloc[sample_indexes[0]]
+# author_descriptions_df = get_authors_descriptions(quotes['author'].unique())
+# quotes = quotes.merge(author_descriptions_df, on='author')
+# quotes["scores"] = scores[0]
+# quotes = quotes.sort_values("scores", ascending=True) # lower is better