fix: change requirements

app.py

@@ -1,19 +1,18 @@
 import streamlit as st
 from sentence_transformers import SentenceTransformer
 import datasets
-
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+import faiss
+import torch
 
 st.sidebar.text_input("Type your quote here")
 
 dataset = datasets.load_dataset('A-Roucher/english_historical_quotes', download_mode="force_redownload")
 
-dataset = dataset['train']
+dataset = datasets.Dataset.from_dict(dataset['train'][:100])
 
 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=4,
@@ -22,8 +21,8 @@ embeddings = encoder.encode(
     normalize_embeddings=True,
 )
 
-dataset_embeddings = datasets.Dataset.from_dict({"embeddings": embeddings})
-dataset_embeddings.add_faiss_index(column="embeddings")
+# 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')
 
@@ -36,17 +35,17 @@ sentence_embedding = encoder.encode([sentence])
 # scores, samples = dataset_embeddings.search(
 #     sentence_embedding, k=10
 # )
-
+sentence_embedding_tensor = torch.Tensor(sentence_embedding)
+dataset_embeddings_tensor = torch.Tensor(embeddings)
 from sentence_transformers.util import semantic_search
 
-# hits = semantic_search(sentence_embedding, dataset_embeddings[:, :], top_k=5)
-author_indexes = list(range(1000))
-hits = semantic_search(sentence_embedding, dataset_embeddings[author_indexes, :], top_k=5)
-st.write(hits)
-list_hits = [author_indexes[i['corpus_id']] for i in hits[0]]
-st.write(dataset_embeddings.select([12676, 4967, 2612, 8884, 4797]))
-
+author_indexes = list(range(10))
+hits = semantic_search(sentence_embedding_tensor, dataset_embeddings_tensor[author_indexes, :], top_k=5)
 
+list_hits = [author_indexes[i['corpus_id']] for i in hits[0]]
+print(list_hits)
+print(dataset)
+st.write(dataset.select(list_hits))
 
 # sentence_embedding = model.encode([sentence])
 # scores, sample_indexes = QUOTES_INDEX.search(

requirements.txt

@@ -1,3 +1,4 @@
-datasets==2.5.2
+datasets==2.14.6
+faiss-cpu==1.7.3
 sentence_transformers==2.2.2
 streamlit==1.28.1