Update app.py

app.py

@@ -5,6 +5,7 @@ from sentence_transformers import SentenceTransformer
 from langchain_community.embeddings import HuggingFaceEmbeddings
 import faiss
 from langchain.prompts import PromptTemplate
+import pandas as pd
 
 import time
 import torch
@@ -24,6 +25,15 @@ dataset = load_dataset("Namitg02/Test", split='train', streaming=False)
 #Returns a list of dictionaries, each representing a row in the dataset.
 print(dataset[1])
 length = len(dataset)
+df = pd.DataFrame(dataset)
+
+embeddings = embedding_model.encode(dataset["text"])
+print(embeddings)
+
+df['embeddings'] = embeddings
+dataset = Dataset.from_pandas(df)
+print(dataset[1])
+
 
 #Itemdetails = dataset.items()
 #print(Itemdetails)
@@ -35,12 +45,12 @@ embedding_model = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
 #doc_func = lambda x: x.text
 #dataset = list(map(doc_func, dataset))
 
-def embedder(dataset):
-    embeddings = embedding_model.encode(dataset["text"])
-    dataset = dataset.add_column('embeddings', embeddings)
-    return dataset
-updated_dataset = dataset.map(embedder)
-dataset['text'][:length]
+#def embedder(dataset):
+#    embeddings = embedding_model.encode(dataset["text"])
+#    dataset = dataset.add_column('embeddings', embeddings)
+#    return dataset
+#updated_dataset = dataset.map(embedder)
+#dataset['text'][:length]
 
 #print(embeddings)