Update app.py

app.py

@@ -16,8 +16,9 @@ from transformers import TextIteratorStreamer
 from threading import Thread
 
 
-dataset = load_dataset("Namitg02/Test", split='train', streaming=False)
-print(dataset)
+#dataset = load_dataset("Namitg02/Test", split='train', streaming=False)
+dataset = load_dataset("not-lain/wikipedia",revision = "embedded")
+
 # Returns a list of dictionaries, each representing a row in the dataset.
 print(dataset[1])
 #splitter = RecursiveCharacterTextSplitter(chunk_size=150, chunk_overlap=25,separators=["\n\n"]) # ["\n\n", "\n", " ", ""])
@@ -35,14 +36,16 @@ embedding_model = HuggingFaceEmbeddings(model_name = "all-MiniLM-L6-v2")
 
 # Returns a FAISS wrapper vector store. Input is a list of strings. from_documents method used documents to Return VectorStore
 
-data = dataset["text"]
+#data = dataset["text"]
+data = dataset["train"]
+
 print(data)
 data = data.add_faiss_index("embeddings") 
 # adds a column that has a index of embeddings
 
 
 print("check1")
-question = "How can I reverse Diabetes?"
+#question = "How can I reverse Diabetes?"
 
 SYS_PROMPT = """You are an assistant for answering questions.
 You are given the extracted parts of a long document and a question. Provide a conversational answer.