Update app.py

app.py

@@ -4,18 +4,20 @@ print(dataset)
 
 from langchain.docstore.document import Document as LangchainDocument
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-#splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15,separators=["\n\n", "\n", " ", ""])
-#docs = splitter.create_documents(str(dataset))
+splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15,separators=["\n\n", "\n", " ", ""])
+docs = splitter.create_documents(str(dataset))
 
 from sentence_transformers import SentenceTransformer
-#from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
-data = dataset["train"]
+data = FAISS.from_documents(docs, embedding_model)
+
+#data = dataset["train"]
 data = data.add_faiss_index("embeddings") # column name that has the embeddings of the dataset
 
 
 from langchain_community.vectorstores import Chroma
-persist_directory = 'docs/chroma/'
+#persist_directory = 'docs/chroma/'
 
 #vectordb = Chroma.from_documents(
  #   documents=docs,