Update app.py

app.py

@@ -4,10 +4,16 @@ from datasets import load_dataset
 dataset = load_dataset("Namitg02/Test")
 print(dataset)
 
+from langchain.docstore.document import Document as LangchainDocument
+
+RAW_KNOWLEDGE_BASE = [
+    LangchainDocument(page_content=doc["dataset"], metadata={"one": doc["two"]})
+]
+
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15,separators=["\n\n", "\n", " ", ""])
-#docs = splitter.split_documents(dataset)
-docs = splitter.split_text(str(dataset))
+docs = splitter.split_documents(RAW_KNOWLEDGE_BASE)
+#docs = splitter.split_text(str(dataset))
 
 
 from langchain_community.embeddings import HuggingFaceEmbeddings
@@ -17,6 +23,7 @@ embedding_model = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
 
 from langchain_community.vectorstores import Chroma
 persist_directory = 'docs/chroma/'
+
 vectordb = Chroma.from_documents(
     documents=[docs],
     embedding=embedding_model,