Update app.py

app.py

@@ -9,6 +9,7 @@ from langchain.llms import HuggingFacePipeline
 from langchain.document_loaders.csv_loader import CSVLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings.spacy_embeddings import SpacyEmbeddings
 from langchain.chains import RetrievalQA
 from langchain.vectorstores import Chroma
 import gradio as gr
@@ -42,6 +43,20 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 ##############################################################################
 
+embedding = SpacyEmbeddings(model_name="en_core_web_sm")
+
+# Embed and store the texts
+# Supplying a persist_directory will store the embeddings on disk
+persist_directory = 'Enron_case_RAG/Langchain_ChromaDB'
+
+# load from disk
+db3 = Chroma(persist_directory=persist_directory,
+             embedding_function=embedding,
+             collection_name="Enron_vectorstore"
+             )
+
+##############################################################################
+
 query_pipeline = transformers.pipeline(
     "text-generation",
     model=model,