push

app.py

@@ -20,11 +20,11 @@ import numpy as np
 from sklearn.manifold import TSNE
 import plotly.graph_objects as go
 
-from langchain.document_loaders import DirectoryLoader, TextLoader
+from langchain_community.document_loaders import TextLoader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.schema import Document
 import chromadb.utils.embedding_functions as embedding_functions
-from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 
 hf_token = os.getenv('HF_TOKEN')
 huggingface_ef = embedding_functions.HuggingFaceEmbeddingFunction(
@@ -52,7 +52,7 @@ search_splitter = CharacterTextSplitter(chunk_size=20, chunk_overlap=2)
 parts = search_splitter.split_text(search_requirements_text)
 
 
-search_documents = [Document(page_content=chunk) for chunk in chunks]
+search_documents = [Document(page_content=chunk) for chunk in parts]
 
 # Initialize Chroma with documents and embeddings
 search_vectorstore = Chroma.from_documents(