Update app.py

app.py

@@ -16,8 +16,9 @@ def load_files(path):
         
 charities_text = load_files("charities.txt")
 financial_advice_text = load_files("financial_advice.txt")
-
-
+un_text = load_files("un.txt")
+investopedia_text = load_files("investopedia.txt")
+cgf_text = load_files("cgf.txt")
 # 
 
 ### 
@@ -47,6 +48,9 @@ def preprocess_text(text):
 
 cleaned_charities = preprocess_text(charities_text)
 cleaned_finance = preprocess_text(financial_advice_text)
+cleaned_un = preprocess_text(un_text)
+cleaned_investopedia = preprocess_text(investopedia_text)
+cleaned_cgf = preprocess_text(cgf_text)
 
 # Load the pre-trained embedding model that converts text to vectors
 model = SentenceTransformer('all-MiniLM-L6-v2')
@@ -67,6 +71,9 @@ def create_embeddings(text_chunks):
 
 charity_embeddings = create_embeddings(cleaned_charities)
 finance_embeddings = create_embeddings(cleaned_finance)
+un_embeddings = create_embeddings(cleaned_un)
+investopedia_embeddings = create_embeddings(cleaned_investopedia)
+cgf_embeddings = create_embeddings(cleaned_cgf)
 
 ###STEP 5
 # Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks