Update src/utils/ingest_text.py

src/utils/ingest_text.py

@@ -8,6 +8,9 @@ from langchain_community.document_loaders.directory import DirectoryLoader
 import os
 from fastembed import TextEmbedding
 from typing import List
+import nltk
+nltk.download('punkt')
+
 
 import nest_asyncio
 nest_asyncio.apply()
@@ -18,8 +21,8 @@ llamaparse_api_key = os.getenv("LLAMA_CLOUD_API_KEY")
 groq_api_key = os.getenv("GROQ_API_KEY")
 
 
-parsed_data_file = r".\data\parsed_data.pkl"
-output_md = r".\data\output.md"
+parsed_data_file = r"data/parsed_data.pkl"
+output_md = r"data/output.md"
 loki = r"data"
 
 import pickle
@@ -61,6 +64,7 @@ def create_vector_database(loc):
 
     """
     # Call the function to either load or parse the data
+    print("text_db")
     llama_parse_documents = load_or_parse_data(loc)
     #print(llama_parse_documents[1].text[:100])