diff --git a/src/dataset.py b/src/dataset.py
index dc26257..741e28d 100644
--- a/src/dataset.py
+++ b/src/dataset.py
@@ -17,10 +17,12 @@ from tenacity import (
 
 from text_splitter import TokenSplitter, split_into_sentences
 from settings import PATH_TO_DATA, PATH_TO_EMBEDDINGS, PATH_TO_DATASET, EMBEDDING_MODEL, LEN_EMBEDDINGS
+import os
+from tqdm.auto import tqdm
 
-import openai
 openai.api_key = os.environ.get('OPENAI_API_KEY')
 
+
 error_count_dict = {
     "Entry has no source.": 0,
     "Entry has no title.": 0,
@@ -131,7 +133,7 @@ class Dataset:
     def get_alignment_texts(self):
         text_splitter = TokenSplitter(self.min_tokens_per_block, self.max_tokens_per_block)
         with jsonlines.open(self.jsonl_data_path, "r") as reader:
-            for entry in reader:
+            for entry in tqdm(reader):
                 try:
                     if 'source' not in entry: 
                         if 'url' in entry and entry['url'] == "https://www.cold-takes.com/": 
@@ -238,8 +240,6 @@ class Dataset:
                             pass
                 """
 
-            
-
     def save_embeddings(self, path: str):
         np.save(path, self.embeddings)
         
@@ -280,22 +280,22 @@ if __name__ == "__main__":
 
     # List of sources we are using for the test run:
     custom_sources = [
-        "https://aipulse.org", 
-        "ebook", 
+        # "https://aipulse.org", 
+        # "ebook", 
         # "https://qualiacomputing.com", 
         # "alignment forum", 
         # "lesswrong", 
         "manual", 
         # "arxiv", 
-        "https://deepmindsafetyresearch.medium.com", 
+        # "https://deepmindsafetyresearch.medium.com", 
         "waitbutwhy.com", 
         "GitHub", 
         # "https://aiimpacts.org", 
         # "arbital.com", 
-        "carado.moe", 
+        # "carado.moe", 
         # "nonarxiv_papers", 
-        "https://vkrakovna.wordpress.com", 
-        "https://jsteinhardt.wordpress.com", 
+        # "https://vkrakovna.wordpress.com", 
+        # "https://jsteinhardt.wordpress.com", 
         "audio-transcripts", 
         # "https://intelligence.org", 
         # "youtube", 
diff --git a/src/settings.py b/src/settings.py
index e80339d..571faff 100644
--- a/src/settings.py
+++ b/src/settings.py
@@ -6,7 +6,7 @@ COMPLETIONS_MODEL = "text-davinci-003"
 LEN_EMBEDDINGS = 1536
 MAX_LEN_PROMPT = 4095 # This may be 8191, unsure.
 
-project_path = Path(__file__).parent.parent.parent
+project_path = Path(__file__).parent.parent#.parent
 PATH_TO_DATA = project_path / "src" / "data" / "alignment_texts.jsonl" # Path to the dataset .jsonl file.
 PATH_TO_EMBEDDINGS = project_path / "src" / "data" / "embeddings.npy" # Path to the saved embeddings (.npy) file.
 PATH_TO_DATASET = project_path / "src" / "data" / "dataset.pkl" # Path to the saved dataset (.pkl) file, containing the dataset class object.
diff --git a/src/text_splitter.py b/src/text_splitter.py
index bcf0c7a..a00f674 100644
--- a/src/text_splitter.py
+++ b/src/text_splitter.py
@@ -8,7 +8,7 @@ import nltk
 
 
 # Download the Punkt tokenizer if you haven't already
-# nltk.download("punkt")
+nltk.download("punkt")
 
 def split_into_sentences(text: str) -> List[str]:
     """
diff --git a/web/api/requirements.txt b/web/api/requirements.txt
new file mode 100644
index 0000000..9220901
--- /dev/null
+++ b/web/api/requirements.txt
@@ -0,0 +1,4 @@
+openai
+typing
+numpy
+tenacity
\ No newline at end of file