diff --git a/README.md b/README.md
index 21efe29..58d0db1 100644
--- a/README.md
+++ b/README.md
@@ -20,13 +20,12 @@ This repo uses a [state of the union transcript](https://github.com/imartinez/pr
 
 ## Instructions for ingesting your own dataset
 
-Place your .txt file in `source_documents` folder.
-Edit `ingest.py` loader to point it to your document.
+Get your .txt file ready.
 
 Run the following command to ingest the data.
 
 ```shell
-python ingest.py
+python ingest.py <path_to_your_txt_file>
 ```
 
 It will create a `db` folder containing the local vectorstore. Will take time, depending on the size of your document.
diff --git a/ingest.py b/ingest.py
index e5d27b3..72b35e4 100644
--- a/ingest.py
+++ b/ingest.py
@@ -1,13 +1,14 @@
 from langchain.document_loaders import TextLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import Chroma
 from langchain.embeddings import LlamaCppEmbeddings
+from sys import argv
 
 def main():
     # Load document and split in chunks
-    loader = TextLoader('./source_documents/state_of_the_union.txt', encoding='utf8')
+    loader = TextLoader(argv[1], encoding="utf8")
     documents = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     texts = text_splitter.split_documents(documents)
     # Create embeddings
     llama = LlamaCppEmbeddings(model_path="./models/ggml-model-q4_0.bin")