Adrian J W Thompson commited on
Commit
df74b57
·
1 Parent(s): 2ce377c

added new corpus

Browse files
cleaned_text-11-02-2023.txt ADDED
The diff for this file is too large to render. See raw diff
 
ingest_data.py CHANGED
@@ -5,7 +5,7 @@ from langchain.embeddings import OpenAIEmbeddings
5
  import pickle
6
 
7
  # Load Data
8
- loader = UnstructuredFileLoader("state_of_the_union.txt")
9
  raw_documents = loader.load()
10
 
11
  # Split text
 
5
  import pickle
6
 
7
  # Load Data
8
+ loader = UnstructuredFileLoader("cleaned_text-11-02-2023.txt")
9
  raw_documents = loader.load()
10
 
11
  # Split text
vectorstore.pkl CHANGED
Binary files a/vectorstore.pkl and b/vectorstore.pkl differ