htafer commited on
Commit
4b62a43
1 Parent(s): 79ab819

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +10 -2
app.py CHANGED
@@ -7,6 +7,9 @@ from langchain.text_splitter import CharacterTextSplitter
7
  from langchain.embeddings import OpenAIEmbeddings
8
  from langchain.vectorstores import FAISS
9
  from langchain.memory import ConversationBufferMemory
 
 
 
10
  import re
11
  def main():
12
  # Initialize the Streamlit app
@@ -22,9 +25,14 @@ def main():
22
  uploaded_file = st.file_uploader("Upload your document", type=['txt'])
23
  if uploaded_file is not None:
24
  # Read and process the document
25
- text_data = uploaded_file.getvalue().decode("utf-8")
 
 
 
 
 
26
  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
27
- data = text_splitter.split_documents(text_data)
28
 
29
  # Create vector store
30
  embeddings = OpenAIEmbeddings()
 
7
  from langchain.embeddings import OpenAIEmbeddings
8
  from langchain.vectorstores import FAISS
9
  from langchain.memory import ConversationBufferMemory
10
+ from langchain.document_loaders import TextLoader
11
+ from tempfile import NamedTemporaryFile
12
+
13
  import re
14
  def main():
15
  # Initialize the Streamlit app
 
25
  uploaded_file = st.file_uploader("Upload your document", type=['txt'])
26
  if uploaded_file is not None:
27
  # Read and process the document
28
+ with NamedTemporaryFile(delete=False) as f:
29
+ f.write(uploaded_file.getbuffer())
30
+ loader = TextLoader(f.name, encoding="utf-8")
31
+ data = loader.load()
32
+
33
+
34
  text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
35
+ data = text_splitter.split_documents(data)
36
 
37
  # Create vector store
38
  embeddings = OpenAIEmbeddings()