Hugging Face's logo

Spaces:
salgadev
/
docverifyrag
Sleeping

App Files Community
Carlos Salgado commited on
Commit
d665e88
•
1 Parent(s): 9ed2bd2

update backend files, ignore pycache

Browse files
Files changed (4) hide show
  1. .gitignore +2 -1
  2. generate_metadata.py → backend/generate_metadata.py +0 -0
  3. backend/ingest.py +7 -0
  4. schema.py → backend/schema.py +0 -0
.gitignore CHANGED
@@ -3,4 +3,5 @@
3
  .env
4
  .venv
5
  .ipynb_checkpoints
6
- flake.nix
 
 
3
  .env
4
  .venv
5
  .ipynb_checkpoints
6
+ flake.nix
7
+ *__pycache__*
generate_metadata.py → backend/generate_metadata.py RENAMED
File without changes
backend/ingest.py ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ from langchain_community.document_loaders import UnstructuredPDFLoader
2
+
3
+ def ingest_pdf(path):
4
+ loader = UnstructuredPDFLoader()
5
+ text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
6
+
7
+ return data
schema.py → backend/schema.py RENAMED
File without changes