Spaces:
Runtime error
Runtime error
Carlos Salgado
commited on
Commit
•
d665e88
1
Parent(s):
9ed2bd2
update backend files, ignore pycache
Browse files- .gitignore +2 -1
- generate_metadata.py → backend/generate_metadata.py +0 -0
- backend/ingest.py +7 -0
- 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
|