Public/kotaemon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add docstring for database and OCR loader

Browse Source
This commit is contained in:
trducng
2024-02-20 21:20:48 +07:00
parent 767aaaa1ef
commit 08cc99d8db
2 changed files with 75 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
libs/kotaemon/kotaemon/loaders/ocr_loader.py
View File

@@ -14,14 +14,25 @@ DEFAULT_OCR_ENDPOINT = "http://127.0.0.1:8000/v2/ai/infer/"
class OCRReader(BaseReader):
def __init__(self, endpoint: str = DEFAULT_OCR_ENDPOINT, use_ocr=True):
"""Init the OCR reader with OCR endpoint (FullOCR pipeline)
"""Read PDF using OCR, with high focus on table extraction
Args:
endpoint: URL to FullOCR endpoint. Defaults to OCR_ENDPOINT.
use_ocr: whether to use OCR to read text
(e.g: from images, tables) in the PDF
"""
Example:
```python
>> from kotaemon.loaders import OCRReader
>> reader = OCRReader()
>> documents = reader.load_data("path/to/pdf")
```
Args:
endpoint: URL to FullOCR endpoint. Defaults to
`kotaemon.loaders.ocr_loader.DEFAULT_OCR_ENDPOINT`
(http://127.0.0.1:8000/v2/ai/infer/)
use_ocr: whether to use OCR to read text (e.g: from images, tables) in the PDF
If False, only the table and text within table cells will be extracted.
"""
def __init__(self, endpoint: str = DEFAULT_OCR_ENDPOINT, use_ocr=True):
"""Init the OCR reader with OCR endpoint (FullOCR pipeline)"""
super().__init__()
self.ocr_endpoint = endpoint
self.use_ocr = use_ocr