72384b191d
### What problem does this PR solve?
Add `.doc` file parser, using tika.
```
pip install tika
```
```
from tika import parser
from io import BytesIO
def extract_text_from_doc_bytes(doc_bytes):
file_like_object = BytesIO(doc_bytes)
parsed = parser.from_buffer(file_like_object)
return parsed["content"]
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: chrysanthemum-boy <fannc@qq.com>
|
||
|---|---|---|
| .. | ||
| app | ||
| llm | ||
| nlp | ||
| res | ||
| svr | ||
| utils | ||
| __init__.py | ||
| settings.py | ||