Comments (2)
Hi @skyler14, I have not yet tested minimum requirements for local extraction. If it helps -- I got it working on a 4 GB machine with no GPU. A GPU is highly recommended for video and audio files.
As for setting up a local REST API to send POST requests to, this is not on the roadmap at the moment -- you can do this yourself with Python API frameworks such as Flask or FastAPI
from thepipe.
These are some of the errors I get
======================================================================
ERROR: test_extract_api (test_thepipe.test_thepipe.test_extract_api)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/dylan/Documents/thepipe/tests/test_thepipe.py", line 200, in test_extract_api
chunks = extractor.extract_from_source(source=self.files_directory+"/example.md", local=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dylan/anaconda3/envs/thepipe/lib/python3.11/site-packages/thepipe_api/extractor.py", line 58, in extract_from_source
return extract_from_file(file_path=source, source_type=source_type, verbose=verbose, ai_extraction=ai_extraction, text_only=text_only, local=local)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/dylan/anaconda3/envs/thepipe/lib/python3.11/site-packages/thepipe_api/extractor.py", line 76, in extract_from_file
raise ValueError(f"{response['error']}")
ValueError: No valid API key given. Visit https://thepi.pe/docs to learn more.
======================================================================
FAIL: test_compress_spreadsheet (test_thepipe.test_thepipe.test_compress_spreadsheet)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/dylan/Documents/thepipe/tests/test_thepipe.py", line 156, in test_compress_spreadsheet
self.assertLess(len(all_new_text), len(all_text))
AssertionError: 194 not less than 194
======================================================================
FAIL: test_compress_with_ctags (test_thepipe.test_thepipe.test_compress_with_ctags)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/home/dylan/Documents/thepipe/tests/test_thepipe.py", line 173, in test_compress_with_ctags
self.assertLess(len(new_chunks[0].text), len(chunks[0].text))
AssertionError: 90 not less than 90
----------------------------------------------------------------------
Ran 18 tests in 37.331s
FAILED (failures=2, errors=1, skipped=2)
from thepipe.
Related Issues (16)
- Feature requests 🔨 HOT 4
- Make docker image
- Video frame + transcript extraction
- Audio transcript extraction HOT 1
- No longer working after addition of THEPIPE_API_KEY HOT 5
- `ai_extraction=True` not working locally HOT 2
- Swap Whisper Version
- Some videos (without audio) fail to extract
- add syntax to match multiple patterns with match/ignore functionality.
- Add .ino functionality for GitHub repos related to arduino
- Error when trying to Pipe Linkedin profile
- file type scanning
- Pytesseract error when text_only is True within GitHub Action
- Increment Timestamp for Long Videos
- Full-page screenshot when extracting page URL HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from thepipe.