🏂
I use the power of knowledge to obtain a better version of ourselves in the infosphere
Highlights
- Pro
Pinned Loading
-
traNsLatorLaB
traNsLatorLaB Publictranslatorlab: a machine translation tool that uses artificial intelligence models to provide accurate and fast translations between different languages
-
This Python script extracts text fro...
This Python script extracts text from PDF files using three different libraries: `pdfminer`, `unstructured`, and `pymupdf`. It allows you to choose the extraction method via command-line arguments and saves the extracted text to a specified output file or prints it to the terminal. 1#!/usr/bin/env python3
2#python3 -m pip install pymupdf unstructured pdfminer
3#chmod +x pdf2text.py
4#python3 pdf2text.py path/to/your/pdf/file.pdf -m unstructured -o output_file
5 -
Split Text into Sentences with Maxim...
Split Text into Sentences with Maximum Length 1#!/usr/bin/env python3
23#python3 -m pip install nltk
4#chmod +x split_max_text.py
5#./split_max_text.py "This is a test sentence. This is another test sentence. This is a long test sentence." 20
-
Secure remote Ollama API with Caddy ...
Secure remote Ollama API with Caddy Auth & Ngrok on Google Colab in one shot 1{
2"nbformat": 4,
3"nbformat_minor": 0,
4"metadata": {
5"colab": {
-
Split Text into Tokenized Chunks
Split Text into Tokenized Chunks 1#!/usr/bin/env python3
2#python3 -m pip install nltk tiktoken
3#chmod +x split_sentence2maxtok.py
4#./split_sentence2maxtok.py "This is a test sentence. This is another test sentence. This is a long test sentence." 6
5 -
awesome-promptbook
awesome-promptbook PublicCollection of creative and useful prompts you can use to create interesting content
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.