|
|
--- |
|
|
language: |
|
|
- en |
|
|
- de |
|
|
tags: |
|
|
- txt |
|
|
- keyword-search |
|
|
- python |
|
|
- windows |
|
|
- RAG |
|
|
--- |
|
|
|
|
|
# raw-txt-snippet-creator |
|
|
Buzzword search with "AND" option within distance. Its like an embedder only with plain txt search!<br> |
|
|
It's like opening a text editor, searching for a keyword, and finding X hits. Now the snippet extractor cuts out a section around each keyword. |
|
|
The maximum text found is never larger than the original text, as overlapping sections are merged! |
|
|
|
|
|
# version 08alpha |
|
|
* Only windows tested with one large book! |
|
|
* Only txt files |
|
|
* Choose one txt file or a whole folder |
|
|
* Type a buzzword or more, only with AND (second search field) its connected with in a "distance option". |
|
|
* All matches found are cut out as a snippet (in % 0.3 before and 0.7 after the keyword) |
|
|
* All overlaped snippets ar merged |
|
|
* Two search options "usual wildcard" and "fuzzy-search"<br> |
|
|
(wildcard search If you have the word “friendship” and search for “friend” it will not be found. You should use “friend*”. "?" is only one character like usual.)<br> |
|
|
(fuzzy is sometime usefully , but it dont work with any punctuation like ip adresses, but it can handle in some cases * and ?) |
|
|
* All snippets are appended and saved (one for wildcard one for fuzzy) in json format with te match and found position<br> |
|
|
(the position you can see eg: in notepad++) |
|
|
* Output files are always overwritten when you click “Search” again. |
|
|
* Now you can easily copy and paste to your chat |
|
|
|
|
|
https://github.com/kalle07/raw-txt-snippet-creator |
|
|
|
|
|
|
|
|
|
|
|
 |
|
|
|
|
|
|
