Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/andrewn6/p
scrapes a pptx or pdf file and summarizes it
https://github.com/andrewn6/p
ml
Last synced: 6 days ago
JSON representation
scrapes a pptx or pdf file and summarizes it
- Host: GitHub
- URL: https://github.com/andrewn6/p
- Owner: andrewn6
- Created: 2023-05-16T23:12:30.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-06-11T19:41:36.000Z (over 1 year ago)
- Last Synced: 2024-12-31T07:44:29.331Z (8 days ago)
- Topics: ml
- Language: Svelte
- Homepage: https://pdf.nijmeh.world
- Size: 413 KB
- Stars: 6
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# p
small tool that takes a PDF file, summarizes it
made this because some of my classes can have super long power points that I don't really wanna go through, and i like automating things.
hosted on p.nijmeh.world if you wanna try it out! (soon)
## tech
- python for backend
- svelte for the UI
- spaCy for NLP
## folder breakdown
- `kibbeh` sanic API, has endpoints to summarize/get files
- `falafel` svelte frontend for `kibbeh`'s functionality
## api design
### `POST /summarize`
append a PDF/PPTX file to FormData under the field `file`
returns
```jsonc
{ id: "[id]" }
```
... which you can then use to fetch the completed summarization from `/summarization/[id]`
example using curl
```
curl -X POST -F "[email protected]" http://localhost:8080/upload
```
### `GET /summarization/[id]`
get a summarization. returns:
```jsonc
{
"text": "text", // bla bla bla
"name": "filename", // the original filename
"ext": "pptx", // the original extension
"date": 1686509446940 // when the summarization was completed
}
```
example using curl
```
curl -0 -J -L http://localhost:8080/summarization/9a973399-deb1-4ec2-b536-83e03f527411`
```