forked from ashimdahal/jelly
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request ashimdahal#24 from regmi-saugat/main
Updated README.md file
- Loading branch information
Showing
1 changed file
with
22 additions
and
14 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,30 +1,38 @@ | ||
# Jelly | ||
A chatbot that replies to romanized Nepali that is in production. | ||
|
||
Jelly is a chatbot that replies to romanized Nepali. The chatbot is currently in production and can be used online or locally on your own machine. | ||
|
||
![Alt text](static/img/demo.png?raw=true "Jelly In action") | ||
Try Jelly [here online!](https://jelly.thetwl.org). | ||
|
||
Read research about jelly [here!](https://doi.org/10.21203/rs.3.rs-2183870/v2). | ||
- Try Jelly demo from [here online](https://jelly.thetwl.org/) | ||
|
||
- Read the research about jelly from [here](https://www.researchsquare.com/article/rs-2183870/v2) | ||
|
||
## Description | ||
Jelly is a chatbot that uses natural language processing to understand and reply to romanized Nepali. It is built using the Facebook BlenderBot, which is available through the huggingface API. | ||
|
||
To use Jelly locally on your machine, start by cloning the repository and installing the required libraries: | ||
|
||
``` | ||
git clone https://github.com/ashimdahal/jelly.git | ||
pip install -r requirements.txt | ||
``` | ||
|
||
#OR Use it locally on your machine | ||
Start by cloning and installing the required libraries. | ||
Next, create an account on huggingface and obtain an API KEY by going to the [tokens settings](https://huggingface.co/settings/tokens). You will be asked to enter the API key when you run the app. | ||
|
||
git clone https://github.com/ashimdahal/jelly.git | ||
pip install -r requirements.txt | ||
Create an account in hugging face and get the API KEY by going to [the tokens settings.](https://huggingface.co/settings/tokens) | ||
To run the app using Flask, set the environment variable and run the Flask app: | ||
|
||
You'd be asked to paste the token when you run the app. | ||
## Run it using FLASK | ||
Set the environment variable and run the flask app. | ||
``` | ||
export FLASK_APP=index | ||
flask run | ||
``` | ||
|
||
--- | ||
|
||
## Credits | ||
I had to squash previous 60+ commits and 7 Pull Requests into single commit to protect privacy on some of our API credentials and Database URLs. This act have blurred the immense amount of contributions from **[Anuj Khadka](https://github.com/Anuj-Khadka)** and **[Parash Bam](https://github.com/Parashbam69)**; show them some love by dropping a follow; while you're on it, drop one for me as well **[Ashim Dahal.](https://github.com/ashimdahal)** | ||
|
||
In order to protect the privacy of certain API credentials and database URLs, we had to squash previous commits (60+ in total) into a single commit. This means that the commit history of this project does not accurately reflect the full extent of the contributions made by our collaborators [Anuj Khadka](https://github.com/Anuj-Khadka) and [Parash Bam](https://github.com/Parashbam69). We would like to extend our thanks to them for their hard work and dedication to this project. | ||
|
||
The chatbot used in this project is facebook blenderbot, used on huggingface API. | ||
Special thanks to [Bishal](https://github.com/kbshal) for allowing us to use his [anytranslate](https://github.com/kbshal/Anytranslate) API in our translation system. | ||
|
||
Special Thanks to **[Bishal](https://github.com/kbshal)** at https://github.com/kbshal for his permission to use his anytranslate API, which I modded to use in our translation system. | ||
The chatbot used in this project is facebook blenderbot, used on huggingface API. |