mirror of
https://github.com/SillyTavern/SillyTavern.git
synced 2025-06-05 21:59:27 +02:00
Merge branch 'main' into paniphons-patch-1
This commit is contained in:
Cohee
GitHub
22
readme.md
22
readme.md
@@ -1,13 +1,13 @@
|
||||
# SillyTavern
|
||||
|
||||
### Brought to you by @SillyLossy and @RossAscends
|
||||
# SillyTavern
|
||||
## Based on fork of TavernAI 1.2.8
|
||||
### Brought to you by @Cohee1207 and @RossAscends
|
||||
|
||||
### What is SillyTavern or TavernAI?
|
||||
Tavern is a user interface you can install on your computer (and Android phones) that allows you to interact text generation AIs and chat/roleplay with characters you or the community create.
|
||||
|
||||
SillyTavern is a fork of TavernAI 1.2.8 which is under more active development, and has added many major features. At this point they can be thought of as completely independent programs.
|
||||
|
||||
|
||||
### What do I need other than Tavern?
|
||||
On its own Tavern is useless, as it's just a user interface. You have to have access to an AI system backend that can act as the roleplay character. There are various supported backends: OpenAPI API (GPT), KoboldAI (either running locally or on Google Colab), and more.
|
||||
|
||||
@@ -15,16 +15,16 @@ On its own Tavern is useless, as it's just a user interface. You have to have ac
|
||||
The most advanced/intelligent AI backend for roleplaying is to pay for OpenAI's GPT API. It's also among the easiest to use. Objectively, GPT is streets ahead of all other backends. However, OpenAI log all your activity, and your account MAY be banned in the future if you violate their policies (e.g. on adult content). However, there are no reports of anyone being banned yet.
|
||||
People who value privacy more tend to run a self-hosted AI backend like KoboldAI. Self-hosted backends do not log, but they are much less capable at roleplaying.
|
||||
|
||||
### Do I need a powerful PC to run Tavern?**
|
||||
### Do I need a powerful PC to run Tavern?
|
||||
Since Tavern is only a user interface, it has tiny hardware requirements, it will run on anything. It's the AI system backend that needs to be powerful.
|
||||
|
||||
### I want to try self-hosted easily. Got a Google Colab?
|
||||
|
||||
Try on Colab (runs KoboldAI backend and TavernAI Extras server alongside): <a target="_blank" href="https://colab.research.google.com/github/SillyLossy/TavernAI-extras/blob/main/colab/GPU.ipynb">
|
||||
Try on Colab (runs KoboldAI backend and TavernAI Extras server alongside): <a target="_blank" href="https://colab.research.google.com/github/Cohee1207/TavernAI-extras/blob/main/colab/GPU.ipynb">
|
||||
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
|
||||
</a>
|
||||
|
||||
https://colab.research.google.com/github/SillyLossy/TavernAI-extras/blob/main/colab/GPU.ipynb
|
||||
https://colab.research.google.com/github/Cohee1207/TavernAI-extras/blob/main/colab/GPU.ipynb
|
||||
|
||||
## Mobile support
|
||||
|
||||
@@ -42,18 +42,18 @@ https://rentry.org/TAI_Termux
|
||||
* [Oobabooga's TextGen WebUI](https://github.com/oobabooga/text-generation-webui) API connection
|
||||
* Soft prompts selector for KoboldAI
|
||||
* Prompt generation formatting tweaking
|
||||
* Extensibility support via [SillyLossy's TAI-extras](https://github.com/SillyLossy/TavernAI-extras) plugins
|
||||
* Extensibility support via [SillyLossy's TAI-extras](https://github.com/Cohee1207/TavernAI-extras) plugins
|
||||
* Character emotional expressions
|
||||
* Auto-Summary of the chat history
|
||||
* Sending images to chat, and the AI interpreting the content.
|
||||
|
||||
## UI Extensions 🚀
|
||||
| Name | Description | Required <a href="https://github.com/SillyLossy/TavernAI-extras#modules" target="_blank">Extra Modules</a> | Screenshot |
|
||||
| Name | Description | Required <a href="https://github.com/Cohee1207/TavernAI-extras#modules" target="_blank">Extra Modules</a> | Screenshot |
|
||||
| ---------------- | ---------------------------------| ---------------------------- | ---------- |
|
||||
| Image Captioning | Send a cute picture to your bot!<br><br>Picture select option will appear beside "Message send" button. | `caption` | <img src="https://user-images.githubusercontent.com/18619528/224161576-ddfc51cd-995e-44ec-bf2d-d2477d603f0c.png" style="max-width:200px" /> |
|
||||
| Character Expressions | See your character reacting to your messages!<br><br>**You need to provide your own character images!**<br><br>1. Create a folder in TavernAI called `public/characters/<name>`, where `<name>` is a name of your character.<br>2. For base emotion classification model, put six PNG files there with the following names: `joy.png`, `anger.png`, `fear.png`, `love.png`, `sadness.png`, `surprise.png`. Other models may provide another options.<br>3. Images only display in desktop mode. | `classify` | <img style="max-width:200px" alt="image" src="https://user-images.githubusercontent.com/18619528/223765089-34968217-6862-47e0-85da-7357370f8de6.png"> |
|
||||
| Memory | Chatbot long-term memory simulation using automatic message context summarization. | `summarize` | <img style="max-width:200px" alt="image" src="https://user-images.githubusercontent.com/18619528/223766279-88a46481-1fa6-40c5-9724-6cdd6f587233.png"> |
|
||||
| Floating Prompt | Adds a string to your scenario after certain amount of messages you send. Usage ideas: reinforce certain events during roleplay. Thanks @Ali឵#2222 for suggesting me that! | None | <img style="max-width:200px" src="https://user-images.githubusercontent.com/18619528/224158641-c317313c-b87d-42b2-9702-ea4ba896593e.png" /> |
|
||||
| Author's Note | Adds a string to your scenario after certain amount of messages you send. Usage ideas: reinforce certain events during roleplay. Thanks @Ali឵#2222 for suggesting me that! | None | <img style="max-width:200px" src="https://user-images.githubusercontent.com/18619528/224158641-c317313c-b87d-42b2-9702-ea4ba896593e.png" /> |
|
||||
| D&D Dice | A set of 7 classic D&D dice for all your dice rolling needs.<br><br>*I used to roll the dice.<br>Feel the fear in my enemies' eyes* | None | <img style="max-width:200px" alt="image" src="https://user-images.githubusercontent.com/18619528/226199925-a066c6fc-745e-4a2b-9203-1cbffa481b14.png"> |
|
||||
| Author's Note | Built-in extension that allows you to append notes that will be added to the context and steer the story and character in a specific direction. Because it's sent after the character description, it has a lot of weight. | None | 
|
||||
|
|
||||
@@ -88,7 +88,7 @@ https://rentry.org/TAI_Termux
|
||||
|
||||
*NOTE: This branch is intended for local install purposes, and has not been tested on a colab or other cloud notebook service.*
|
||||
|
||||
1. install [NodeJS](nodejs.org)
|
||||
1. install [NodeJS](https://nodejs.org/en)
|
||||
2. download the zip from this github repo
|
||||
3. unzip it into a folder of your choice
|
||||
4. run start.bat via double clicking or in a command line.
|
||||
@@ -130,7 +130,7 @@ Contact us on Discord: Cohee#1207 or RossAscends#1779
|
||||
|
||||
## License and credits
|
||||
* TAI Base by Humi: Unknown license
|
||||
* SillyLossy's TAI mod: Public domain
|
||||
* Cohee's TAI mod: Public domain
|
||||
* RossAscends' additions: Public domain
|
||||
* Portions of CncAnon's TavernAITurbo mod: Unknown license
|
||||
* Thanks oobabooga for compiling presets for TextGen
|
||||
|
||||
@@ -168,9 +168,11 @@ app.use((req, res, next) => {
|
||||
if (req.url.startsWith('/characters/') && is_colab && process.env.googledrive == 2) {
|
||||
|
||||
const filePath = path.join(charactersPath, decodeURIComponent(req.url.substr('/characters'.length)));
|
||||
console.log('req.url: ' + req.url);
|
||||
console.log(filePath);
|
||||
fs.access(filePath, fs.constants.R_OK, (err) => {
|
||||
if (!err) {
|
||||
res.sendFile(filePath);
|
||||
res.sendFile(filePath, { root: __dirname });
|
||||
} else {
|
||||
res.send('Character not found: ' + filePath);
|
||||
//next();
|
||||
|
||||
Reference in New Issue
Block a user