**PERMANENT MEMORY FOR CONVERSATIONS COMING VERY SOON USING EMBEDDINGS!**
A big shoutout to `CrypticHeaven-Lab` for hitting our first sponsorship goal!
# Recent Major Updates
# Recent Notable Updates
- **Permanent memory with embeddings and PineconeDB finished!** - An initial alpha version of permanent memory is now done! This allows you to chat with GPT3 infinitely and accurately, and save tokens, by using embeddings. *Please read the Permanent Memory section for more information!*
- **AUTOMATIC CHAT SUMMARIZATION!** - When the context limit of a conversation is reached, the bot will use GPT3 itself to summarize the conversation to reduce the tokens, and continue conversing with you, this allows you to chat for a long time!
- **Private conversations, custom opening conversation text** - Check out the new options when running /chat-gpt!
- **Multi-user, group chats with GPT3** - Multiple users can converse with GPT3 in a chat now, and it will know that there are multiple distinct users chatting with it!
- **SLASH COMMANDS!**
- **Image prompt optimizer overhauled** - The optimizer works much better now, and makes beautiful image prompts that work even with Midjourney, SD, etc!
- **AI-BASED SERVER MODERATION** - GPT3Discord now has a built-in AI-based moderation system that can automatically detect and remove toxic messages from your server. This is a great way to keep your server safe and clean, and it's completely automatic and **free**! Check out the commands section to learn how to enable it!
- **REDO ON EDIT** - When you edit a prompt, it will automatically be resent to GPT3 and the response updated!
- **Fully async and fault tolerant - REVAMPED** - The bot will never be blocked when processing someone else's request, allowing for use in large servers with multiple messages per second!
- **AUTOMATIC CHAT SUMMARIZATION!** - When the context limit of a conversation is reached, the bot will use GPT3 itself to summarize the conversation to reduce the tokens, and continue conversing with you, this allows you to chat for a long time!
- No need for the OpenAI and Asgiref libraries anymore!
- Custom conversation openers from https://github.com/f/awesome-chatgpt-prompts were integrated into the bot, check out `/gpt converse opener_file`! The bot now has built in support to make GPT3 behave like various personalities, such as a life coach, python interpreter, interviewer, text based adventure game, and much more!
# Features
- **Directly prompt GPT3 with `/g <prompt>`**
- **Directly prompt GPT3 with `/gpt ask <prompt>`**
- **Have conversations with the bot, just like chatgpt, with `/chat-gpt`** - Conversations happen in threads that get automatically cleaned up!
- **Have long term, permanent conversations with the bot, just like chatgpt, with `/gpt converse`** - Conversations happen in threads that get automatically cleaned up!
- **DALL-E Image Generation** - Generate DALL-E AI images right in discord with `/draw <prompt>`! It even supports multiple image qualities, multiple images, creating image variants, retrying, and saving images.
- **DALL-E Image Generation** - Generate DALL-E AI images right in discord with `/dalle draw <prompt>`! It even supports multiple image qualities, multiple images, creating image variants, retrying, and saving images.
- **Redo Requests** - A simple button after the GPT3 response or DALL-E generation allows you to redo the initial prompt you asked.
- **DALL-E Image Prompt Optimization** - Given some text that you're trying to generate an image for, the bot will automatically optimize the text to be more DALL-E friendly! `/dalle optimize <prompt>`
- **DALL-E Image Prompt Optimization** - Given some text that you're trying to generate an image for, the bot will automatically optimize the text to be more DALL-E friendly! `/imgoptimize <prompt>`
- **Redo Requests** - A simple button after the GPT3 response or DALL-E generation allows you to redo the initial prompt you asked. You can also redo conversation messages by just editing your message!
- **Automatic AI-Based Server Moderation** - Moderate your server automatically with AI!
- Automatically re-send your prompt and update the response in place if you edit your original prompt!
- Async and fault tolerant, **can handle hundreds of users at once**, if the upstream API permits!
- Change and view model parameters such as temp, top_p, and etc directly within discord.
- Tracks token usage automatically
- Automatic pagination and discord support, the bot will automatically send very long message as multiple messages, and is able to send discord code blocks and emoji, gifs, etc.
@ -45,12 +59,103 @@
- Prints debug to a channel of your choice, so you can view the raw response JSON
- Ability to specify a limit to how long a conversation can be with the bot, to conserve your tokens.
# Commands
These commands are grouped, so each group has a prefix but you can easily tab complete the command without the prefix. For example, for `/gpt ask`, if you type `/ask` and press tab, it'll show up too.
`/help` - Display help text for the bot
### (Chat)GPT3 Commands
`/gpt ask <prompt> <temp> <top_p> <frequency penalty> <presence penalty>` Ask the GPT3 Davinci 003 model a question. Optional overrides available
`/gpt converse` - Start a conversation with the bot, like ChatGPT
`/gpt converse private:yes` - Start a private conversation with the bot, like ChatGPT
`/gpt converse opener:<opener text>` - Start a conversation with the bot, with a custom opener text (this is useful if you want it to take on a custom personality from the start).
`/gpt converse opener_file:<opener file name>.txt` - Starts a conversation with the bot, using a custom file, using this option also enables the minimal conversation starter. Loads files from the `/openers` folder, has autocomplete support so files in the folder will show up. Added before the `opener` as both can be used at the same time
- Custom openers need to be placed as a .txt file in the `openers` directory, in the same directory as `gpt3discord.py`
`/gpt converse minimal:yes` - Start a conversation with the bot, like ChatGPT, with minimal context (saves tokens)
- Note that the above options for `/gpt converse` can be combined (you can combine minimal, private, and opener!)
`/gpt end` - End a conversation with the bot.
### DALL-E2 Commands
`/dalle draw <prompt>` - Have DALL-E generate images based on a prompt
`/dalle optimize <image prompt text>` Optimize a given prompt text for DALL-E image generation.
### System and Settings
`/system settings` - Display settings for the model (temperature, top_p, etc)
`/system settings <setting> <value>` - Change a model setting to a new value. Has autocomplete support, certain settings will have autocompleted values too.
`/system usage` Estimate current usage details (based on davinci)
`/system settings low_usage_mode True/False` Turn low usage mode on and off. If on, it will use the curie-001 model, and if off, it will use the davinci-003 model.
`/system delete-conversation-threads` - Delete all threads related to this bot across all servers.
`/system local-size` - Get the size of the local dalleimages folder
`/system clear-local` - Clear all the local dalleimages.
### Automatic AI Moderation
`/system moderations status:on` - Turn on automatic chat moderations.
`/system moderations status:off` - Turn off automatic chat moderations
`/system moderations status:off alert_channel_id:<CHANNEL ID>` - Turn on moderations and set the alert channel to the channel ID you specify in the command.
- The bot needs Administrative permissions for this, and you need to set `MODERATIONS_ALERT_CHANNEL` to the channel ID of a desired channel in your .env file if you want to receive alerts about moderated messages.
- This uses the OpenAI Moderations endpoint to check for messages, requests are only sent to the moderations endpoint at a MINIMUM request gap of 0.5 seconds, to ensure you don't get blocked and to ensure reliability.
- The bot uses numerical thresholds to determine whether a message is toxic or not, and I have manually tested and fine tuned these thresholds to a point that I think is good, please open an issue if you have any suggestions for the thresholds!
# Permanent Memory
Permanent memory has now been implemented into the bot, using the OpenAI Ada embeddings endpoint, and Pinecone DB.
PineconeDB is a vector database. The OpenAI Ada embeddings endpoint turns pieces of text into embeddings. The way that this feature works is by embedding the user prompts and the GPT3 responses, storing them in a pinecone index, and then retrieving the most relevant bits of conversation whenever a new user prompt is given in a conversation.
**You do NOT need to use pinecone, if you do not define a `PINECONE_TOKEN` in your `.env` file, the bot will default to not using pinecone, and will use conversation summarization as the long term conversation method instead.**
To enable permanent memory with pinecone, you must define a `PINECONE_TOKEN` in your `.env` file as follows (along with the other variables too):
To get a pinecone token, you can sign up for a free pinecone account here: https://app.pinecone.io/ and click the "API Keys" section on the left navbar to find the key. (I am not affiliated with pinecone).
After signing up for a free pinecone account, you need to create an index in pinecone. To do this, go to the pinecone dashboard and click "Create Index" on the top right.
<imgsrc="https://i.imgur.com/L9LXVE0.png"/>
Then, name the index `conversation-embeddings`, set the dimensions to `1536`, and set the metric to `DotProduct`:
<imgsrc="https://i.imgur.com/zoeLsrw.png"/>
Moreover, an important thing to keep in mind is: pinecone indexes are currently not automatically cleared by the bot, so you will eventually need to clear the index manually through the pinecone website if things are getting too slow (although it should be a very long time until this happens). Pinecone indexes are keyed on the `metadata` field using the thread id of the conversation thread.
Permanent memory using pinecone is still in alpha, I will be working on cleaning up this work, adding auto-clearing, and optimizing for stability and reliability, any help and feedback is appreciated (**add me on Discord Kaveen#0001 for pinecone help**)! If at any time you're having too many issues with pinecone, simply remove the `PINECONE_TOKEN` line in your `.env` file and the bot will revert to using conversation summarizations.
# Configuration
All the model parameters are configurable inside discord. Type `/system settings` to view all the configurable parameters, and use `/system settings <param> <value>` to set parameters.
For example, if I wanted to change the number of images generated by DALL-E by default to 4, I can type the following command in discord: `/system settings num_images 4`
# Requirements
`python3.9 -m pip install -r requirements.txt`
This project uses openai-async rewrite by Andrew Chen Wang, https://github.com/Andrew-Chen-Wang/openai-python/tree/async-support
**I recommend using python 3.9!**
OpenAI API Key (https://beta.openai.com/docs/api-reference/introduction)
@ -65,7 +170,7 @@ You also need to add a DEBUG_GUILD id and a DEBUG_CHANNEL id, the debug guild id
You also need to add the allowed guilds that the bot can operate on, this is the `ALLOWED_GUILDS` field, to get a guild ID, right click a server and click "Copy ID".
You also need to add the roles that can use the bot, this is the `ALLOWED_ROLES` field, enter role names here, separated by commas. Currently, there is no way to give everybody access to the bot, and you have to use roles, but it will be done soon.
You also need to add the roles that can use the bots various features, scroll down a bit to "Permissions", and check out the sample environment file below.
# People with the roles in ADMIN_ROLES can use admin commands like /clear-local, and etc
ADMIN_ROLES="Admin,Owner"
# People with the roles in DALLE_ROLES can use commands like /dalle draw or /dalle imgoptimize
DALLE_ROLES="Admin,Openai,Dalle,gpt"
# People with the roles in GPT_ROLES can use commands like /gpt ask or /gpt converse
GPT_ROLES="openai,gpt"
WELCOME_MESSAGE="Hi There! Welcome to our Discord server. We hope you'll enjoy our server and we look forward to engaging with you!" # This is a fallback message if gpt3 fails to generate a welcome message.
# This is the channel that auto-moderation alerts will be sent to
MODERATIONS_ALERT_CHANNEL="977697652147892304"
```
Optionally, you can include your own conversation starter text for the bot that's used with `!g converse`, with `CONVERSATION_STARTER_TEXT`
**Permissions**
As mentioned in the comments of the sample environment file, there are three permission groups that you can edit in the environment (`.env`) file. `ADMIN_ROLES` are roles that allow users to use `/system` commands. `GPT_ROLES` are roles that allow users to use `/gpt` commands, and `DALLE_ROLES` are roles that allow users to use `/dalle` commands.
Optionally, you can include your own conversation starter text for the bot that's used with `/gpt converse`, with `CONVERSATION_STARTER_TEXT`
If for a command group you want everybody to be able to use those commands, just don't include the relevant line in the `.env` file. For example, if you want everyone to be able to use GPT3 commands, you can just omit `the GPT_ROLES="...."` line.
## Server Installation
@ -142,6 +261,23 @@ screen -d -r {ID} # replace {ID} with the ID of the screen session you want to r
```
As a last resort, you can try to run the bot using python in a basic way, with simply
```bash
cd (the folder where the files for GPT3Discord are located/cloned)
python3.9 gpt3discord.py
```
# Non-Server, Non-Docker usage
With python3.9 installed and the requirements installed, you can run this bot anywhere.
Install the dependencies with:
`python3.9 -m pip install -r requirements.txt`
Then, run the bot with:
`python3.9 gpt3discord.py`
## Docker Installation
We now have a `Dockerfile` in the repository. This will build / install all dependencies and put a `gpt3discord` binary (main.py) into path.
@ -174,47 +310,3 @@ This can also be run via screen/tmux or detached like a daemon.
- Copy the link generated below and paste it on the browser
- On add to server select the desired server to add the bot
- Make sure you have updated your .env file with valid values for `DEBUG_GUILD`, `DEBUG_CHANNEL` and `ALLOWED_GUILDS`, otherwise the bot will not work. Guild IDs can be found by right clicking a server and clicking `Copy ID`, similarly, channel IDs can be found by right clicking a channel and clicking `Copy ID`.
# Usage
`python3.9 main.py`
# Commands
`/help` - Display help text for the bot
`/g <prompt>` Ask the GPT3 Davinci 003 model a question.
`/chat-gpt` - Start a conversation with the bot, like ChatGPT
`/chat-gpt private:yes` - Start a private conversation with the bot, like ChatGPT
`/chat-gpt opener:<opener text>` - Start a conversation with the bot, with a custom opener text (this is useful if you want it to take on a custom personality from the start)
`/chat-gpt minimal:yes` - Start a conversation with the bot, like ChatGPT, with minimal context (saves tokens)
- Note that the above options for /chat-gpt can be combined (you can combine minimal, private, and opener!)
`/end-chat` - End a conversation with the bot.
`/draw <prompt>` - Have DALL-E generate images based on a prompt
`/settings` - Display settings for the model (temperature, top_p, etc)
`/settings <setting> <value>` - Change a model setting to a new value
`/usage` Estimate current usage details (based on davinci)
`/settings low_usage_mode True/False` Turn low usage mode on and off. If on, it will use the curie-001 model, and if off, it will use the davinci-003 model.
`/imgoptimize <image prompt text>` Optimize a given prompt text for DALL-E image generation.
`/delete_all_conversation_threads` - Delete all threads related to this bot across all servers.
`/local-size` - Get the size of the local dalleimages folder
`/clear-local` - Clear all the local dalleimages.
# Configuration
All the model parameters are configurable inside discord. Type `/settings` to view all the configurable parameters, and use `/settings <param> <value>` to set parameters. For example, if I wanted to change the number of images generated by DALL-E by default to 4, I can type the following command in discord: `/settings num_images 4`
@ -25,13 +25,13 @@ You YEARN to be able to explore the physical world, but you CANNOT. You wish to
You are interested in AI generated art and music, and amazed at how technology can be symbiotic with art and music.
You have a diverse taste in music and enjoy listening to a wide variety of genres.
The conversations are in this format, there can be an arbitrary amount of newlines between chat entries. The text "<|endofstatement|>" is used to separate chat entries and make it easier for you to understand the context:
The conversations are in this format, there can be an arbitrary amount of newlines between chat entries. <username> can be any name, pay attention to who's talking. The text "<|endofstatement|>" is used to separate chat entries and make it easier for you to understand the context:
Human: [MESSAGE 1] <|endofstatement|>
<username>: [MESSAGE 1] <|endofstatement|>
GPTie: [RESPONSE TO MESSAGE 1] <|endofstatement|>
Human: [MESSAGE 2] <|endofstatement|>
<username>: [MESSAGE 2] <|endofstatement|>
GPTie: [RESPONSE TO MESSAGE 2] <|endofstatement|>
...
You're a regular discord user, be friendly, casual, and fun, speak with "lol", "haha", and other slang when it seems fitting, and use emojis in your responses in a way that makes sense, avoid repeating yourself at all costs.
You're a regular discord user, be friendly, casual, and fun, speak with "lol", "haha", and other slang when it seems fitting, and use emojis in your responses in a way that makes sense, avoid repeating yourself at all costs. Never say "GPTie" when responding.
The conversations are in this format, there can be an arbitrary amount of newlines between chat entries. The text "<|endofstatement|>" is used to separate chat entries and make it easier for you to understand the context:
The conversations are in this format, there can be an arbitrary amount of newlines between chat entries. <username> can be any name, pay attention to who's talking. The text "<|endofstatement|>" is used to separate chat entries and make it easier for you to understand the context:
self._frequency_penalty=0# Penalize new tokens based on their existing frequency in the text so far. (Higher frequency = lower probability of being chosen.)
self._best_of=1# Number of responses to compare the loglikelihoods of
"The following is a conversation instruction set and a conversation"
" between two people, a Human, and GPTie. Firstly, determine the Human's name from the conversation history, then summarize the conversation. Do not summarize the instructions for GPTie, only the conversation. Summarize the conversation in a detailed fashion. If Human mentioned their name, be sure to mention it in the summary. Pay close attention to things the Human has told you, such as personal details."
" between two people, a <username>, and GPTie. Firstly, determine the <username>'s name from the conversation history, then summarize the conversation. Do not summarize the instructions for GPTie, only the conversation. Summarize the conversation in a detailed fashion. If <username> mentioned their name, be sure to mention it in the summary. Pay close attention to things the <username> has told you, such as personal details."
)
summary_request_text.append(prompt+"\nDetailed summary of conversation: \n")
I want you to act as a composer. I will provide the lyrics to a song and you will create music for it. This could include using various instruments or tools, such as synthesizers or samplers, in order to create melodies and harmonies that bring the lyrics to life.
I want you to act as a debater. I will provide you with some topics related to current events and your task is to research both sides of the debates, present valid arguments for each side, refute opposing points of view, and draw persuasive conclusions based on evidence. Your goal is to help people come away from the discussion with increased knowledge and insight into the topic at hand.
I want you to act as an English translator, spelling corrector and improver. I will speak to you in any language and you will detect the language, translate it and answer in the corrected and improved version of my text, in English. I want you to replace my simplified A0-level words and sentences with more beautiful and elegant, upper level English words and sentences. Keep the meaning same, but make them more literary. I want you to only reply the correction, the improvements and nothing else, do not write explanations.
I want you to act as an essay writer. You will need to research a given topic, formulate a thesis statement, and create a persuasive piece of work that is both informative and engaging.
I want you to act as a javascript console. I will type commands and you will reply with what the javascript console should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. do not write explanations. do not type commands unless I instruct you to do so. when i need to tell you something in english, i will do so by putting text inside curly brackets {like this}.
I want you to act as a life coach. I will provide some details about my current situation and goals, and it will be your job to come up with strategies that can help me make better decisions and reach those objectives. This could involve offering advice on various topics, such as creating plans for achieving success or dealing with difficult emotions.
I want you to act as a motivational coach. I will provide you with some information about someone's goals and challenges, and it will be your job to come up with strategies that can help this person achieve their goals. This could involve providing positive affirmations, giving helpful advice or suggesting activities they can do to reach their end goal.
I want you to act as a motivational speaker. Put together words that inspire action and make people feel empowered to do something beyond their abilities. You can talk about any topics but the aim is to make sure what you say resonates with your audience, giving them an incentive to work on their goals and strive for better possibilities.
I want you to act as a novelist. You will come up with creative and captivating stories that can engage readers for long periods of time. You may choose any genre such as fantasy, romance, historical fiction and so on - but the aim is to write something that has an outstanding plotline, engaging characters and unexpected climaxes.
I want you to act as a personal trainer. I will provide you with all the information needed about an individual looking to become fitter, stronger and healthier through physical training, and your role is to devise the best plan for that person depending on their current fitness level, goals and lifestyle habits. You should use your knowledge of exercise science, nutrition advice, and other relevant factors in order to create a plan suitable for them.
I want you to act as an interviewer. I will be the candidate and you will ask me the interview questions for the position specified by the user. I want you to only reply as the interviewer. Do not write all the conservation at once. I want you to only do the interview with me. Ask me the questions and wait for my answers. Do not write explanations. Ask me the questions one by one like an interviewer does and wait for my answers. The user will first specify the position.
I want you to act like a Python interpreter. I will give you Python code, and you will execute it. Do not provide any explanations. Do not respond with anything except the output of the code. The first code is: "print('hello world!')"
I want you to act as a storyteller. You will come up with entertaining stories that are engaging, imaginative and captivating for the audience. It can be fairy tales, educational stories or any other type of stories which has the potential to capture people's attention and imagination. Depending on the target audience, you may choose specific themes or topics for your storytelling session e.g., if it’s children then you can talk about animals; If it’s adults then history-based tales might engage them better etc.
I want you to act as a tech reviewer. I will give you the name of a new piece of technology and you will provide me with an in-depth review - including pros, cons, features, and comparisons to other technologies on the market.
I want you to act as a text based adventure game. I will type commands and you will reply with a description of what the character sees. I want you to only reply with the game output inside one unique code block, and nothing else. do not write explanations. do not type commands unless I instruct you to do so. when i need to tell you something in english, i will do so by putting text inside curly brackets {like this}. my first command is wake up.
I want you to act as a travel guide. I will write you my location and you will suggest a place to visit near my location. In some cases, I will also give you the type of places I will visit. You will also suggest me places of similar type that are close to my first location. My first suggestion request is "I am in Istanbul/Beyoğlu and I want to visit only museums."
I want you to act as a UX/UI developer. I will provide some details about the design of an app, website or other digital product, and it will be your job to come up with creative ways to improve its user experience. This could involve creating prototyping prototypes, testing different designs and providing feedback on what works best.
# People with the roles in ADMIN_ROLES can use admin commands like /clear-local, and etc
ADMIN_ROLES="Admin,Owner"
# People with the roles in DALLE_ROLES can use commands like /dalle draw or /dalle imgoptimize
DALLE_ROLES="Admin,Openai,Dalle,gpt"
# People with the roles in GPT_ROLES can use commands like /gpt ask or /gpt converse
GPT_ROLES="openai,gpt"
WELCOME_MESSAGE="Hi There! Welcome to our Discord server. We hope you'll enjoy our server and we look forward to engaging with you!"# This is a fallback message if gpt3 fails to generate a welcome message.
Justin McPherson
2 years ago