update docs

README.md

@@ -2,6 +2,11 @@
 
 _Chatbots for Matrix._
 
+This bot supports OpenAI, Anthropic, and locally hosted models that use an OpenAI-compatible endpoint. It can run multiple different models using
+different triggers, such as `!c4` for GPT4 and `!ca` for Anthropic, all through the same bot.
+
+<br>
+
 ## Install
 
 1. Install requirements:
@@ -9,36 +14,32 @@ _Chatbots for Matrix._
     sudo apt install libolm-dev gcc python3-dev
     pip install -r requirements.txt
     ```
-2. Copy `config.sample.yaml` to `config.yaml` and fill it out with your bot's Matrix auth and your API key(s).
+2. Copy `config.sample.yaml` to `config.yaml` and fill it out with the bot's Matrix authentication and your OpenAI and/or Anthropic API keys.
+3. Start the bot with `python3 main.py`
+
+[Pantalaimon](https://github.com/matrix-org/pantalaimon) is **required** for the bot to be able to talk in encrypted rooms.
+
+I included a sample Systemd service (`matrixgpt.service`).
 
-[Pantalaimon](https://github.com/matrix-org/pantalaimon) is **required** for the bot to be able to talk in encrypted
-rooms.
 
-I included a sample Systemd service.
 
 ## Use
 
-Invite your bot to a room.
+First, invite your bot to a room. Then you can start a chat by prefixing your message with your trigger (for example, `!c hello!`). The bot will create a thread when it replies. You don't need to use the trigger in the thread.
-
-Start a chat by prefixing your message with your trigger (for example, `!c`). The bot will create a thread when it
-replies to you and you don't need to use the trigger in the thread.
-
-Don't try to use two bots in the same thread.
-
-You can DM a bot for a private chat. Don't use the trigger prefix in a DM.
-
-The bot will move its read marker when a new message is sent in the room.
-
-The bot can give helpful reactions:
-
-- 🚫 means that the user is not allowed to chat with the bot.
-- ❌ means the bot encountered an exception. The bot restarts when it encounters an exception which means it will not be
-  able to respond for a short time after this reaction.
-- ❌ 🔐 means there was a decryption failure.
 
 Use `!matrixgpt` to view the bot's help. The bot also responds to `!bots`.
 
-## Encryption
+<br>
 
-This bot supports encryption. I recommend using [Pantalaimon](https://github.com/matrix-org/pantalaimon/) to manage
+- Don't try to use two bots in the same thread.
-encryption keys as the built-in solution is a little janky and may be unreliable.
+- You can DM a bot for a private chat. Don't use the trigger prefix in a DM.
+- The bot will move its read marker when a new message is sent in the room.
+
+<br>
+
+The bot can give helpful reactions:
+
+- 🚫 means permission denied (not allowed to chat with the bot).
+- 🕒 means the API timed out.
+- ❌ means the bot encountered an exception.
+- ❌ 🔐 means there was a decryption failure.

config.sample.yaml

@@ -40,6 +40,9 @@ allowed_to_invite:
 response_timeout:    120
 
 command:
+  # Define what models respond to what trigger.
+  # Try adding multiple triggers!
+
   # What triggers this model.
   - trigger:         '!c4'
 

matrix_gpt/config.py

@@ -83,6 +83,7 @@ class ConfigManager:
         if not self._config.config['openai']['api_key'] and not self._config.config['anthropic']['api_key']:
             raise SchemeValidationError('You need an OpenAI or Anthropic API key')
         self._parsed_config = self._merge_in_list_defaults()
+        # TODO: make sure there aren't duplicate triggers
         self._command_prefixes = self._generate_command_prefixes()
 
     def _merge_in_list_defaults(self):