Switch to GPT-3.5 engine

README.md

@@ -1,24 +1,33 @@
-# ChatGPT Telegram Bot
+# ChatGPT Telegram Bot (**fast** and **no limits**)
+We all love [chat.openai.com](https://chat.openai.com), but...
+
+It's TERRIBLY laggy, has daily limits, and is only accessible through an archaic web interface.
+
+This repo is ChatGPT re-created with GPT-3.5 LLM as Telegram Bot. **And it works great.**
+
+## Features
+- Low latency replies (it usually takes about 3-5 seconds) 
+- No request limits
+- Code highlighting
+- `/retry` command to regenerate last bot answer
+- Control of allowed Telegram users
+- *Next up*: Different chat modes (code writing helper, therapist, movie expert, etc.)
 
 ## Setup
-1. Get your ChatGPT session token. You can find it in [chat.openai.com](https://chat.openai.com) cookies (key: `"__Secure-next-auth.session-token"`)
+1. Get your [OpenAI API](https://openai.com/api/) key
 
 2. Get your Telegram bot token from [@BotFather](https://t.me/BotFather)
 
-3. Edit `config.env.example` to add your tokens. It looks like this:
+3. Edit `config.example.yml` to add your tokens and raname it to `config.yml`:
 ```bash
-TELEGRAM_TOKEN="<YOU TELEGRAM BOT TOKE>"
-CHATGPT_SESSION_TOKEN="<YOUR CHATGPT SESSION ID>"
-ALLOWED_TELEGRAM_USERNAMES="<@USERNAME>"
+mv config.example.yml config.yml
 ```
 
-4. Rename `config.env.example` to `config.env`:
-```bash
-mv config.env.example config.env
-```
-
-## Run
+🔥 And now **run**:
 
 ```bash
 docker compose up --build
 ```
+
+## References
+1. [*Build ChatGPT from GPT-3*](https://learnprompting.org/docs/applied_prompting/build_chatgpt)