Add AI functionality and full English documentation

Author: AlexTkDev

.env.example

@@ -1,2 +1,3 @@
 BOT_TOKEN=your_telegram_bot_token
 OPENAI_API_KEY=your_openai_api_key
+GROQ_API_KEY=your_groq_api_key

.pylintrc

@@ -4,10 +4,16 @@ ignore=venv,.venv
 
 [MESSAGES CONTROL]
 # Disable warnings about missing docstrings
+# and other project-specific disables
+# Existing disables:
 disable=missing-module-docstring,
         missing-function-docstring,
         too-few-public-methods,
-        missing-final-newline
+        missing-final-newline,
+        import-outside-toplevel,
+        redefined-outer-name,
+        broad-exception-caught,
+        too-many-return-statements
 
 [FORMAT]
 # Max line length

README.md

@@ -6,12 +6,54 @@
 
 ## 📌 Features
 
-- 📚 Generate personalized study plans (LLM/OpenAI)
+- 📚 Generate personalized study plans (LLM/OpenAI, fallback to Groq)
 - 📝 Export study plans to PDF/TXT
 - ⏰ Send reminders as Telegram messages for each study step
 - 🗄️ Store data using TinyDB
 - 📊 Python 3.10–3.13 support
 
+## 🆕 Groq Fallback Integration
+
+If the OpenAI API is unavailable, out of quota, or not configured, the bot will automatically use [Groq](https://groq.com/) as a fallback LLM provider. Groq offers:
+
+- **Fast and reliable generations**
+- **No strict quotas for most users**
+- **OpenAI-compatible API**
+- **Always available fallback**
+
+If both OpenAI and Groq are unavailable, the bot falls back to a local plan generator (simple stub).
+
+### How it works
+
+1. **Primary:** OpenAI API (if `OPENAI_API_KEY` is set and quota is available)
+2. **Fallback:** [Groq](https://groq.com/) (if `GROQ_API_KEY` is set)
+3. **Last resort:** Local plan generator (simple stub)
+
+### How to use Groq
+
+1. Register and get your API key at [Groq](https://console.groq.com/keys).
+2. Add the following line to your `.env` file:
+   ```
+   GROQ_API_KEY=your_groq_api_key
+   ```
+3. (Optional) Add to `.env.example` for documentation:
+   ```
+   GROQ_API_KEY=your_groq_api_key
+   ```
+
+No other changes are needed — the bot will automatically use Groq if OpenAI is not available.
+
+## 🌐 Multilingual Support
+
+You can now choose your preferred language for all bot interactions! Use the `/language` command to select from English, Russian, or Spanish. The bot will automatically translate all responses, study plans, and reminders to your chosen language using LLMs (OpenAI or Groq). If translation is not possible, the original English text will be sent.
+
+**Supported languages:**
+- English (`en`)
+- Русский (`ru`)
+- Español (`es`)
+
+Translations are performed in real time using the same LLMs that generate study plans, ensuring high-quality and context-aware results.
+
 ## 🚀 Quick Start
 
 ### 1. Clone the project
@@ -32,6 +74,7 @@ Create a `.env` file in the root directory or rename `.env.example` to `.env` an
 ```bash
 BOT_TOKEN=your_telegram_bot_token
 OPENAI_API_KEY=your_openai_api_key
+GROQ_API_KEY=your_groq_api_key
 ```
 
 ### 4. Run the bot
@@ -70,7 +113,7 @@ EduPlannerBotAI/
 │   ├── start.py            # /start and greeting
 │   └── planner.py          # Study plan generation flow
 ├── services/               # Core logic and helper functions
-│   ├── llm.py              # OpenAI integration
+│   ├── llm.py              # OpenAI and Groq integration
 │   ├── pdf.py              # PDF export
 │   ├── txt.py              # TXT export
 │   ├── reminders.py        # Reminder simulation
@@ -87,6 +130,7 @@ EduPlannerBotAI/
 | Python 3.10+  | Programming language                   |
 | aiogram 3.x   | Telegram Bot Framework                 |
 | OpenAI API    | LLM for text generation                |
+| Groq API      | Fallback LLM provider                  |
 | fpdf          | PDF file generation                    |
 | TinyDB        | Lightweight NoSQL database             |
 | python-dotenv | Environment variable management        |
@@ -98,14 +142,28 @@ EduPlannerBotAI/
 - Python version compatibility: 3.10, 3.11, 3.12, 3.13
 - Custom `.pylintrc` configuration
 
-## 📝 Release 2.0.0 Highlights
+## 📝 Release 2.1.0 Highlights
 
 - Full English codebase (comments, docstrings, messages)
 - PEP8 and pylint compliance (score 10/10)
 - Full test coverage for all services and handlers
 - Improved error handling and async file operations
+- Multilingual support with LLM-based translation
+- Telegram reminders for study plans
+- **Groq fallback LLM integration**
+- **Arli AI fully removed**
 - Ready for open source and team development
 
+## 🆕 2025 Updates
+
+- All messages and buttons always contain non-empty text, eliminating Telegram errors (Bad Request: text must be non-empty).
+- Keyboards (format selection, next actions) are always accompanied by a short message to ensure buttons are displayed reliably.
+- Language selection buttons are not translated, so the language filter works correctly.
+- The entire bot scenario is fully localized: all messages, buttons, and files are translated to the user's selected language.
+- The logic is maximally simplified, with no unnecessary conditions; all stages work reliably and predictably.
+- Fallback to Groq is supported for generation and translation if OpenAI is unavailable.
+- The project is ready for use and open for extension.
+
 ## ⚠️ Handling Frequent 429 Errors
 
 If you're experiencing too many `429 Too Many Requests` errors, consider the following:

bot.py

@@ -8,7 +8,7 @@
 from aiogram.client.default import DefaultBotProperties
 
 from config import TOKEN
-from handlers import start, planner
+from handlers import start, planner, language
 
 # Create necessary directories
 os.makedirs("plans", exist_ok=True)
@@ -40,6 +40,7 @@
 # Register handlers
 dp.include_router(start.router)
 dp.include_router(planner.router)
+dp.include_router(language.router)
 
 if __name__ == "__main__":
 

config.py

@@ -5,3 +5,4 @@
 
 TOKEN = os.getenv("BOT_TOKEN")
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")

handlers/__init__.py

@@ -1 +1,2 @@
 from . import start, planner
+from . import language

handlers/language.py

@@ -0,0 +1,49 @@
+from aiogram import Router, types, F
+from aiogram.filters import Command
+from aiogram.fsm.context import FSMContext
+from services.db import set_user_language, get_user_language
+from services.llm import translate_text
+from handlers.planner import send_translated
+
+router = Router()
+
+LANGUAGES = {
+    "en": "English",
+    "ru": "Русский",
+    "es": "Español",
+}
+
+@router.message(Command("language"))
+async def choose_language(message: types.Message, state: FSMContext):
+    user_id = message.from_user.id if message.from_user else 0
+    user_lang = get_user_language(user_id) or "en"
+    # Do not translate language selection buttons so the filter works correctly
+    keyboard = types.ReplyKeyboardMarkup(
+        keyboard=[
+            [types.KeyboardButton(text=lang_name)] for lang_name in LANGUAGES.values()
+        ],
+        resize_keyboard=True,
+        one_time_keyboard=True,
+    )
+    prompt = await translate_text("Choose your language / Выберите язык:", user_lang)
+    await send_translated(message, prompt)
+    await message.answer(prompt, reply_markup=keyboard)
+    await state.set_state("waiting_for_language")
+
+@router.message(F.text.in_(LANGUAGES.values()))
+async def set_language(message: types.Message, state: FSMContext):
+    lang_code = [k for k, v in LANGUAGES.items() if v == message.text][0]
+    user_id = message.from_user.id if message.from_user else 0
+    set_user_language(user_id, lang_code)
+    lang_set_msg = await translate_text(f"Language set to {LANGUAGES[lang_code]}", lang_code)
+    await send_translated(message, lang_set_msg)
+    await message.answer(lang_set_msg, reply_markup=types.ReplyKeyboardRemove())
+    await state.clear()
+    # Send greeting and next-step instruction in the chosen language
+    greeting = (
+        "👋 Hi! I am a bot for creating study plans.\n"
+        "Use the /plan command to start creating a study plan."
+    )
+    if lang_code != "en":
+        greeting = await translate_text(greeting, lang_code)
+    await send_translated(message, greeting)