Merge branch 'main' into tts-support

.env.example

@@ -23,6 +23,7 @@ ALLOWED_TELEGRAM_USER_IDS=USER_ID_1,USER_ID_2
 # ENABLE_TRANSCRIPTION=true
 # PROXY=http://localhost:8080
 # OPENAI_MODEL=gpt-3.5-turbo
+# OPENAI_API_BASE=https://example.com/v1/
 # ASSISTANT_PROMPT="You are a helpful assistant."
 # SHOW_USAGE=false
 # STREAM=true
@@ -35,7 +36,11 @@ ALLOWED_TELEGRAM_USER_IDS=USER_ID_1,USER_ID_2
 # TEMPERATURE=1.0
 # PRESENCE_PENALTY=0.0
 # FREQUENCY_PENALTY=0.0
-# IMAGE_SIZE=512x512
+# IMAGE_MODEL=dall-e-3
+# IMAGE_QUALITY=hd
+# IMAGE_STYLE=natural
+# IMAGE_SIZE=1024x1024
+# IMAGE_FORMAT=document
 # GROUP_TRIGGER_KEYWORD=""
 # IGNORE_GROUP_TRANSCRIPTIONS=true
 # TTS_MODEL="tts-1"

README.md

@@ -30,12 +30,14 @@ A [Telegram bot](https://core.telegram.org/bots/api) that integrates with OpenAI
 - [x] GPT-4 support
   - If you have access to the GPT-4 API, simply change the `OPENAI_MODEL` parameter to `gpt-4`
 - [x] Localized bot language
-  - Available languages :gb: :de: :ru: :tr: :it: :finland: :es: :indonesia: :netherlands: :cn: :taiwan: :vietnam: :iran: :brazil: :ukraine: :malaysia:
+  - Available languages :gb: :de: :ru: :tr: :it: :finland: :es: :indonesia: :netherlands: :cn: :taiwan: :vietnam: :iran: :brazil: :ukraine: :malaysia: :uzbekistan:
 - [x] Improved inline queries support for group and private chats - by [@bugfloyd](https://github.com/bugfloyd)
   - To use this feature, enable inline queries for your bot in BotFather via the `/setinline` [command](https://core.telegram.org/bots/inline)
-- [x] (NEW!) Support *new models* [announced on June 13, 2023](https://openai.com/blog/function-calling-and-other-api-updates)
+- [x] Support *new models* [announced on June 13, 2023](https://openai.com/blog/function-calling-and-other-api-updates)
-- [x] (NEW!) Support *functions* (plugins) to extend the bot's functionality with 3rd party services
+- [x] Support *functions* (plugins) to extend the bot's functionality with 3rd party services
   - Weather, Spotify, Web search, text-to-speech and more. See [here](#available-plugins) for a list of available plugins
+- [x] Support unofficial OpenAI-compatible APIs - by [@kristaller486](https://github.com/kristaller486)
+- [x] (NEW!) Support GPT-4 Turbo and DALL·E 3 [announced on November 6, 2023](https://openai.com/blog/new-models-and-developer-products-announced-at-devday) - by by [@AlexHTW](https://github.com/AlexHTW)
 
 ## Additional features - help needed!
 If you'd like to help, check out the [issues](https://github.com/n3d1117/chatgpt-telegram-bot/issues) section and contribute!  
@@ -84,6 +86,7 @@ Check out the [Budget Manual](https://github.com/n3d1117/chatgpt-telegram-bot/di
 | `ENABLE_TTS_GENERATION`             | Whether to enable text to speech generation via the `/tts`                                                                                                                                                                                                              | `true`                              |
 | `PROXY`                            | Proxy to be used for OpenAI and Telegram bot (e.g. `http://localhost:8080`)                                                                                                                                                                                           | -                                   |
 | `OPENAI_MODEL`                     | The OpenAI model to use for generating responses. You can find all available models [here](https://platform.openai.com/docs/models/)                                                                                                                                  | `gpt-3.5-turbo`                     |
+| `OPENAI_API_BASE`                  | Endpoint URL for unofficial OpenAI-compatible APIs (e.g., LocalAI or text-generation-webui)                                                                                                                                                                           | Default OpenAI API URL              |
 | `ASSISTANT_PROMPT`                 | A system message that sets the tone and controls the behavior of the assistant                                                                                                                                                                                        | `You are a helpful assistant.`      |
 | `SHOW_USAGE`                       | Whether to show OpenAI token usage information after each response                                                                                                                                                                                                    | `false`                             |
 | `STREAM`                           | Whether to stream responses. **Note**: incompatible, if enabled, with `N_CHOICES` higher than 1                                                                                                                                                                       | `true`                              |
@@ -96,10 +99,14 @@ Check out the [Budget Manual](https://github.com/n3d1117/chatgpt-telegram-bot/di
 | `TEMPERATURE`                      | Number between 0 and 2. Higher values will make the output more random                                                                                                                                                                                                | `1.0`                               |
 | `PRESENCE_PENALTY`                 | Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far                                                                                                                                                      | `0.0`                               |
 | `FREQUENCY_PENALTY`                | Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far                                                                                                                                                 | `0.0`                               |
-| `IMAGE_SIZE`                       | The DALL·E generated image size. Allowed values: `256x256`, `512x512` or `1024x1024`                                                                                                                                                                                  | `512x512`                           |
+| `IMAGE_FORMAT`                     | The Telegram image receive mode. Allowed values: `document` or `photo`                                                                                                                                                                                                | `photo`                             |
+| `IMAGE_MODEL`                      | The DALL·E model to be used. Available models: `dall-e-2` and `dall-e-3`, find current available models [here](https://platform.openai.com/docs/models/dall-e)                                                                                                        | `dall-e-2`                          |
+| `IMAGE_QUALITY`                    | Quality of DALL·E images, only available for `dall-e-3`-model. Possible options: `standard` or `hd`, beware of [pricing differences](https://openai.com/pricing#image-models).                                                                                        | `standard`                          |
+| `IMAGE_STYLE`                      | Style for DALL·E image generation, only available for `dall-e-3`-model. Possible options: `vivid` or `natural`. Check availbe styles [here](https://platform.openai.com/docs/api-reference/images/create).                                                            | `vivid`                             |
+| `IMAGE_SIZE`                       | The DALL·E generated image size. Must be `256x256`, `512x512`, or `1024x1024` for dall-e-2. Must be `1024x1024` for dall-e-3 models.                                                                                                                                  | `512x512`                           |
 | `GROUP_TRIGGER_KEYWORD`            | If set, the bot in group chats will only respond to messages that start with this keyword                                                                                                                                                                             | -                                   |
 | `IGNORE_GROUP_TRANSCRIPTIONS`      | If set to true, the bot will not process transcriptions in group chats                                                                                                                                                                                                | `true`                              |
-| `BOT_LANGUAGE`                     | Language of general bot messages. Currently available: `en`, `de`, `ru`, `tr`, `it`, `fi`, `es`, `id`, `nl`, `zh-cn`, `zh-tw`, `vi`, `fa`, `pt-br`, `uk`, `ms`.  [Contribute with additional translations](https://github.com/n3d1117/chatgpt-telegram-bot/discussions/219) | `en`                                |
+| `BOT_LANGUAGE`                     | Language of general bot messages. Currently available: `en`, `de`, `ru`, `tr`, `it`, `fi`, `es`, `id`, `nl`, `zh-cn`, `zh-tw`, `vi`, `fa`, `pt-br`, `uk`, `ms`, `uz`.  [Contribute with additional translations](https://github.com/n3d1117/chatgpt-telegram-bot/discussions/219) | `en`                                |
 | `WHISPER_PROMPT`                     | To improve the accuracy of Whisper's transcription service, especially for specific names or terms, you can set up a custom message.  [Speech to text - Prompting](https://platform.openai.com/docs/guides/speech-to-text/prompting) | `-`                                |
 | `TTS_VOICE`                       | The Text to Speech voice to use. Allowed values: `alloy`, `echo`, `fable`, `onyx`, `nova`, or `shimmer`                                                                                                                                                                                  | `alloy`                           |
 | `TTS_MODEL`                       | The Text to Speech model to use. Allowed values: `tts-1` or `tts-1-hd`                                                                                                                                                                                  | `tts-1`                           |

bot/main.py

@@ -41,6 +41,9 @@ def main():
         'max_tokens': int(os.environ.get('MAX_TOKENS', max_tokens_default)),
         'n_choices': int(os.environ.get('N_CHOICES', 1)),
         'temperature': float(os.environ.get('TEMPERATURE', 1.0)),
+        'image_model': os.environ.get('IMAGE_MODEL', 'dall-e-2'),
+        'image_quality': os.environ.get('IMAGE_QUALITY', 'standard'),
+        'image_style': os.environ.get('IMAGE_STYLE', 'vivid'),
         'image_size': os.environ.get('IMAGE_SIZE', '512x512'),
         'model': model,
         'enable_functions': os.environ.get('ENABLE_FUNCTIONS', str(functions_available)).lower() == 'true',
@@ -84,6 +87,7 @@ def main():
         'group_trigger_keyword': os.environ.get('GROUP_TRIGGER_KEYWORD', ''),
         'token_price': float(os.environ.get('TOKEN_PRICE', 0.002)),
         'image_prices': [float(i) for i in os.environ.get('IMAGE_PRICES', "0.016,0.018,0.02").split(",")],
+        'image_receive_mode': os.environ.get('IMAGE_FORMAT', "photo"),
         'tts_model': os.environ.get('TTS_MODEL', 'tts-1'),
         'tts_prices': [float(i) for i in os.environ.get('TTS_PRICES', "0.015,0.030").split(",")],
         'transcription_price': float(os.environ.get('TRANSCRIPTION_PRICE', 0.006)),

bot/openai_helper.py

@@ -21,10 +21,11 @@ from plugin_manager import PluginManager
 
 # Models can be found here: https://platform.openai.com/docs/models/overview
 GPT_3_MODELS = ("gpt-3.5-turbo", "gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613")
-GPT_3_16K_MODELS = ("gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613")
+GPT_3_16K_MODELS = ("gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-1106")
 GPT_4_MODELS = ("gpt-4", "gpt-4-0314", "gpt-4-0613")
 GPT_4_32K_MODELS = ("gpt-4-32k", "gpt-4-32k-0314", "gpt-4-32k-0613")
-GPT_ALL_MODELS = GPT_3_MODELS + GPT_3_16K_MODELS + GPT_4_MODELS + GPT_4_32K_MODELS
+GPT_4_128K_MODELS = ("gpt-4-1106-preview",)
+GPT_ALL_MODELS = GPT_3_MODELS + GPT_3_16K_MODELS + GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_128K_MODELS
 
 
 def default_max_tokens(model: str) -> int:
@@ -38,10 +39,14 @@ def default_max_tokens(model: str) -> int:
         return base
     elif model in GPT_4_MODELS:
         return base * 2
-    elif model in GPT_3_16K_MODELS:
+    elif model in GPT_3_16K_MODELS:    
+        if model == "gpt-3.5-turbo-1106":
+            return 4096
         return base * 4
     elif model in GPT_4_32K_MODELS:
         return base * 8
+    elif model in GPT_4_128K_MODELS:
+        return 4096
 
 
 def are_functions_available(model: str) -> bool:
@@ -52,7 +57,7 @@ def are_functions_available(model: str) -> bool:
     if model in ("gpt-3.5-turbo-0301", "gpt-4-0314", "gpt-4-32k-0314"):
         return False
     # Stable models will be updated to support functions on June 27, 2023
-    if model in ("gpt-3.5-turbo", "gpt-4", "gpt-4-32k"):
+    if model in ("gpt-3.5-turbo", "gpt-3.5-turbo-1106", "gpt-4", "gpt-4-32k","gpt-4-1106-preview"):
         return datetime.date.today() > datetime.date(2023, 6, 27)
     return True
 
@@ -321,6 +326,9 @@ class OpenAIHelper:
             response = await self.client.images.generate(
                 prompt=prompt,
                 n=1,
+                model=self.config['image_model'],
+                quality=self.config['image_quality'],
+                style=self.config['image_style'],
                 size=self.config['image_size']
             )
 
@@ -421,7 +429,7 @@ class OpenAIHelper:
             messages=messages,
             temperature=0.4
         )
-        return response.choices[0]['message']['content']
+        return response.choices[0].message.content
 
     def __max_model_tokens(self):
         base = 4096
@@ -433,6 +441,8 @@ class OpenAIHelper:
             return base * 2
         if self.config['model'] in GPT_4_32K_MODELS:
             return base * 8
+        if self.config['model'] in GPT_4_128K_MODELS:
+            return base * 31
         raise NotImplementedError(
             f"Max tokens for model {self.config['model']} is not implemented yet."
         )
@@ -453,7 +463,7 @@ class OpenAIHelper:
         if model in GPT_3_MODELS + GPT_3_16K_MODELS:
             tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
             tokens_per_name = -1  # if there's a name, the role is omitted
-        elif model in GPT_4_MODELS + GPT_4_32K_MODELS:
+        elif model in GPT_4_MODELS + GPT_4_32K_MODELS + GPT_4_128K_MODELS:
             tokens_per_message = 3
             tokens_per_name = 1
         else:

bot/telegram_bot.py

@@ -242,10 +242,18 @@ class ChatGPTTelegramBot:
         async def _generate():
             try:
                 image_url, image_size = await self.openai.generate_image(prompt=image_query)
-                await update.effective_message.reply_photo(
+                if self.config['image_receive_mode'] == 'photo':
-                    reply_to_message_id=get_reply_to_message_id(self.config, update),
+                    await update.effective_message.reply_photo(
-                    photo=image_url
+                        reply_to_message_id=get_reply_to_message_id(self.config, update),
-                )
+                        photo=image_url
+                    )
+                elif self.config['image_receive_mode'] == 'document':
+                    await update.effective_message.reply_document(
+                        reply_to_message_id=get_reply_to_message_id(self.config, update),
+                        document=image_url
+                    )
+                else:
+                    raise Exception(f"env variable IMAGE_RECEIVE_MODE has invalid value {self.config['image_receive_mode']}")
                 # add image request to users usage tracker
                 user_id = update.message.from_user.id
                 self.usage[user_id].add_image_request(image_size, self.config['image_prices'])

requirements.txt

@@ -1,7 +1,7 @@
 python-dotenv~=1.0.0
 pydub~=0.25.1
 tiktoken==0.5.1
-openai==1.1.1
+openai==1.3.3
 python-telegram-bot==20.3
 requests~=2.31.0
 tenacity==8.2.2
@@ -10,4 +10,4 @@ duckduckgo_search~=3.8.3
 spotipy~=2.23.0
 pytube~=15.0.0
 gtts~=2.3.2
-whois~=0.9.27
+whois~=0.9.27

translations.json

@@ -690,5 +690,48 @@
         "ask_chatgpt":"Tanya ChatGPT",
         "loading":"Memuatkan...",
         "function_unavailable_in_inline_mode": "Fungsi ini tidak tersedia dalam mod sebaris"
+    },
+    "uz": {
+        "help_description": "Yordam xabarini ko'rsatish",
+        "reset_description": "Suhbatni qayta boshlang. Agar xohlasangiz, umumiy ko'rsatmalar bering (masalan, /reset siz foydali yordamchisiz)",
+        "image_description": "Tasvirni so'rov bo'yicha yaratish (masalan, /image mushuk)",
+        "stats_description": "Hozirgi foydalanilgan statistikani olish",
+        "resend_description": "Oxirgi xabarni qayta yuborish",
+        "chat_description": "Bot bilan suxbat!",
+        "disallowed": "Kechirasiz, sizga bu botdan foydalanish taqiqlangan. Siz manba kodini tekshirishingiz mumkin https://github.com/n3d1117/chatgpt-telegram-bot",
+        "budget_limit": "Kechirasiz, siz foydalanish chegarasiga yetdingiz.",
+        "help_text": ["Men ChatGPT botman, men bilan gaplashing!", "Menga ovozli xabar yoki fayl yuboring, men uni siz uchun transkripsiya qilaman", "Ochiq manba: https://github.com/n3d1117/chatgpt-telegram-bot"],
+        "stats_conversation": ["Hozirgi suhbat", "tarixdagi chat xabarlari", "tarixdagi suhbat tokenlari"],
+        "usage_today": "Bugungi foydalanish",
+        "usage_month": "Bu oydagi foydalanish",
+        "stats_tokens": "tokenlar",
+        "stats_images": "yaratilgan tasvirlar",
+        "stats_transcribe": ["minutlar va", "soniyalar transkripsiya qilingan"],
+        "stats_total": "💰 Jami miqdor $",
+        "stats_budget": "Qolgan budjetingiz",
+        "monthly": " bu oy uchun",
+        "daily": " bugun uchun",
+        "all-time": "",
+        "stats_openai": "Shu oyda OpenAI hisobingizdan to'lov amalga oshirildi $",
+        "resend_failed": "Sizda qayta yuborish uchun hech narsa yo'q",
+        "reset_done": "Bajarildi!",
+        "image_no_prompt": "Iltimos, so'rov yozing! (masalan, /image mushuk)",
+        "image_fail": "Tasvir yaratish amalga oshmadi",
+        "media_download_fail": ["Audio faylni yuklab olish amalga oshmadi", "Fayl hajmi katta emasligiga ishonch hosil qiling. (max 20MB)"],
+        "media_type_fail": "Qo'llab-quvvatlanmaydigan fayl turi",
+        "transcript": "Transkript",
+        "answer": "Javob",
+        "transcribe_fail": "Matnni transkripsiya qilib bo'lmadi",
+        "chat_fail": "Javob olish amalga oshmadi",
+        "prompt": "so'rov",
+        "completion": "yakunlash",
+        "openai_rate_limit": "OpenAI ta'rif chegarasidan oshib ketdi",
+        "openai_invalid": "OpenAI So'rov noto'g'ri",
+        "error": "Xatolik yuz berdi",
+        "try_again": "Birozdan keyin qayta urinib ko'ring",
+        "answer_with_chatgpt": "ChatGPT bilan javob berish",
+        "ask_chatgpt": "ChatGPTdan so'rash",
+        "loading": "Yuklanmoqda...",
+        "function_unavailable_in_inline_mode": "Bu funksiya inline rejimida mavjud emas"
     }
 }