gpt4free

公开

关注 0 Fork 0 Star 1

XFEstudio/gpt4free

Add support for multiple AI models and enhance agent functionality in Blackbox provider (#2484)

* refactor(g4f/Provider/Airforce.py): improve model handling and filtering - Add hidden_models set to exclude specific models - Add evil alias for uncensored model handling - Extend filtering for model-specific response tokens - Add response buffering for streamed content - Update model fetching with error handling * refactor(g4f/Provider/Blackbox.py): improve caching and model handling - Add caching system for validated values with file-based storage - Rename 'flux' model to 'ImageGeneration' and update references - Add temperature, top_p and max_tokens parameters to generator - Simplify HTTP headers and remove redundant options - Add model alias mapping for ImageGeneration - Add file system utilities for cache management * feat(g4f/Provider/RobocodersAPI.py): add caching and error handling - Add file-based caching system for access tokens and sessions - Add robust error handling with specific error messages - Add automatic dialog continuation on resource limits - Add HTML parsing with BeautifulSoup for token extraction - Add debug logging for error tracking - Add timeout configuration for API requests * refactor(g4f/Provider/DarkAI.py): update DarkAI default model and aliases - Change default model from llama-3-405b to llama-3-70b - Remove llama-3-405b from supported models list - Remove llama-3.1-405b from model aliases * feat(g4f/Provider/Blackbox2.py): add image generation support - Add image model 'flux' with dedicated API endpoint - Refactor generator to support both text and image outputs - Extract headers into reusable static method - Add type hints for AsyncGenerator return type - Split generation logic into _generate_text and _generate_image methods - Add ImageResponse handling for image generation results BREAKING CHANGE: create_async_generator now returns AsyncGenerator instead of AsyncResult * refactor(g4f/Provider/ChatGptEs.py): update ChatGptEs model configuration - Update models list to include gpt-3.5-turbo - Remove chatgpt-4o-latest from supported models - Remove model_aliases mapping for gpt-4o * feat(g4f/Provider/DeepInfraChat.py): add Accept-Language header support - Add Accept-Language header for internationalization - Maintain existing header configuration - Improve request compatibility with language preferences * refactor(g4f/Provider/needs_auth/Gemini.py): add ProviderModelMixin inheritance - Add ProviderModelMixin to class inheritance - Import ProviderModelMixin from base_provider - Move BaseConversation import to base_provider imports * refactor(g4f/Provider/Liaobots.py): update model details and aliases - Add version suffix to o1 model IDs - Update model aliases for o1-preview and o1-mini - Standardize version format across model definitions * refactor(g4f/Provider/PollinationsAI.py): enhance model support and generation - Split generation logic into dedicated image/text methods - Add additional text models including sur and claude - Add width/height parameters for image generation - Add model existence validation - Add hasattr checks for model lists initialization * chore(gitignore): add provider cache directory - Add g4f/Provider/.cache to gitignore patterns * refactor(g4f/Provider/ReplicateHome.py): update model configuration - Update default model to gemma-2b-it - Add default_image_model configuration - Remove llava-13b from supported models - Simplify request headers * feat(g4f/models.py): expand provider and model support - Add new providers DarkAI and PollinationsAI - Add new models for Mistral, Flux and image generation - Update provider lists for existing models - Add P1 and Evil models with experimental providers BREAKING CHANGE: Remove llava-13b model support * refactor(Airforce): Update type hint for split_message return - Change return type of from to for consistency with import. - Maintain overall functionality and structure of the class. - Ensure compatibility with type hinting standards in Python. * refactor(g4f/Provider/Airforce.py): Update type hint for split_message return - Change return type of 'split_message' from 'list[str]' to 'List[str]' for consistency with import. - Maintain overall functionality and structure of the 'Airforce' class. - Ensure compatibility with type hinting standards in Python. * feat(g4f/Provider/RobocodersAPI.py): Add support for optional BeautifulSoup dependency - Introduce a check for the BeautifulSoup library and handle its absence gracefully. - Raise a if BeautifulSoup is not installed, prompting the user to install it. - Remove direct import of BeautifulSoup to avoid import errors when the library is missing. * fix: Updating provider documentation and small fixes in providers * Disabled the provider (RobocodersAPI) * Fix: Conflicting file g4f/models.py * Update g4f/models.py g4f/Provider/Airforce.py * Update docs/providers-and-models.md g4f/models.py g4f/Provider/Airforce.py g4f/Provider/PollinationsAI.py * Update docs/providers-and-models.md * Update .gitignore * Update g4f/models.py * Update g4f/Provider/PollinationsAI.py * feat(g4f/Provider/Blackbox.py): add support for additional AI models and agents - Introduce new agent modes for Meta-Llama, Mistral, DeepSeek, DBRX, Qwen, and Nous-Hermes - Update model aliases to include newly supported models * Update (g4f/Provider/Blackbox.py) * Update (g4f/Provider/Blackbox.py) * feat(g4f/Provider/Blackbox2.py): add license key caching and validation - Add cache file management for license key persistence - Implement async license key extraction from JavaScript files - Add license key validation to text generation requests - Update type hints for async generators - Add error handling for cache file operations Breaking changes: - Text generation now requires license key validation --------- Co-authored-by: kqlio67 <>

ca2b609e

kqlio67 <166700875+kqlio67@users.noreply.github.com>

提交于 2024-12-15 22:27

父提交 8d8756f

代码差异

6 个文件 +166 -44

Modified docs/providers-and-models.md +6 -3

@@ -22,7 +22,7 @@ This document provides an overview of various AI providers and models, including

22 22 |----------|-------------|--------------|---------------|--------|--------|------|------|

23 23

|[api.airforce](https://api.airforce)|`g4f.Provider.Airforce`|`phi-2, gpt-4, gpt-4o-mini, gpt-4o, gpt-4-turbo, o1-mini, openchat-3.5, deepseek-coder, hermes-2-dpo, hermes-2-pro, openhermes-2.5, lfm-40b, german-7b, llama-2-7b, llama-3.1-70b, neural-7b, zephyr-7b, evil,`|`sdxl, flux-pro, flux, flux-realism, flux-anime, flux-3d, flux-disney, flux-pixel, flux-4o, any-dark, midjourney, dall-e-3`|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|❌+✔|

24 24

|[amigochat.io](https://amigochat.io/chat/)|`g4f.Provider.AmigoChat`|✔|✔|❌|✔|![Error](https://img.shields.io/badge/RateLimit-f48d37)|❌|

|[blackbox.ai](https://www.blackbox.ai)|`g4f.Provider.Blackbox`|`blackboxai, gpt-4, gpt-4o, gemini-pro, claude-3.5-sonnet, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b`|`flux`|`blackboxai, gpt-4o, gemini-pro, gemini-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b`|✔|![](https://img.shields.io/badge/Active-brightgreen)|❌|

|[blackbox.ai](https://www.blackbox.ai)|`g4f.Provider.Blackbox`|`blackboxai, gpt-4, gpt-4o, gemini-pro, claude-3.5-sonnet, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, llama-3.3-70b, mixtral-7b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo`|`flux`|`blackboxai, gpt-4o, gemini-pro, gemini-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b`|✔|![](https://img.shields.io/badge/Active-brightgreen)|❌|

26 26

|[blackbox.ai](https://www.blackbox.ai)|`g4f.Provider.Blackbox2`|`llama-3.1-70b`|`flux`|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|❌|

27 27

|[chatgpt.com](https://chatgpt.com)|`g4f.Provider.ChatGpt`|✔|❌|❌|✔|![Error](https://img.shields.io/badge/HTTPError-f48d37)|❌|

28 28

|[chatgpt.es](https://chatgpt.es)|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|✔|![](https://img.shields.io/badge/Active-brightgreen)|❌|

@@ -97,7 +97,8 @@ This document provides an overview of various AI providers and models, including

99 99

|llama-3.2-11b|Meta Llama|2+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)|

@@ -122,8 +123,9 @@ This document provides an overview of various AI providers and models, including

126 127 |pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|

@@ -137,6 +139,7 @@ This document provides an overview of various AI providers and models, including

139 141 |p1|PollinationsAI|1+ Providers|[]( )|

140 143 |evil|Evil Mode - Experimental|2+ Providers|[]( )|

141 144 |midijourney||1+ Providers|[]( )|

142 145 |turbo||1+ Providers|[]( )|

Modified docs/providers.md +3 -3

@@ -17,8 +17,8 @@

17 17 | -------- | ---- |

18 18 | **Website** | [blackbox.ai](https://www.blackbox.ai) |

19 19 | **Status** | ![Active](https://img.shields.io/badge/Active-brightgreen) |

| **Models** | gpt-4, gpt-4o, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gemini-pro, gemini-flash, claude-3.5-sonnet, blackboxai, blackboxai-pro (41)|

21 | **Image Models (Image Generation)** | flux |

| **Models** | gpt-4, gpt-4o, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gemini-pro, gemini-flash, claude-3.5-sonnet, blackboxai, blackboxai-pro, llama-3.3-70b, mixtral-7b, deepseek-chat, dbrx-instruct, llama-3.1-405b, qwq-32b, hermes-2-dpo (46)|

21 | **Image Models (Image Generation)** | flux (2)|

22 22 | **Vision (Image Upload)** | ✔️ |

23 23 | **Authentication** | ❌ |

24 24 | **Streaming** | ✔️ |

@@ -572,4 +572,4 @@

572 572

| Pollinations AI | `g4f.Provider.PollinationsAI` | flux, flux-realism, flux-cablyai, flux-anime, flux-3d, any-dark, flux-pro, turbo, midjourney, dall-e-3| ❌ | [pollinations.ai](https://pollinations.ai) |

574 574

| ReplicateHome | `g4f.Provider.ReplicateHome` | sd-3, sdxl, playground-v2.5| ❌ | [replicate.com](https://replicate.com) |

Modified g4f/Provider/Blackbox.py +36 -21

@@ -35,7 +35,14 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

35 35 userSelectedModel = ['gpt-4o', 'gemini-pro', 'claude-sonnet-3.5', 'blackboxai-pro']

36 36

37 37 agentMode = {

38 'ImageGeneration': {'mode': True, 'id': "ImageGenerationLV45LJp", 'name': "Image Generation"}

38 'ImageGeneration': {'mode': True, 'id': "ImageGenerationLV45LJp", 'name': "Image Generation"},

        'meta-llama/Llama-3.3-70B-Instruct-Turbo': {'mode': True, 'id': "meta-llama/Llama-3.3-70B-Instruct-Turbo", 'name': "Meta-Llama-3.3-70B-Instruct-Turbo"},

        'mistralai/Mistral-7B-Instruct-v0.2': {'mode': True, 'id': "mistralai/Mistral-7B-Instruct-v0.2", 'name': "Mistral-(7B)-Instruct-v0.2"},

        'deepseek-ai/deepseek-llm-67b-chat': {'mode': True, 'id': "deepseek-ai/deepseek-llm-67b-chat", 'name': "DeepSeek-LLM-Chat-(67B)"},

42 'databricks/dbrx-instruct': {'mode': True, 'id': "databricks/dbrx-instruct", 'name': "DBRX-Instruct"},

        'meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro': {'mode': True, 'id': "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro", 'name': "Meta-Llama-3.1-405B-Instruct-Turbo"}, #

44 'Qwen/QwQ-32B-Preview': {'mode': True, 'id': "Qwen/QwQ-32B-Preview", 'name': "Qwen-QwQ-32B-Preview"},

        'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO': {'mode': True, 'id': "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", 'name': "Nous-Hermes-2-Mixtral-8x7B-DPO"}

39 46 }

40 47

41 48 trendingAgentMode = {

@@ -102,6 +109,13 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

102 109 "gpt-4": "gpt-4o",

103 110 "gemini-flash": "gemini-1.5-flash",

104 111 "claude-3.5-sonnet": "claude-sonnet-3.5",

112 "llama-3.3-70b": "meta-llama/Llama-3.3-70B-Instruct-Turbo",

113 "mixtral-7b": "mistralai/Mistral-7B-Instruct-v0.2",

114 "deepseek-chat": "deepseek-ai/deepseek-llm-67b-chat",

115 "dbrx-instruct": "databricks/dbrx-instruct",

116 "llama-3.1-405b": "meta-llama/Meta-Llama-3.1-405B-Instruct-Lite-Pro",

117 "qwq-32b": "Qwen/QwQ-32B-Preview",

118 "hermes-2-dpo": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",

105 119

106 120 ### image ###

107 121 "flux": "ImageGeneration",

@@ -198,9 +212,9 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

198 212 proxy: str = None,

199 213 web_search: bool = False,

200 214 images: ImagesType = None,

201 top_p: float = 0.9,

202 temperature: float = 0.5,

203 max_tokens: int = 1024,

215 top_p: float = None,

216 temperature: float = None,

217 max_tokens: int = None,

204 218 **kwargs

205 219 ) -> AsyncResult:

206 220 message_id = cls.generate_id()

@@ -233,30 +247,31 @@ class Blackbox(AsyncGeneratorProvider, ProviderModelMixin):

233 247 }

234 248

235 249 data = {

236 "messages": messages,

237 "id": message_id,

238 "previewToken": None,

239 "userId": None,

240 "codeModelMode": True,

241 250 "agentMode": cls.agentMode.get(model, {}) if model in cls.agentMode else {},

242 "trendingAgentMode": cls.trendingAgentMode.get(model, {}) if model in cls.trendingAgentMode else {},

243 "isMicMode": False,

244 "userSystemPrompt": None,

245 "maxTokens": max_tokens,

246 "playgroundTopP": top_p,

247 "playgroundTemperature": temperature,

248 "isChromeExt": False,

249 "githubToken": None,

250 251 "clickedAnswer2": False,

251 252 "clickedAnswer3": False,

252 253 "clickedForceWebSearch": False,

253 "visitFromDelta": False,

254 "codeModelMode": True,

255 "deepSearchMode": False,

256 "githubToken": None,

257 "id": message_id,

258 "imageGenerationMode": False,

259 "isChromeExt": False,

260 "isMicMode": False,

261 "maxTokens": max_tokens,

262 "messages": messages,

254 263 "mobileClient": False,

264 "playgroundTemperature": temperature,

265 "playgroundTopP": top_p,

266 "previewToken": None,

267 "trendingAgentMode": cls.trendingAgentMode.get(model, {}) if model in cls.trendingAgentMode else {},

268 "userId": None,

255 269 "userSelectedModel": model if model in cls.userSelectedModel else None,

256 "webSearchMode": web_search,

270 "userSystemPrompt": None,

257 271 "validated": validated_value,

258 "imageGenerationMode": False,

259 "webSearchModePrompt": web_search

272 "visitFromDelta": False,

273 "webSearchModePrompt": False,

274 "webSearchMode": web_search

260 275 }

261 276

262 277 async with ClientSession(headers=headers) as session:

Modified g4f/Provider/Blackbox2.py +81 -13

@@ -2,12 +2,16 @@ from __future__ import annotations

2 2

3 3 import random

4 4 import asyncio

5 import re

6 import json

7 from pathlib import Path

5 8 from aiohttp import ClientSession

6 9 from typing import AsyncGenerator

7 10

8 11 from ..typing import AsyncResult, Messages

9 12 from ..image import ImageResponse

10 13 from .base_provider import AsyncGeneratorProvider, ProviderModelMixin

14 from ..cookies import get_cookies_dir

11 15

12 16 from .. import debug

13 17

@@ -28,23 +32,84 @@ class Blackbox2(AsyncGeneratorProvider, ProviderModelMixin):

28 32 image_models = ['flux']

29 33 models = [*chat_models, *image_models]

30 34

35 @classmethod

36 def _get_cache_file(cls) -> Path:

37 """Returns the path to the cache file."""

38 dir = Path(get_cookies_dir())

39 dir.mkdir(exist_ok=True)

40 return dir / 'blackbox2.json'

42 @classmethod

43 def _load_cached_license(cls) -> str | None:

44 """Loads the license key from the cache."""

45 cache_file = cls._get_cache_file()

46 if cache_file.exists():

47 try:

48 with open(cache_file, 'r') as f:

49 data = json.load(f)

50 return data.get('license_key')

51 except Exception as e:

52 debug.log(f"Error reading cache file: {e}")

53 return None

55 @classmethod

56 def _save_cached_license(cls, license_key: str):

57 """Saves the license key to the cache."""

58 cache_file = cls._get_cache_file()

59 try:

60 with open(cache_file, 'w') as f:

61 json.dump({'license_key': license_key}, f)

62 except Exception as e:

63 debug.log(f"Error writing to cache file: {e}")

65 @classmethod

66 async def _get_license_key(cls, session: ClientSession) -> str:

67 """Gets the license key from the cache or from JavaScript files."""

68 cached_license = cls._load_cached_license()

69 if cached_license:

70 return cached_license

72 try:

73 async with session.get(cls.url) as response:

74 html = await response.text()

75 js_files = re.findall(r'static/chunks/\d{4}-[a-fA-F0-9]+\.js', html)

77 license_pattern = re.compile(r'j="(\d{6}-\d{6}-\d{6}-\d{6}-\d{6})"')

79 for js_file in js_files:

80 js_url = f"{cls.url}/_next/{js_file}"

81 async with session.get(js_url) as js_response:

82 js_content = await js_response.text()

83 if license_match := license_pattern.search(js_content):

84 license_key = license_match.group(1)

85 cls._save_cached_license(license_key)

86 return license_key

88 raise ValueError("License key not found")

89 except Exception as e:

90 debug.log(f"Error getting license key: {str(e)}")

91 raise

31 93 @classmethod

32 94 async def create_async_generator(

33 95 cls,

34 96 model: str,

35 97 messages: Messages,

98 prompt: str = None,

36 99 proxy: str = None,

37 100 max_retries: int = 3,

38 101 delay: int = 1,

102 max_tokens: int = None,

39 103 **kwargs

40 ) -> AsyncResult:

104 ) -> AsyncGenerator[str, None]:

41 105 if not model:

42 106 model = cls.default_model

107

43 108 if model in cls.chat_models:

44 async for result in cls._generate_text(model, messages, proxy, max_retries, delay):

109 async for result in cls._generate_text(model, messages, proxy, max_retries, delay, max_tokens):

45 110 yield result

46 111 elif model in cls.image_models:

47 prompt = messages[-1]["content"] if prompt is None else prompt

112 prompt = messages[-1]["content"]

48 113 async for result in cls._generate_image(model, prompt, proxy):

49 114 yield result

50 115 else:

@@ -57,17 +122,21 @@ class Blackbox2(AsyncGeneratorProvider, ProviderModelMixin):

57 122 messages: Messages,

58 123 proxy: str = None,

59 124 max_retries: int = 3,

60 delay: int = 1

61 ) -> AsyncGenerator:

125 delay: int = 1,

126 max_tokens: int = None,

127 ) -> AsyncGenerator[str, None]:

62 128 headers = cls._get_headers()

63 api_endpoint = cls.api_endpoints[model]

65 data = {

66 "messages": messages,

67 "max_tokens": None

68 }

69 129

70 130 async with ClientSession(headers=headers) as session:

131 license_key = await cls._get_license_key(session)

132 api_endpoint = cls.api_endpoints[model]

133

134 data = {

135 "messages": messages,

136 "max_tokens": max_tokens,

137 "validated": license_key

138 }

139

71 140 for attempt in range(max_retries):

72 141 try:

73 142 async with session.post(api_endpoint, json=data, proxy=proxy) as response:

@@ -92,7 +161,7 @@ class Blackbox2(AsyncGeneratorProvider, ProviderModelMixin):

92 161 model: str,

93 162 prompt: str,

94 163 proxy: str = None

95 ) -> AsyncGenerator:

164 ) -> AsyncGenerator[ImageResponse, None]:

96 165 headers = cls._get_headers()

97 166 api_endpoint = cls.api_endpoints[model]

98 167

@@ -116,7 +185,6 @@ class Blackbox2(AsyncGeneratorProvider, ProviderModelMixin):

116 185 'accept-language': 'en-US,en;q=0.9',

117 186 'content-type': 'text/plain;charset=UTF-8',

118 187 'origin': 'https://www.blackbox.ai',

119 'priority': 'u=1, i',

120 188 'referer': 'https://www.blackbox.ai',

121 189

            'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36'

122 190 }

Modified g4f/gui/client/index.html +1 -0

@@ -285,6 +285,7 @@

285 285 <option value="Copilot">Microsoft Copilot</option>

286 286 <option value="Gemini">Google Gemini</option>

287 287 <option value="DDG">DuckDuckGo AI Chat</option>

288 <option value="Blackbox">Blackbox AI</option>

288 289 <option disabled="disabled">----</option>

289 290 </select>

290 291 </div>

Modified g4f/models.py +39 -4

@@ -76,8 +76,9 @@ default = Model(

76 76 DeepInfraChat,

77 77 Airforce,

78 78 Cloudflare,

79 Mhystical,

80 79 PollinationsAI,

80 ChatGptEs,

81 ChatGpt,

81 82 ])

82 83 )

83 84

@@ -195,10 +196,16 @@ llama_3_2_11b = Model(

195 196 llama_3_3_70b = Model(

196 197 name = "llama-3.3-70b",

197 198 base_provider = "Meta Llama",

198 best_provider = IterListProvider([HuggingChat, HuggingFace, PerplexityLabs])

199 best_provider = IterListProvider([Blackbox, HuggingChat, HuggingFace, PerplexityLabs])

199 200 )

200 201

201 202 ### Mistral ###

203 mixtral_7b = Model(

204 name = "mixtral-7b",

205 base_provider = "Mistral",

206 best_provider = Blackbox

207 )

208

202 209 mixtral_8x7b = Model(

203 210 name = "mixtral-8x7b",

204 211 base_provider = "Mistral",

@@ -221,7 +228,7 @@ mistral_large = Model(

221 228 hermes_2_dpo = Model(

222 229 name = "hermes-2-dpo",

223 230 base_provider = "NousResearch",

224 best_provider = Airforce

231 best_provider = IterListProvider([Blackbox, Airforce])

225 232 )

226 233

227 234 hermes_2_pro = Model(

@@ -368,7 +375,7 @@ qwen_2_5_coder_32b = Model(

368 375 qwq_32b = Model(

369 376 name = 'qwq-32b',

370 377 base_provider = 'Qwen',

371 best_provider = IterListProvider([DeepInfraChat, HuggingChat, HuggingFace])

378 best_provider = IterListProvider([DeepInfraChat, Blackbox, HuggingChat, HuggingFace])

372 379 )

373 380

374 381 ### Inflection ###

@@ -379,6 +386,12 @@ pi = Model(

379 386 )

380 387

381 388 ### DeepSeek ###

389 deepseek_chat = Model(

390 name = 'deepseek-chat',

391 base_provider = 'DeepSeek',

392 best_provider = Blackbox

393 )

394

382 395 deepseek_coder = Model(

383 396 name = 'deepseek-coder',

384 397 base_provider = 'DeepSeek',

@@ -463,6 +476,20 @@ neural_7b = Model(

463 476 best_provider = Airforce

464 477 )

465 478

479 ### Databricks ###

480 dbrx_instruct = Model(

481 name = 'dbrx-instruct',

482 base_provider = 'Databricks',

483 best_provider = Blackbox

484 )

485

486 ### PollinationsAI ###

487 p1 = Model(

488 name = 'p1',

489 base_provider = 'PollinationsAI',

490 best_provider = PollinationsAI

491 )

492

466 493 ### Uncensored AI ###

467 494 evil = Model(

468 495 name = 'evil',

@@ -654,6 +681,7 @@ class ModelUtils:

654 681 llama_3_3_70b.name: llama_3_3_70b,

655 682

656 683 ### Mistral ###

684 mixtral_7b.name: mixtral_7b,

657 685 mixtral_8x7b.name: mixtral_8x7b,

658 686 mistral_nemo.name: mistral_nemo,

659 687 mistral_large.name: mistral_large,

@@ -728,6 +756,7 @@ class ModelUtils:

728 756 sonar_chat.name: sonar_chat,

729 757

730 758 ### DeepSeek ###

759 deepseek_chat.name: deepseek_chat,

731 760 deepseek_coder.name: deepseek_coder,

732 761

733 762 ### TheBloke ###

@@ -748,6 +777,12 @@ class ModelUtils:

748 777 ### Inferless ###

749 778 neural_7b.name: neural_7b,

750 779

780 ### Databricks ###

781 dbrx_instruct.name: dbrx_instruct,

782

783 ### PollinationsAI ###

784 p1.name: p1,

785

751 786 ### Uncensored AI ###

752 787 evil.name: evil,

753 788