webscout 6.2b0__py3-none-any.whl → 6.4__py3-none-any.whl

webscout/Local/formats.py

@@ -291,7 +291,7 @@ llama2chat: dict[str, str | list] = {
 # https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/
 llama3: dict[str, str | list] = {
     "system_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
-    "system_prompt": 'You are a helpful AI assistant called "Llama 3".',
+    "system_prompt": 'You are a helpful AI assistant.',
     "system_suffix": "<|eot_id|>\n",
     "user_prefix": "<|start_header_id|>user<|end_header_id|>\n\n",
     "user_suffix": "<|eot_id|>\n",
@@ -628,6 +628,8 @@ airoboros = llama2chat.copy()
 airoboros['system_prompt'] = \
     "You are a helpful, unbiased, uncensored assistant."
 tess = synthia.copy()
+helpingai2 = llama3.copy()
+helpingai2['system_prompt'] = "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style."
 tess['system_prompt'] = ''  # Tess can use any system prompt, or none
 alpaca_strict = alpaca.copy()  # Alpaca with more stopping strings
 alpaca_strict['stops'] = [
@@ -651,7 +653,7 @@ def _llama3_suffix_with_timestamp():
 
 Llama3WithTimestamps = AdvancedFormat({
     "system_prefix": "<|start_header_id|>system<|end_header_id|>\n\n",
-    "system_prompt": 'You are a helpful AI assistant called "Llama 3".',
+    "system_prompt": 'You are a helpful AI assistant.',
     "system_suffix": _llama3_suffix_with_timestamp,
     "user_prefix": "<|start_header_id|>user<|end_header_id|>\n\n",
     "user_suffix": _llama3_suffix_with_timestamp,

webscout/Provider/Amigo.py

@@ -16,12 +16,17 @@ class AmigoChat(Provider):
     """
 
     AVAILABLE_MODELS = [
-        "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",  # Llama 3
-        "o1-mini",                                   # OpenAI O1 Mini
-        "claude-3-sonnet-20240229",                  # Claude Sonnet
-        "gemini-1.5-pro",                             # Gemini Pro
-        "gemini-1-5-flash",                            # Gemini Flash
-        "o1-preview",                                 # OpenAI O1 Preview
+        "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",    # Llama 3
+        "o1-mini",                                          # OpenAI O1 Mini
+        "claude-3-sonnet-20240229",                         # Claude Sonnet
+        "gemini-1.5-pro",                                   # Gemini Pro
+        "gemini-1-5-flash",                                 # Gemini Flash
+        "o1-preview",                                       # OpenAI O1 Preview
+        "claude-3-5-sonnet-20241022",                       # Claude 3.5 Sonnet
+        "Qwen/Qwen2.5-72B-Instruct-Turbo",                  # Qwen 2.5
+        "gpt-4o"                                            # OpenAI GPT-4o
+        "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo"    # Llama 3.2
+
     ]
 
     def __init__(
@@ -29,13 +34,15 @@ class AmigoChat(Provider):
         is_conversation: bool = True,
         max_tokens: int = 600,
         timeout: int = 30,
+        temperature: float = 1,
         intro: str = None,
         filepath: str = None,
+        top_p: float = 0.95,
         update_file: bool = True,
         proxies: dict = {},
         history_offset: int = 10250,
         act: str = None,
-        model: str = "o1-preview",  # Default model
+        model: str = "Qwen/Qwen2.5-72B-Instruct-Turbo",  # Default model
         system_prompt: str = "You are a helpful and friendly AI assistant.",
     ):
         """
@@ -68,8 +75,10 @@ class AmigoChat(Provider):
         self.api_endpoint = "https://api.amigochat.io/v1/chat/completions"
         self.stream_chunk_size = 64
         self.timeout = timeout
+        self.temperature = temperature
         self.last_response = {}
         self.model = model
+        self.top_p = top_p
         self.headers = {
             "Accept": "*/*",
             "Accept-Encoding": "gzip, deflate, br, zstd",
@@ -158,11 +167,11 @@ class AmigoChat(Provider):
             ],
             "model": self.model,
             "frequency_penalty": 0,
-            "max_tokens": 4000,
+            "max_tokens": self.max_tokens_to_sample,
             "presence_penalty": 0,
             "stream": stream,
-            "temperature": 0.5,
-            "top_p": 0.95
+            "temperature":self.temperature,
+            "top_p": self.top_p
         }
 
         def for_stream():

webscout/Provider/Andi.py

@@ -92,40 +92,7 @@ class AndiSearch(Provider):
         optimizer: str = None,
         conversationally: bool = False,
     ) -> dict:
-        """Chat with AI
 
-        Args:
-            prompt (str): Prompt to be send.
-            stream (bool, optional): Flag for streaming response. Defaults to False.
-            raw (bool, optional): Stream back raw response as received. Defaults to False.
-            optimizer (str, optional): Prompt optimizer name - `[code, shell_command]`. Defaults to None.
-            conversationally (bool, optional): Chat conversationally when using optimizer. Defaults to False.
-        Returns:
-           dict : {}
-        ```json
-        {
-            "id": "chatcmpl-TaREJpBZsRVQFRFic1wIA7Q7XfnaD",
-            "object": "chat.completion",
-            "created": 1704623244,
-            "model": "gpt-3.5-turbo",
-            "usage": {
-                "prompt_tokens": 0,
-                "completion_tokens": 0,
-                "total_tokens": 0
-                },
-            "choices": [
-                {
-                    "message": {
-                        "role": "assistant",
-                        "content": "Hello! How can I assist you today?"
-                },
-                "finish_reason": "stop",
-                "index": 0
-                }
-            ]
-        }
-        ```
-        """
         conversation_prompt = self.conversation.gen_complete_prompt(prompt)
         if optimizer:
             if optimizer in self.__available_optimizers:

webscout/Provider/Blackboxai.py

@@ -146,7 +146,7 @@ class BLACKBOXAI:
             for value in response.iter_lines(
                 decode_unicode=True,
                 chunk_size=self.stream_chunk_size,
-                delimiter="\n",
+
             ):
                 try:
                     if bool(value):
@@ -206,206 +206,6 @@ class BLACKBOXAI:
     def get_message(self, response: dict) -> str:
         """Retrieves message only from response
 
-        Args:
-            response (dict): Response generated by `self.ask`
-
-        Returns:
-            str: Message extracted
-        """
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response["text"]
-
-
-
-class AsyncBLACKBOXAI(AsyncProvider):
-    def __init__(
-        self,
-        is_conversation: bool = True,
-        max_tokens: int = 600,
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-        model: str = None,
-    ):
-        """Instantiates BLACKBOXAI
-
-        Args:
-            is_conversation (bool, optional): Flag for chatting conversationally. Defaults to True
-            max_tokens (int, optional): Maximum number of tokens to be generated upon completion. Defaults to 600.
-            timeout (int, optional): Http request timeout. Defaults to 30.
-            intro (str, optional): Conversation introductory prompt. Defaults to None.
-            filepath (str, optional): Path to file containing conversation history. Defaults to None.
-            update_file (bool, optional): Add new prompts and responses to the file. Defaults to True.
-            proxies (dict, optional): Http request proxies. Defaults to {}.
-            history_offset (int, optional): Limit conversation history to this number of last texts. Defaults to 10250.
-            act (str|int, optional): Awesome prompt key or index. (Used as intro). Defaults to None.
-            model (str, optional): Model name. Defaults to "Phind Model".
-        """
-        self.max_tokens_to_sample = max_tokens
-        self.is_conversation = is_conversation
-        self.chat_endpoint = "https://www.blackbox.ai/api/chat"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.model = model
-        self.previewToken: str = None
-        self.userId: str = ""
-        self.codeModelMode: bool = True
-        self.id: str = ""
-        self.agentMode: dict = {}
-        self.trendingAgentMode: dict = {}
-        self.isMicMode: bool = False
-
-        self.headers = {
-            "Content-Type": "application/json",
-            "User-Agent": "",
-            "Accept": "*/*",
-            "Accept-Encoding": "Identity",
-        }
-
-        self.__available_optimizers = (
-            method
-            for method in dir(Optimizers)
-            if callable(getattr(Optimizers, method)) and not method.startswith("__")
-        )
-        Conversation.intro = (
-            AwesomePrompts().get_act(
-                act, raise_not_found=True, default=None, case_insensitive=True
-            )
-            if act
-            else intro or Conversation.intro
-        )
-        self.conversation = Conversation(
-            is_conversation, self.max_tokens_to_sample, filepath, update_file
-        )
-        self.conversation.history_offset = history_offset
-        self.session = httpx.AsyncClient(headers=self.headers, proxies=proxies)
-
-    async def ask(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-    ) -> dict | AsyncGenerator:
-        """Chat with AI asynchronously.
-
-        Args:
-            prompt (str): Prompt to be send.
-            stream (bool, optional): Flag for streaming response. Defaults to False.
-            raw (bool, optional): Stream back raw response as received. Defaults to False.
-            optimizer (str, optional): Prompt optimizer name - `[code, shell_command]`. Defaults to None.
-            conversationally (bool, optional): Chat conversationally when using optimizer. Defaults to False.
-        Returns:
-           dict|AsyncGenerator : ai content
-        ```json
-        {
-           "text" : "print('How may I help you today?')"
-        }
-        ```
-        """
-        conversation_prompt = self.conversation.gen_complete_prompt(prompt)
-        if optimizer:
-            if optimizer in self.__available_optimizers:
-                conversation_prompt = getattr(Optimizers, optimizer)(
-                    conversation_prompt if conversationally else prompt
-                )
-            else:
-                raise Exception(
-                    f"Optimizer is not one of {self.__available_optimizers}"
-                )
-
-        payload = {
-            "messages": [
-                # json.loads(prev_messages),
-                {"content": conversation_prompt, "role": "user"}
-            ],
-            "id": self.id,
-            "previewToken": self.previewToken,
-            "userId": self.userId,
-            "codeModelMode": self.codeModelMode,
-            "agentMode": self.agentMode,
-            "trendingAgentMode": self.trendingAgentMode,
-            "isMicMode": self.isMicMode,
-        }
-
-        async def for_stream():
-            async with self.session.stream(
-                "POST", self.chat_endpoint, json=payload, timeout=self.timeout
-            ) as response:
-                if (
-                    not response.is_success
-                    or not response.headers.get("Content-Type")
-                    == "text/plain; charset=utf-8"
-                ):
-                    raise exceptions.FailedToGenerateResponseError(
-                        f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
-                    )
-                streaming_text = ""
-                async for value in response.aiter_lines():
-                    try:
-                        if bool(value):
-                            streaming_text += value + ("\n" if stream else "")
-                            resp = dict(text=streaming_text)
-                            self.last_response.update(resp)
-                            yield value if raw else resp
-                    except json.decoder.JSONDecodeError:
-                        pass
-            self.conversation.update_chat_history(
-                prompt, await self.get_message(self.last_response)
-            )
-
-        async def for_non_stream():
-            async for _ in for_stream():
-                pass
-            return self.last_response
-
-        return for_stream() if stream else await for_non_stream()
-
-    async def chat(
-        self,
-        prompt: str,
-        stream: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-    ) -> str | AsyncGenerator:
-        """Generate response `str` asynchronously.
-        Args:
-            prompt (str): Prompt to be send.
-            stream (bool, optional): Flag for streaming response. Defaults to False.
-            optimizer (str, optional): Prompt optimizer name - `[code, shell_command]`. Defaults to None.
-            conversationally (bool, optional): Chat conversationally when using optimizer. Defaults to False.
-        Returns:
-            str|AsyncGenerator: Response generated
-        """
-
-        async def for_stream():
-            async_ask = await self.ask(
-                prompt, True, optimizer=optimizer, conversationally=conversationally
-            )
-            async for response in async_ask:
-                yield await self.get_message(response)
-
-        async def for_non_stream():
-            return await self.get_message(
-                await self.ask(
-                    prompt,
-                    False,
-                    optimizer=optimizer,
-                    conversationally=conversationally,
-                )
-            )
-
-        return for_stream() if stream else await for_non_stream()
-
-    async def get_message(self, response: dict) -> str:
-        """Retrieves message only from response
-
         Args:
             response (dict): Response generated by `self.ask`
 
@@ -418,10 +218,10 @@ class AsyncBLACKBOXAI(AsyncProvider):
 # Function to clean the response text
 def clean_response(response_text: str) -> str:
     # Remove web search results
-    response_text = re.sub(r'\$@\$v=undefined-rv1\$@\$Sources:.*?\$~~~', '', response_text, flags=re.DOTALL)
+    cleaned_response = re.sub(r'\$~~~\$.*?\$~~~\$', '', response_text, flags=re.DOTALL)
     # Remove any remaining special characters or markers
-    response_text = re.sub(r'\$~~~', '', response_text)
-    return response_text
+    cleaned_response = re.sub(r'\$~~~', '', cleaned_response)
+    return cleaned_response.strip()
 if __name__ == '__main__':
     from rich import print
     ai = BLACKBOXAI()

webscout/Provider/DARKAI.py

@@ -218,7 +218,7 @@ class DARKAI(Provider):
         return response["text"]
 if __name__ == '__main__':
     from rich import print
-    ai = DARKAI(model='llama-3-405b')
+    ai = DARKAI()
     response = ai.chat("tell me about india")
     for chunk in response:
         print(chunk, end="", flush=True)

webscout/Provider/EDITEE.py

@@ -1,6 +1,6 @@
 import cloudscraper
 from webscout.AIutel import Optimizers
-from webscout.AIutel import Conversation, Proxy
+from webscout.AIutel import Conversation
 from webscout.AIutel import AwesomePrompts, sanitize_stream
 from webscout.AIbase import  Provider, AsyncProvider
 from webscout import exceptions

webscout/Provider/Llama3.py

@@ -183,7 +183,7 @@ class LLAMA3(Provider):
 
 if __name__ == "__main__":
     from rich import print
-    ai = LLAMA3(api_key='7979b01c-c5ea-40df-9198-f45733fa2208')
+    ai = LLAMA3(api_key='')
     response = ai.chat(input(">>> "))
     for chunks in response:
         print(chunks, end="", flush=True)

webscout/Provider/Marcus.py

@@ -0,0 +1,137 @@
+import requests
+import json
+from typing import Any, Dict, Optional, Generator
+
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation
+from webscout.AIutel import AwesomePrompts
+from webscout.AIbase import Provider
+from webscout import exceptions
+
+
+class Marcus(Provider):
+    """
+    This class provides methods for interacting with the AskMarcus API.
+    Improved to match webscout provider standards.
+    """
+
+    def __init__(
+        self,
+        is_conversation: bool = True,
+        max_tokens: int = 2048,  # Added max_tokens parameter
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+    ):
+        """Initializes the Marcus API."""
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.api_endpoint = "https://www.askmarcus.app/api/response"
+        self.timeout = timeout
+        self.last_response = {}
+        self.headers = {
+            'content-type': 'application/json',
+            'accept': '*/*',
+            'origin': 'https://www.askmarcus.app',
+            'referer': 'https://www.askmarcus.app/chat',
+            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36'
+        }
+        self.__available_optimizers = (
+            method
+            for method in dir(Optimizers)
+            if callable(getattr(Optimizers, method)) and not method.startswith("__")
+        )
+        Conversation.intro = (
+            AwesomePrompts().get_act(
+                act, raise_not_found=True, default=None, case_insensitive=True
+            )
+            if act
+            else intro or Conversation.intro
+        )
+        self.conversation = Conversation(
+            is_conversation, self.max_tokens_to_sample, filepath, update_file
+        )
+        self.conversation.history_offset = history_offset
+        self.session.proxies = proxies
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> Dict[str, Any] | Generator[str, None, None]:
+        """Sends a prompt to the AskMarcus API and returns the response."""
+        conversation_prompt = self.conversation.gen_complete_prompt(prompt)
+        if optimizer:
+            if optimizer in self.__available_optimizers:
+                conversation_prompt = getattr(Optimizers, optimizer)(
+                    conversation_prompt if conversationally else prompt
+                )
+            else:
+                raise exceptions.FailedToGenerateResponseError(
+                    f"Optimizer is not one of {self.__available_optimizers}"
+                )
+
+        data = {"message": conversation_prompt}
+
+        def for_stream():
+            try:
+                with requests.post(self.api_endpoint, headers=self.headers, json=data, stream=True, timeout=self.timeout) as response:
+                    response.raise_for_status()
+                    for line in response.iter_lines():
+                        if line:
+                            yield line.decode('utf-8')
+                    self.conversation.update_chat_history(prompt, self.get_message(self.last_response))
+
+            except requests.exceptions.RequestException as e:
+                raise exceptions.ProviderConnectionError(f"Error connecting to Marcus: {str(e)}")
+
+        def for_non_stream():
+            full_response = ""
+            for line in for_stream():
+                full_response += line
+            self.last_response = {"text": full_response}
+            return self.last_response
+
+        return for_stream() if stream else for_non_stream()
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> str | Generator[str, None, None]:
+        """Generates a response from the AskMarcus API."""
+
+        def for_stream():
+            for response_chunk in self.ask(
+                prompt, stream=True, optimizer=optimizer, conversationally=conversationally
+            ):
+                yield response_chunk
+
+        def for_non_stream():
+            response = self.ask(
+                prompt, stream=False, optimizer=optimizer, conversationally=conversationally
+            )
+            return self.get_message(response)
+
+        return for_stream() if stream else for_non_stream()
+
+    def get_message(self, response: Dict[str, Any]) -> str:
+        """Extracts the message from the API response."""
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        return response.get("text", "")
+
+if __name__ == '__main__':
+    ai = Marcus(timeout=30)
+    response = ai.chat("Tell me about India", stream=True)
+    for chunk in response:
+        print(chunk)

webscout/Provider/NinjaChat.py

@@ -35,7 +35,7 @@ class NinjaChat(Provider):
         proxies: dict = {},
         history_offset: int = 10250,
         act: str = None,
-        model: str = "perplexity",  # Default model
+        model: str = "llama",  # Default model
         system_message: str = "You are a helpful AI assistant.",  # Default system message
     ):
         """Initializes the NinjaChat API client."""