webscout 8.2.2__py3-none-any.whl → 8.2.7__py3-none-any.whl

webscout/Provider/PizzaGPT.py

@@ -1,198 +0,0 @@
-import requests
-import json
-import re
-from typing import Any, Dict, Optional, Union, Generator
-from webscout.AIutel import Optimizers, Conversation, AwesomePrompts
-from webscout.AIbase import Provider
-from webscout import exceptions
-from webscout.litagent import LitAgent as Lit
-
-class PIZZAGPT(Provider):
-    """
-    PIZZAGPT is a provider class for interacting with the PizzaGPT API.
-    Supports web search integration and handles responses using regex.
-    """
-    AVAILABLE_MODELS = ["gpt-4o-mini"]
-    
-    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 = "gpt-4o-mini"
-    ) -> None:
-        """Initialize PizzaGPT with enhanced configuration options."""
-        if model not in self.AVAILABLE_MODELS:
-            raise ValueError(f"Invalid model: {model}. Choose from: {self.AVAILABLE_MODELS}")
-            
-        self.session = requests.Session()
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.api_endpoint = "https://www.pizzagpt.it/api/chatx-completion"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.model = model
-        
-        self.headers = {
-            "accept": "application/json",
-            "accept-language": "en-US,en;q=0.9",
-            "content-type": "application/json",
-            "origin": "https://www.pizzagpt.it",
-            "referer": "https://www.pizzagpt.it/en",
-            "user-agent": Lit().random(),
-            "x-secret": "Marinara",
-            "sec-ch-ua": '"Chromium";v="134", "Not:A-Brand";v="24"',
-            "sec-ch-ua-platform": '"Windows"'
-        }
-
-        self.__available_optimizers = (
-            method for method in dir(Optimizers)
-            if callable(getattr(Optimizers, method)) and not method.startswith("__")
-        )
-        
-        self.session.headers.update(self.headers)
-        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 _extract_content(self, text: str) -> Dict[str, Any]:
-        """
-        Extract content from response text using regex.
-        """
-        try:
-            # Look for content pattern
-            content_match = re.search(r'"content"\s*:\s*"(.*?)"(?=\s*[,}])', text, re.DOTALL)
-            if not content_match:
-                raise exceptions.FailedToGenerateResponseError("Content not found in response")
-                
-            content = content_match.group(1)
-            # Unescape special characters
-            content = content.encode().decode('unicode_escape')
-            
-            # Look for citations if present
-            citations = []
-            citations_match = re.search(r'"citations"\s*:\s*\[(.*?)\]', text, re.DOTALL)
-            if citations_match:
-                citations_text = citations_match.group(1)
-                citations = re.findall(r'"(.*?)"', citations_text)
-            
-            return {
-                "content": content,
-                "citations": citations
-            }
-            
-        except Exception as e:
-            raise exceptions.FailedToGenerateResponseError(f"Failed to extract content: {str(e)}")
-
-    def ask(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-        web_search: bool = False,
-    ) -> Dict[str, Any]:
-        """
-        Send a prompt to PizzaGPT API with optional web search capability.
-        """
-        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 = {
-            "question": conversation_prompt,
-            "model": self.model,
-            "searchEnabled": web_search
-        }
-
-        try:
-            response = self.session.post(
-                self.api_endpoint,
-                json=payload,
-                timeout=self.timeout
-            )
-            
-            if not response.ok:
-                raise exceptions.FailedToGenerateResponseError(
-                    f"Failed to generate response - ({response.status_code}, {response.reason})"
-                )
-
-            response_text = response.text
-            if not response_text:
-                raise exceptions.FailedToGenerateResponseError("Empty response received from API")
-
-            try:
-                resp = self._extract_content(response_text)
-                    
-                self.last_response.update(dict(text=resp['content']))
-                self.conversation.update_chat_history(
-                    prompt, self.get_message(self.last_response)
-                )
-                return self.last_response
-
-            except Exception as e:
-                raise exceptions.FailedToGenerateResponseError(f"Failed to parse response: {str(e)}")
-
-        except requests.exceptions.RequestException as e:
-            raise exceptions.FailedToGenerateResponseError(f"Request failed: {str(e)}")
-
-    def chat(
-        self,
-        prompt: str,
-        stream: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-        web_search: bool = False,
-    ) -> str:
-        """
-        Chat with PizzaGPT with optional web search capability.
-        """
-        try:
-            response = self.ask(
-                prompt,
-                optimizer=optimizer,
-                conversationally=conversationally,
-                web_search=web_search
-            )
-            return self.get_message(response)
-        except Exception as e:
-            raise
-
-    def get_message(self, response: dict) -> str:
-        """Extract message from response dictionary."""
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response.get("text", "")
-
-if __name__ == "__main__":
-    from rich import print
-    
-    # Example usage with web search enabled
-    ai = PIZZAGPT()
-    try:
-        response = ai.chat("hi")
-        print(response)
-    except Exception as e:
-        print(f"Error: {str(e)}")

webscout/Provider/QwenLM.py

@@ -1,254 +0,0 @@
-import json
-from typing import Union, Any, Dict, Generator, Optional
-
-import cloudscraper
-
-from webscout.AIutel import Optimizers, Conversation, AwesomePrompts
-from webscout.AIbase import Provider
-from webscout import exceptions
-
-class QwenLM(Provider):
-    """
-    A class to interact with the QwenLM API
-    """
-
-    AVAILABLE_MODELS = [
-        "qwen-max-latest",
-        "qwen-plus-latest",
-        "qwen2.5-14b-instruct-1m",
-        "qwq-32b",
-        "qwen2.5-coder-32b-instruct",
-        "qwen-turbo-latest",
-        "qwen2.5-72b-instruct",
-        "qwen2.5-vl-72b-instruct",
-        "qvq-72b-preview"
-    ]
-
-    def __init__(
-        self,
-        cookies_path: str,
-        is_conversation: bool = True,
-        max_tokens: int = 600,
-        timeout: int = 30,
-        intro: Optional[str] = None,
-        filepath: Optional[str] = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: Optional[str] = None,
-        model: str = "qwen-plus-latest",
-        system_prompt: str = "You are a helpful AI assistant."
-    ):
-        """Initializes the QwenLM API client."""
-        if model not in self.AVAILABLE_MODELS:
-            raise ValueError(
-                f"Invalid model: {model}. Choose from: {self.AVAILABLE_MODELS}"
-            )
-
-        self.session = cloudscraper.create_scraper()
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.api_endpoint = "https://chat.qwenlm.ai/api/chat/completions"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.model = model
-        self.system_prompt = system_prompt
-        self.cookies_path = cookies_path
-        self.cookie_string, self.token = self._load_cookies()
-
-        self.headers = {
-            "accept": "*/*",
-            "accept-language": "en-US,en;q=0.9",
-            "content-type": "application/json",
-            "origin": "https://chat.qwenlm.ai",
-            "referer": "https://chat.qwenlm.ai/",
-            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36 Edg/127.0.0.0",
-            "authorization": f"Bearer {self.token}" if self.token else '',
-        }
-        self.session.headers.update(self.headers)
-        self.session.proxies = proxies
-        self.chat_type = "t2t"  # search - used WEB, t2t - chatbot, t2i - image_gen
-        if self.chat_type != "t2t":
-            AVAILABLE_MODELS = [
-                'qwen-plus-latest', 'qvq-72b-preview',
-                'qvq-32b', 'qwen-turbo-latest',
-                'qwen-max-latest'
-            ]
-
-        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
-
-    def _load_cookies(self) -> tuple[str, str]:
-        """Load cookies from a JSON file and build a cookie header string."""
-        try:
-            with open(self.cookies_path, "r") as f:
-                cookies = json.load(f)
-            cookie_string = "; ".join(
-                f"{cookie['name']}={cookie['value']}" for cookie in cookies
-            )
-            token = next(
-                (cookie.get("value") for cookie in cookies if cookie.get("name") == "token"),
-                "",
-            )
-            return cookie_string, token
-        except FileNotFoundError:
-            raise exceptions.InvalidAuthenticationError(
-                "Error: cookies.json file not found!"
-            )
-        except json.JSONDecodeError:
-            raise exceptions.InvalidAuthenticationError(
-                "Error: Invalid JSON format in cookies.json!"
-            )
-
-    def ask(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-        optimizer: Optional[str] = None,
-        conversationally: bool = False,
-    ) -> Union[Dict[str, Any], Generator[Any, None, None]]:
-        """Chat with AI."""
-
-        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 {list(self.__available_optimizers)}"
-                )
-
-        payload = {
-            'chat_type': self.chat_type,
-            "messages": [
-                {"role": "system", "content": self.system_prompt},
-                {"role": "user", "content": conversation_prompt}
-            ],
-            "model": self.model,
-            "stream": stream,
-            "max_tokens": self.max_tokens_to_sample
-        }
-
-        def for_stream() -> Generator[Dict[str, Any], None, None]:
-            response = self.session.post(
-                self.api_endpoint, json=payload, headers=self.headers, stream=True, timeout=self.timeout
-            )
-            if not response.ok:
-                raise exceptions.FailedToGenerateResponseError(
-                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                )
-
-            cumulative_text = ""
-            for line in response.iter_lines(decode_unicode=True):
-                if line and line.startswith("data: "):
-                    data = line[6:]
-                    if data == "[DONE]":
-                        break
-                    try:
-                        json_data = json.loads(data)
-                        # Handle multiple response formats
-                        if "choices" in json_data:
-                            new_content = json_data.get("choices")[0].get("delta", {}).get("content", "")
-                        elif "messages" in json_data:
-                            assistant_msg = next(
-                                (msg for msg in reversed(json_data["messages"]) if msg.get("role") == "assistant"),
-                                {}
-                            )
-                            content_field = assistant_msg.get("content", "")
-                            if isinstance(content_field, list):
-                                new_content = "".join(item.get("text", "") for item in content_field)
-                            else:
-                                new_content = content_field
-                        else:
-                            new_content = ""
-                        delta = new_content[len(cumulative_text):]
-                        cumulative_text = new_content
-                        if delta:
-                            yield delta if raw else {"text": delta}
-                    except json.JSONDecodeError:
-                        continue
-            self.last_response.update(dict(text=cumulative_text))
-            self.conversation.update_chat_history(
-                prompt, self.get_message(self.last_response)
-            )
-
-        def for_non_stream() -> Dict[str, Any]:
-            """
-            Handles non-streaming responses by aggregating all streamed chunks into a single string.
-            """
-
-            # Initialize an empty string to accumulate the full response
-            full_response = ""
-
-            # Iterate through the stream generator and accumulate the text
-            try:
-                for response in self.ask(prompt, True, optimizer=optimizer, conversationally=conversationally):
-                    if isinstance(response, dict):  # Check if the response is a dictionary
-                        full_response += response.get("text", "")  # Extract and append the "text" field
-                    elif isinstance(response, str):  # If the response is a string, directly append it
-                        full_response += response
-            except Exception as e:
-                raise
-
-            # Ensure last_response is updated with the aggregated text
-            self.last_response.update({"text": full_response})
-
-            # Update conversation history with the final response
-            self.conversation.update_chat_history(prompt, self.get_message(self.last_response))
-
-            return {"text": full_response}  # Return the dictionary containing the full response
-
-        return for_stream() if stream else for_non_stream()
-
-
-    def chat(
-        self,
-        prompt: str,
-        stream: bool = False,
-        optimizer: Optional[str] = None,
-        conversationally: bool = False,
-    ) -> Union[str, Generator[str, None, None]]:
-        """Generate response string from chat."""
-
-        def for_stream() -> Generator[str, None, None]:
-            for response in self.ask(prompt, True, optimizer=optimizer, conversationally=conversationally):
-                yield response if isinstance(response, str) else response["text"]
-
-        def for_non_stream() -> str:
-            result = self.ask(prompt, False, optimizer=optimizer, conversationally=conversationally)
-            return self.get_message(result)
-
-        return for_stream() if stream else for_non_stream()
-
-    def get_message(self, response: dict) -> str:
-        """Extracts the message content from a response dict."""
-        assert isinstance(response, dict), "Response should be a dict"
-        return response.get("text", "")
-
-if __name__ == "__main__":
-    from rich import print
-    ai = QwenLM(cookies_path="cookies.json")
-    response = ai.chat(input(">>> "), stream=False)
-    ai.chat_type = "search" # search - used WEB, t2t - chatbot, t2i - image_gen
-    print(response)
-    # for chunk in response:
-    #     print(chunk, end="", flush=True)

webscout/Provider/Reka.py

@@ -1,214 +0,0 @@
-import requests
-
-
-import json
-
-from webscout.AIutel import Optimizers
-from webscout.AIutel import Conversation
-from webscout.AIutel import AwesomePrompts, sanitize_stream
-from webscout.AIbase import  Provider, AsyncProvider
-from webscout import exceptions
-
-#-----------------------------------------------REKA-----------------------------------------------
-class REKA(Provider):
-    def __init__(
-        self,
-        api_key: str,
-        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 = "reka-core",
-        system_prompt: str = "Be Helpful and Friendly. Keep your response straightforward, short and concise",
-        use_search_engine: bool = False,
-        use_code_interpreter: bool = False,
-    ):
-        """Instantiates REKA
-
-        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): REKA model name. Defaults to "reka-core".
-            system_prompt (str, optional): System prompt for REKA. Defaults to "Be Helpful and Friendly. Keep your response straightforward, short and concise".
-            use_search_engine (bool, optional): Whether to use the search engine. Defaults to False.
-            use_code_interpreter (bool, optional): Whether to use the code interpreter. Defaults to False.
-        """
-        self.session = requests.Session()
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.api_endpoint = "https://chat.reka.ai/api/chat"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.model = model
-        self.system_prompt = system_prompt
-        self.use_search_engine = use_search_engine
-        self.use_code_interpreter = use_code_interpreter
-        self.access_token = api_key
-        self.headers = {
-            "Authorization": f"Bearer {self.access_token}",
-        }
-
-        self.__available_optimizers = (
-            method
-            for method in dir(Optimizers)
-            if callable(getattr(Optimizers, method)) and not method.startswith("__")
-        )
-        self.session.headers.update(self.headers)
-        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:
-        """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
-        {
-           "text" : "How may I assist 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}"
-                )
-
-        self.session.headers.update(self.headers)
-        payload = {
-
-            "conversation_history": [
-                {"type": "human", "text": f"## SYSTEM PROMPT: {self.system_prompt}\n\n## QUERY: {conversation_prompt}"},
-            ],
-
-            "stream": stream,
-            "use_search_engine": self.use_search_engine,
-            "use_code_interpreter": self.use_code_interpreter,
-            "model_name": self.model,
-            # "model_name": "reka-flash",
-            # "model_name": "reka-edge",
-        }
-
-        def for_stream():
-            response = self.session.post(self.api_endpoint, json=payload, stream=True, timeout=self.timeout)
-            if not response.ok:
-                raise Exception(
-                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                )
-
-            for value in response.iter_lines(
-                decode_unicode=True,
-                chunk_size=self.stream_chunk_size,
-            ):
-                try:
-                    resp = json.loads(value)
-                    self.last_response.update(resp)
-                    yield value if raw else resp
-                except json.decoder.JSONDecodeError:
-                    pass
-            self.conversation.update_chat_history(
-                prompt, self.get_message(self.last_response)
-            )
-
-        def for_non_stream():
-            # let's make use of stream
-            for _ in for_stream():
-                pass
-            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:
-        """Generate response `str`
-        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: Response generated
-        """
-
-        def for_stream():
-            for response in self.ask(
-                prompt, True, optimizer=optimizer, conversationally=conversationally
-            ):
-                yield self.get_message(response)
-
-        def for_non_stream():
-            return self.get_message(
-                self.ask(
-                    prompt,
-                    False,
-                    optimizer=optimizer,
-                    conversationally=conversationally,
-                )
-            )
-
-        return for_stream() if stream else for_non_stream()
-
-    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.get("text")
-if __name__ == "__main__":
-    
-    from rich import print
-    ai = REKA(api_key="YOUR_API_KEY", timeout=5000)
-    response = ai.chat("write a poem about AI", stream=True)
-    for chunk in response:
-        print(chunk, end="", flush=True)