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

webscout/Local/utils.py

@@ -1,93 +0,0 @@
-"""
-Utility functions for webscout.local
-"""
-
-import base64
-import logging
-
-logger = logging.getLogger(__name__)
-
-def parse_duration(duration_str: str) -> float:
-    """
-    Parse a duration string into seconds.
-    
-    Args:
-        duration_str (str): Duration string (e.g., '5m', '1h', '30s', '500ms', '0').
-    Returns:
-        float: Duration in seconds.
-    """
-    if not duration_str:
-        return 300.0  # Default 5 minutes
-    if duration_str.endswith("ms"):
-        return int(duration_str[:-2]) / 1000.0
-    elif duration_str.endswith("s"):
-        return int(duration_str[:-1])
-    elif duration_str.endswith("m"):
-        return int(duration_str[:-1]) * 60
-    elif duration_str.endswith("h"):
-        return int(duration_str[:-1]) * 3600
-    elif duration_str == "0":
-        return 0.0
-    else:
-        try:
-            return float(duration_str)
-        except ValueError:
-            return 300.0  # Default 5 minutes
-
-def format_duration(seconds: float) -> str:
-    """
-    Format seconds into a human-readable duration string.
-    Args:
-        seconds (float): Duration in seconds.
-    Returns:
-        str: Human-readable duration string.
-    """
-    if seconds < 1:
-        return f"{int(seconds * 1000)}ms"
-    elif seconds < 60:
-        return f"{int(seconds)}s"
-    elif seconds < 3600:
-        return f"{int(seconds / 60)}m"
-    else:
-        return f"{int(seconds / 3600)}h"
-
-def decode_image(image_str: str) -> bytes:
-    """
-    Decode a base64 image string to bytes.
-    Args:
-        image_str (str): Base64-encoded image string (optionally with data URI prefix).
-    Returns:
-        bytes: Decoded image bytes.
-    """
-    if image_str.startswith("data:"):
-        image_str = image_str.split(",", 1)[1]
-    return base64.b64decode(image_str)
-
-def encode_image(image_bytes: bytes, mime_type: str = "image/png") -> str:
-    """
-    Encode image bytes to a base64 data URI.
-    Args:
-        image_bytes (bytes): Image data.
-        mime_type (str): MIME type for the image.
-    Returns:
-        str: Base64-encoded data URI string.
-    """
-    encoded = base64.b64encode(image_bytes).decode("utf-8")
-    return f"data:{mime_type};base64,{encoded}"
-
-def get_file_size_str(size_bytes: int) -> str:
-    """
-    Convert file size in bytes to a human-readable string.
-    Args:
-        size_bytes (int): File size in bytes.
-    Returns:
-        str: Human-readable file size string.
-    """
-    if size_bytes < 1024:
-        return f"{size_bytes} B"
-    elif size_bytes < 1024 * 1024:
-        return f"{size_bytes / 1024:.2f} KB"
-    elif size_bytes < 1024 * 1024 * 1024:
-        return f"{size_bytes / (1024 * 1024):.2f} MB"
-    else:
-        return f"{size_bytes / (1024 * 1024 * 1024):.2f} GB"

webscout/Provider/AI21.py

@@ -1,177 +0,0 @@
-import requests
-import json
-from typing import Union, Dict, Any
-
-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 AI21(Provider):
-    """
-    A class to interact with the AI21 Studio API.
-    """
-
-    def __init__(
-        self,
-        api_key: str,
-        model: str = "jamba-1.5-large",
-        max_tokens: int = 1024,
-        temperature: float = 0.4,
-        top_p: float = 1,
-        is_conversation: bool = True,
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-        system_prompt: str = "You are a helpful and informative AI assistant."
-    ):
-        """
-        Initializes the AI21 Studio API with given parameters.
-        """
-        self.api_key = api_key
-        self.api_endpoint = "https://api.ai21.com/studio/v1/chat/completions"
-        self.model = model
-        self.max_tokens = max_tokens
-        self.temperature = temperature
-        self.top_p = top_p
-        self.system_prompt = system_prompt
-        self.session = requests.Session()
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            'Accept': 'application/json, text/plain, */*',
-            'Accept-Encoding': 'gzip, deflate, br, zstd',
-            'Accept-Language': 'en-US,en;q=0.9,en-IN;q=0.8',
-            'Authorization': f"Bearer {self.api_key}",
-            'Content-Type': 'application/json',
-            'DNT': '1',
-            'Origin': 'https://studio.ai21.com',
-            'Referer': 'https://studio.ai21.com/',
-            'Sec-CH-UA': '"Chromium";v="128", "Not;A=Brand";v="24", "Microsoft Edge";v="128"',
-            'Sec-CH-UA-Mobile': '?0',
-            'Sec-CH-UA-Platform': '"Windows"',
-            'Sec-Fetch-Dest': 'empty',
-            'Sec-Fetch-Mode': 'cors',
-            'Sec-Fetch-Site': 'same-site',
-            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0',
-        }
-
-        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[str, Any]:
-        """
-        Sends a prompt to the AI21 Studio 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 Exception(
-                    f"Optimizer is not one of {self.__available_optimizers}"
-                )
-
-        payload = {
-            "messages": [
-                {"role": "system", "content": self.system_prompt},
-                {"role": "user", "content": conversation_prompt}
-            ],
-            "n": 1,
-            "max_tokens": self.max_tokens,
-            "model": self.model,
-            "stop": [],
-            "temperature": self.temperature,
-            "top_p": self.top_p,
-            "documents": [],
-        }
-
-        response = self.session.post(self.api_endpoint, headers=self.headers, json=payload, timeout=self.timeout)
-
-        if not response.ok:
-            raise exceptions.FailedToGenerateResponseError(
-                f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-            )
-
-        resp = response.json()
-        self.last_response.update(resp)
-        self.conversation.update_chat_history(
-            prompt, self.get_message(self.last_response)
-        )
-        return self.last_response
-
-    def chat(
-        self,
-        prompt: str,
-        stream: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-    ) -> str:
-        """
-        Generates a response from the AI21 API.
-        """
-
-        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:
-        """
-        Extracts the message from the API response.
-        """
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response['choices'][0]['message']['content']
-
-# Example usage
-if __name__ == "__main__":
-    from rich import print
-    ai = AI21(api_key="api_key")
-    response = ai.chat(input(">>> "))
-    for line in response:
-        print(line, end="", flush=True)

webscout/Provider/AISEARCH/DeepFind.py

@@ -1,250 +0,0 @@
-from uuid import uuid4
-import requests
-import re
-from typing import Any, Dict, Generator, Optional, Union
-
-from webscout.AIbase import AISearch
-from webscout import exceptions
-from webscout.litagent import LitAgent
-
-class Response:
-    """A wrapper class for DeepFind API responses.
-    
-    This class automatically converts response objects to their text representation
-    when printed or converted to string.
-    
-    Attributes:
-        text (str): The text content of the response
-        
-    Example:
-        >>> response = Response("Hello, world!")
-        >>> print(response)
-        Hello, world!
-        >>> str(response)
-        'Hello, world!'
-    """
-    def __init__(self, text: str):
-        self.text = text
-    
-    def __str__(self):
-        return self.text
-    
-    def __repr__(self):
-        return self.text
-
-class DeepFind(AISearch):
-    """A class to interact with the DeepFind AI search API.
-    
-    DeepFind provides a powerful search interface that returns AI-generated responses
-    based on web content. It supports both streaming and non-streaming responses.
-    
-    Basic Usage:
-        >>> from webscout import DeepFind
-        >>> ai = DeepFind()
-        >>> # Non-streaming example
-        >>> response = ai.search("What is Python?")
-        >>> print(response)
-        Python is a high-level programming language...
-        
-        >>> # Streaming example
-        >>> for chunk in ai.search("Tell me about AI", stream=True):
-        ...     print(chunk, end="", flush=True)
-        Artificial Intelligence is...
-        
-        >>> # Raw response format
-        >>> for chunk in ai.search("Hello", stream=True, raw=True):
-        ...     print(chunk)
-        {'text': 'Hello'}
-        {'text': ' there!'}
-    
-    Args:
-        timeout (int, optional): Request timeout in seconds. Defaults to 30.
-        proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-    
-    Attributes:
-        api_endpoint (str): The DeepFind API endpoint URL.
-        stream_chunk_size (int): Size of chunks when streaming responses.
-        timeout (int): Request timeout in seconds.
-        headers (dict): HTTP headers used in requests.
-    """
-
-    def __init__(
-        self,
-        timeout: int = 30,
-        proxies: Optional[dict] = None,
-    ):
-        """Initialize the DeepFind API client.
-        
-        Args:
-            timeout (int, optional): Request timeout in seconds. Defaults to 30.
-            proxies (dict, optional): Proxy configuration for requests. Defaults to None.
-        
-        Example:
-            >>> ai = DeepFind(timeout=60)  # Longer timeout
-            >>> ai = DeepFind(proxies={'http': 'http://proxy.com:8080'})  # With proxy
-        """
-        self.session = requests.Session()
-        self.api_endpoint = "https://www.deepfind.co/?q={query}"
-        self.stream_chunk_size = 1024
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "Accept": "text/x-component",
-            "Accept-Encoding": "gzip, deflate, br, zstd",
-            "Accept-Language": "en-US,en;q=0.9,en-IN;q=0.8",
-            "Content-Type": "text/plain;charset=UTF-8",
-            "DNT": "1",
-            "Next-Action": "f354668f23f516a46ad0abe4dedb84b19068bb54",
-            "Next-Router-State-Tree": '%5B%22%22%2C%7B%22children%22%3A%5B%22__PAGE__%3F%7B%5C%22q%5C%22%3A%5C%22hi%5C%22%7D%22%2C%7B%7D%2C%22%2F%3Fq%3Dhi%22%2C%22refresh%22%5D%7D%2Cnull%2Cnull%2Ctrue%5D',
-            "Origin": "https://www.deepfind.co",
-            "Referer": "https://www.deepfind.co/?q=hi",
-            "Sec-Ch-Ua": '"Not A(Brand";v="8", "Chromium";v="132", "Microsoft Edge";v="132"',
-            "Sec-Ch-Ua-Mobile": "?0",
-            "Sec-Ch-Ua-Platform": '"Windows"',
-            "Sec-Fetch-Dest": "empty",
-            "Sec-Fetch-Mode": "cors",
-            "Sec-Fetch-Site": "same-origin",
-            "User-Agent": LitAgent().random(),
-        }
-        self.session.headers.update(self.headers)
-        self.proxies = proxies
-
-    def search(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-    ) -> Union[Response, Generator[Union[Dict[str, str], Response], None, None]]:
-        """Search using the DeepFind API and get AI-generated responses.
-        
-        This method sends a search query to DeepFind and returns the AI-generated response.
-        It supports both streaming and non-streaming modes, as well as raw response format.
-        
-        Args:
-            prompt (str): The search query or prompt to send to the API.
-            stream (bool, optional): If True, yields response chunks as they arrive.
-                                   If False, returns complete response. Defaults to False.
-            raw (bool, optional): If True, returns raw response dictionaries with 'text' key.
-                                If False, returns Response objects that convert to text automatically.
-                                Defaults to False.
-        
-        Returns:
-            Union[Dict[str, Any], Generator[str, None, None]]: 
-                - If stream=False: Returns complete response
-                - If stream=True: Yields response chunks as they arrive
-        
-        Raises:
-            APIConnectionError: If the API request fails
-        
-        Examples:
-            Basic search:
-            >>> ai = DeepFind()
-            >>> response = ai.search("What is Python?")
-            >>> print(response)
-            Python is a programming language...
-            
-            Streaming response:
-            >>> for chunk in ai.search("Tell me about AI", stream=True):
-            ...     print(chunk, end="")
-            Artificial Intelligence...
-            
-            Raw response format:
-            >>> for chunk in ai.search("Hello", stream=True, raw=True):
-            ...     print(chunk)
-            {'text': 'Hello'}
-            {'text': ' there!'}
-            
-            Error handling:
-            >>> try:
-            ...     response = ai.search("My question")
-            ... except exceptions.APIConnectionError as e:
-            ...     print(f"API error: {e}")
-        """
-        url = self.api_endpoint.format(query=prompt)
-        payload = [
-            [{"role": "user", "id": uuid4().hex, "content": prompt}],
-            uuid4().hex,
-        ]
-
-        def for_stream():
-            try:
-                with self.session.post(
-                    url,
-                    headers=self.headers,
-                    json=payload,
-                    stream=True,
-                    timeout=self.timeout,
-                ) as response:
-                    response.raise_for_status()
-                    streaming_text = ""
-                    for line in response.iter_lines(decode_unicode=True):
-                        if line:
-                            content_matches = re.findall(r'"content":"([^"\\]*(?:\\.[^"\\]*)*)"', line)
-                            if content_matches:
-                                for content in content_matches:
-                                    if len(content) > len(streaming_text):
-                                        delta = content[len(streaming_text):]
-                                        streaming_text = content
-                                        delta = delta.replace('\\"', '"').replace('\\n', '\n')
-                                        delta = re.sub(r'\[REF\]\(https?://[^\s]*\)', '', delta)
-                                        if raw:
-                                            yield {"text": delta}
-                                        else:
-                                            yield Response(delta)
-                            description_matches = re.findall(r'"description":"([^"\\]*(?:\\.[^"\\]*)*)"', line)
-                            if description_matches:
-                                for description in description_matches:
-                                    if description and len(description) > len(streaming_text):
-                                        delta = description[len(streaming_text):]
-                                        streaming_text = description
-                                        delta = delta.replace('\\"', '"').replace('\\n', '\n')
-                                        delta = re.sub(r'\[REF\]\(https?://[^\s]*\)', '', delta)
-                                        if raw:
-                                            yield {"text": f"{delta}\n"}
-                                        else:
-                                            yield Response(f"{delta}\n")
-                    self.last_response = Response(streaming_text)
-            except requests.exceptions.RequestException as e:
-                raise exceptions.APIConnectionError(f"Request failed: {e}")
-
-        def for_non_stream():
-            full_response = ""
-            for chunk in for_stream():
-                if raw:
-                    yield chunk
-                else:
-                    full_response += str(chunk)
-            if not raw:
-                self.last_response = Response(full_response)
-                return self.last_response
-        
-        return for_stream() if stream else for_non_stream()
-
-    @staticmethod
-    def clean_content(text: str) -> str:
-        """Removes all webblock elements with research or detail classes.
-        
-        Args:
-            text (str): The text to clean
-        
-        Returns:
-            str: The cleaned text
-        
-        Example:
-            >>> text = '<webblock class="research">...</webblock>Other text'
-            >>> cleaned_text = DeepFind.clean_content(text)
-            >>> print(cleaned_text)
-            Other text
-        """
-        cleaned_text = re.sub(
-            r'<webblock class="(?:research|detail)">[^<]*</webblock>', "", text
-        )
-        return cleaned_text
-
-
-if __name__ == "__main__":
-    from rich import print
-    ai = DeepFind()
-    response = ai.search(input(">>> "), stream=True, raw=False)
-    for chunk in response:
-        print(chunk, end="", flush=True)