webscout 8.2.7__py3-none-any.whl → 8.2.8__py3-none-any.whl

webscout/Litlogger/utils/formatters.py

@@ -0,0 +1,200 @@
+import json
+import re
+import traceback
+from datetime import datetime
+from typing import Any, Dict, Optional, Union
+
+class MessageFormatter:
+    """Utility class for formatting log messages."""
+    
+    @staticmethod
+    def format_exception(exc_info: tuple) -> str:
+        """
+        Format exception information into a readable string.
+        
+        Args:
+            exc_info: Tuple of (type, value, traceback)
+            
+        Returns:
+            Formatted exception string
+        """
+        return "".join(traceback.format_exception(*exc_info))
+
+    @staticmethod
+    def format_dict(data: Dict[str, Any], indent: int = 2) -> str:
+        """
+        Format dictionary into pretty-printed string.
+        
+        Args:
+            data: Dictionary to format
+            indent: Number of spaces for indentation
+            
+        Returns:
+            Formatted string representation
+        """
+        return json.dumps(data, indent=indent, default=str, ensure_ascii=False)
+
+    @staticmethod
+    def format_object(obj: Any) -> str:
+        """
+        Format any object into a string representation.
+        
+        Args:
+            obj: Object to format
+            
+        Returns:
+            String representation of object
+        """
+        if hasattr(obj, "to_dict"):
+            return MessageFormatter.format_dict(obj.to_dict())
+        if hasattr(obj, "__dict__"):
+            return MessageFormatter.format_dict(obj.__dict__)
+        return str(obj)
+
+    @staticmethod
+    def truncate(message: str, max_length: int = 1000, suffix: str = "...") -> str:
+        """
+        Truncate message to maximum length.
+        
+        Args:
+            message: Message to truncate
+            max_length: Maximum length
+            suffix: String to append when truncated
+            
+        Returns:
+            Truncated message
+        """
+        if len(message) <= max_length:
+            return message
+        return message[:max_length - len(suffix)] + suffix
+
+    @staticmethod
+    def mask_sensitive(message: str, patterns: Dict[str, str]) -> str:
+        """
+        Mask sensitive information in message.
+        
+        Args:
+            message: Message to process
+            patterns: Dictionary of {pattern: mask}
+            
+        Returns:
+            Message with sensitive info masked
+        """
+        result = message
+        for pattern, mask in patterns.items():
+            result = re.sub(pattern, mask, result)
+        return result
+
+    @staticmethod
+    def format_context(context: Dict[str, Any]) -> str:
+        """
+        Format context dictionary into readable string.
+        
+        Args:
+            context: Context dictionary
+            
+        Returns:
+            Formatted context string
+        """
+        parts = []
+        for key, value in sorted(context.items()):
+            formatted_value = (
+                MessageFormatter.format_object(value)
+                if isinstance(value, (dict, list, tuple))
+                else str(value)
+            )
+            parts.append(f"{key}={formatted_value}")
+        return " ".join(parts)
+
+    @staticmethod
+    def format_metrics(metrics: Dict[str, Union[int, float]]) -> str:
+        """
+        Format performance metrics into readable string.
+        
+        Args:
+            metrics: Dictionary of metric names and values
+            
+        Returns:
+            Formatted metrics string
+        """
+        parts = []
+        for key, value in sorted(metrics.items()):
+            if isinstance(value, float):
+                formatted = f"{value:.3f}"
+            else:
+                formatted = str(value)
+            parts.append(f"{key}={formatted}")
+        return " ".join(parts)
+
+    @staticmethod
+    def format_timestamp(
+        timestamp: Optional[datetime] = None,
+        format: str = "%Y-%m-%d %H:%M:%S.%f"
+    ) -> str:
+        """
+        Format timestamp into string.
+        
+        Args:
+            timestamp: Datetime object (uses current time if None)
+            format: strftime format string
+            
+        Returns:
+            Formatted timestamp string
+        """
+        if timestamp is None:
+            timestamp = datetime.now()
+        return timestamp.strftime(format)
+
+    @classmethod
+    def format_message(
+        cls,
+        message: str,
+        context: Optional[Dict[str, Any]] = None,
+        metrics: Optional[Dict[str, Union[int, float]]] = None,
+        max_length: Optional[int] = None,
+        mask_patterns: Optional[Dict[str, str]] = None,
+        timestamp_format: Optional[str] = None
+    ) -> str:
+        """
+        Format complete log message with all options.
+        
+        Args:
+            message: Base message
+            context: Optional context dictionary
+            metrics: Optional performance metrics
+            max_length: Optional maximum length
+            mask_patterns: Optional sensitive data patterns
+            timestamp_format: Optional timestamp format
+            
+        Returns:
+            Formatted complete message
+        """
+        parts = []
+        
+        # Add timestamp
+        if timestamp_format:
+            parts.append(cls.format_timestamp(format=timestamp_format))
+            
+        # Add main message
+        parts.append(message)
+        
+        # Add context if present
+        if context:
+            parts.append(cls.format_context(context))
+            
+        # Add metrics if present
+        if metrics:
+            parts.append(cls.format_metrics(metrics))
+            
+        # Join all parts
+        result = " ".join(parts)
+        
+        # Apply masking if needed
+        if mask_patterns:
+            result = cls.mask_sensitive(result, mask_patterns)
+            
+        # Apply length limit if needed
+        if max_length:
+            result = cls.truncate(result, max_length)
+            
+        return result

webscout/Provider/AI21.py

@@ -0,0 +1,177 @@
+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

@@ -0,0 +1,254 @@
+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.stream_chunk_size = 1024
+        self.timeout = timeout
+        self.last_response = {}
+        self.proxies = proxies
+        # Headers will be set per request, as conversationId is dynamic
+
+    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}")
+        """
+        conversation_id = uuid4().hex
+        message_id = uuid4().hex
+        url = f"https://www.deepfind.co/s/{conversation_id}"
+        payload = [
+            {
+                "id": conversation_id,
+                "messages": [
+                    {
+                        "role": "user",
+                        "conversationId": conversation_id,
+                        "messageId": message_id,
+                        "content": prompt,
+                    }
+                ],
+            },
+            conversation_id,
+            message_id,
+        ]
+        # Update headers for this conversation
+        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": f'%5B%22%22%2C%7B%22children%22%3A%5B%22s%22%2C%7B%22children%22%3A%5B%5B%22conversationId%22%2C%22{conversation_id}%22%2C%22d%22%5D%2C%7B%22children%22%3A%5B%22__PAGE__%22%2C%7B%7D%2C%22%2Fs%2F{conversation_id}%22%2C%22refresh%22%5D%7D%5D%7D%5D%7D%2Cnull%2Cnull%2Ctrue%5D',
+            "Origin": "https://www.deepfind.co",
+            "Referer": f"https://www.deepfind.co/s/{conversation_id}",
+            "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.clear()
+        self.session.headers.update(headers)
+
+        def for_stream():
+            try:
+                with self.session.post(
+                    url,
+                    headers=headers,
+                    json=payload,
+                    stream=True,
+                    timeout=self.timeout,
+                    proxies=self.proxies,
+                ) as response:
+                    response.raise_for_status()
+                    streaming_text = ""
+                    for line in response.iter_lines(decode_unicode=True):
+                        if line:
+                            # Try to extract content from the new streaming format
+                            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)
+                    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)