webscout 6.6__py3-none-any.whl → 6.8__py3-none-any.whl

webscout/Provider/mhystical.py

@@ -1,176 +0,0 @@
-import requests
-import json
-from typing import Any, Dict, Optional, Generator, List
-
-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 Mhystical(Provider):
-    """
-    A class to interact with the Mhystical API. Improved to meet webscout provider standards.
-    """
-
-    AVAILABLE_MODELS = ["gpt-4", "gpt-3.5-turbo"]  # Add available models
-
-    def __init__(
-        self,
-        is_conversation: bool = True,
-        max_tokens: int = 2048,
-        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-4", # Default model
-        system_prompt: str = "You are a helpful AI assistant." # Default system prompt
-    ):
-        """Initializes the Mhystical API."""
-        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://api.mhystical.cc/v1/completions"
-        self.timeout = timeout
-        self.last_response = {}
-        self.model = model
-        self.system_prompt = system_prompt # Store system prompt
-        self.headers = {
-            "x-api-key": "mhystical", # Set API key in header (or better, in __init__ from parameter)
-            "Content-Type": "application/json",
-            "accept": "*/*",
-            "user-agent": "Mozilla/5.0"
-        }
-        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[Dict[str, Any], None, None]:
-
-        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}"
-                )
-
-        messages = [
-                {"role": "system", "content": self.system_prompt},  # Include system prompt
-                {"role": "user", "content": conversation_prompt},
-            ]
-            
-        data = {
-            "model": self.model,  # Now using self.model
-            "messages": messages # Pass messages to API
-        }
-
-        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() # Raise exceptions for HTTP errors
-
-                    # Emulate streaming for this API
-                    full_response = ""  # Accumulate the full response
-                    for chunk in response.iter_content(decode_unicode=True, chunk_size=self.stream_chunk_size):
-                        if chunk:
-                            full_response += chunk
-                            yield chunk if raw else {"text": chunk}
-
-                    self.last_response.update({"text": full_response})
-                    self.conversation.update_chat_history(prompt, full_response)
-            except requests.exceptions.RequestException as e:
-                raise exceptions.ProviderConnectionError(f"Network error: {str(e)}")
-
-        def for_non_stream():
-            try:
-                response = self.session.post(self.api_endpoint, headers=self.headers, json=data, timeout=self.timeout)
-                response.raise_for_status()
-
-                full_response = self._parse_response(response.text)
-                self.last_response.update({"text": full_response})
-
-                # Yield the entire response as a single chunk
-                yield {"text": full_response}
-
-            except requests.exceptions.RequestException as e:
-                raise exceptions.ProviderConnectionError(f"Network error: {str(e)}")
-
-        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]:
-
-        def for_stream():
-            for response in self.ask(
-                prompt, stream=True, optimizer=optimizer, conversationally=conversationally
-            ):
-                yield self.get_message(response)
-
-        def for_non_stream():
-            response = next(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:
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response["text"]
-
-    @staticmethod
-    def _parse_response(response_text: str) -> str:
-        """Parse and validate API response."""
-        try:
-            data = json.loads(response_text)
-            return data["choices"][0]["message"]["content"].strip()
-        except (json.JSONDecodeError, KeyError, IndexError) as e:
-            raise exceptions.InvalidResponseError(f"Failed to parse response: {str(e)}")
-
-if __name__ == "__main__":
-    from rich import print
-    ai = Mhystical()
-    response = ai.chat(input(">>> "))
-    for chunk in response:
-        print(chunk, end="", flush=True)

webstoken/t.py

@@ -1,75 +0,0 @@
-from webstoken import (
-    process_text, NamedEntityRecognizer, TextClassifier,
-    TopicClassifier, LanguageDetector, SentimentAnalyzer,
-    KeywordExtractor
-)
-from rich import print
-# Example text
-text = """
-Dr. John Smith from Microsoft Corporation visited New York City on January 15th, 2024.
-He presented an excellent paper about artificial intelligence and machine learning at
-the International Technology Conference. The research was incredibly well-received,
-and many attendees were excited about its potential applications in healthcare.
-"""
-
-print("1. Basic Text Processing")
-print("-" * 50)
-result = process_text(text)
-for sentence_data in result['sentences']:
-    print("Original:", sentence_data['original'])
-    print("Tokens:", sentence_data['tokens'])
-    print("POS Tags:", sentence_data['pos_tags'])
-    print("Stems:", sentence_data['stems'])
-    print()
-
-print("\n2. Named Entity Recognition")
-print("-" * 50)
-ner = NamedEntityRecognizer()
-entities = ner.extract_entities(text)
-for entity_type, entity_list in entities.items():
-    if entity_list:
-        print(f"{entity_type}:", entity_list)
-
-print("\n3. Topic Classification")
-print("-" * 50)
-topic_classifier = TopicClassifier()
-topics = topic_classifier.classify(text)
-print("Topics (with confidence):")
-for topic, confidence in topics[:3]:  # Top 3 topics
-    print(f"{topic}: {confidence:.2f}")
-
-print("\n4. Language Detection")
-print("-" * 50)
-lang_detector = LanguageDetector()
-languages = lang_detector.detect(text)
-print("Detected Languages (with confidence):")
-for lang, confidence in languages:
-    print(f"{lang}: {confidence:.2f}")
-
-print("\n5. Sentiment Analysis")
-print("-" * 50)
-sentiment_analyzer = SentimentAnalyzer()
-sentiment = sentiment_analyzer.analyze_sentiment(text)
-print("Sentiment Scores:")
-print(f"Polarity: {sentiment['polarity']:.2f}")
-print(f"Subjectivity: {sentiment['subjectivity']:.2f}")
-print(f"Confidence: {sentiment['confidence']:.2f}")
-
-print("\nEmotions:")
-emotions = sentiment_analyzer.analyze_emotions(text)
-for emotion, score in emotions:
-    if score > 0.1:  # Only show significant emotions
-        print(f"{emotion}: {score:.2f}")
-
-print("\n6. Keyword Extraction")
-print("-" * 50)
-keyword_extractor = KeywordExtractor()
-print("Keywords:")
-keywords = keyword_extractor.extract_keywords(text, num_keywords=5)
-for keyword, score in keywords:
-    print(f"{keyword}: {score:.2f}")
-
-print("\nKey Phrases:")
-keyphrases = keyword_extractor.extract_keyphrases(text, num_phrases=3)
-for phrase, score in keyphrases:
-    print(f"{phrase}: {score:.2f}")