webscout 8.2.7__py3-none-any.whl → 8.2.9__py3-none-any.whl

webscout/Provider/multichat.py

@@ -0,0 +1,364 @@
+from curl_cffi.requests import Session
+from curl_cffi import CurlError
+import json
+import uuid
+from typing import Any, Dict, Union
+from datetime import datetime
+from webscout.AIutel import Optimizers, Conversation, AwesomePrompts, sanitize_stream # Import sanitize_stream
+from webscout.AIbase import Provider
+from webscout import exceptions
+from webscout.litagent import LitAgent 
+
+# Model configurations
+MODEL_CONFIGS = {
+    "llama": {
+        "endpoint": "https://www.multichatai.com/api/chat/meta",
+        "models": {
+            "llama-3.3-70b-versatile": {"contextLength": 131072},
+            "llama-3.2-11b-vision-preview": {"contextLength": 32768},
+            "deepseek-r1-distill-llama-70b": {"contextLength": 128000},
+        },
+    },
+    "cohere": {
+        "endpoint": "https://www.multichatai.com/api/chat/cohere",
+        "models": {
+            "command-r": {"contextLength": 128000},
+            "command": {"contextLength": 4096},
+        },
+    },
+    "google": {
+        "endpoint": "https://www.multichatai.com/api/chat/google",
+        "models": {
+            "gemini-1.5-flash-002": {"contextLength": 1048576},
+            "gemma2-9b-it": {"contextLength": 8192},
+            "gemini-2.0-flash": {"contextLength": 128000},
+                    },
+        "message_format": "parts",
+    },
+    "deepinfra": {
+        "endpoint": "https://www.multichatai.com/api/chat/deepinfra",
+        "models": {
+            "Sao10K/L3.1-70B-Euryale-v2.2": {"contextLength": 8192},
+            "Gryphe/MythoMax-L2-13b": {"contextLength": 8192},
+            "nvidia/Llama-3.1-Nemotron-70B-Instruct": {"contextLength": 131072},
+            "deepseek-ai/DeepSeek-V3": {"contextLength": 32000},
+            "meta-llama/Meta-Llama-3.1-405B-Instruct": {"contextLength": 131072},
+            "NousResearch/Hermes-3-Llama-3.1-405B": {"contextLength": 131072},
+            "gemma-2-27b-it": {"contextLength": 8192},
+        },
+    },
+    "mistral": {
+        "endpoint": "https://www.multichatai.com/api/chat/mistral",
+        "models": {
+            "mistral-small-latest": {"contextLength": 32000},
+            "codestral-latest": {"contextLength": 32000},
+            "open-mistral-7b": {"contextLength": 8000},
+            "open-mixtral-8x7b": {"contextLength": 8000},
+        },
+    },
+    "alibaba": {
+        "endpoint": "https://www.multichatai.com/api/chat/alibaba",
+        "models": {
+            "Qwen/Qwen2.5-72B-Instruct": {"contextLength": 32768},
+            "Qwen/Qwen2.5-Coder-32B-Instruct": {"contextLength": 32768},
+            "Qwen/QwQ-32B-Preview": {"contextLength": 32768},
+        },
+    },
+}
+
+class MultiChatAI(Provider):
+    """
+    A class to interact with the MultiChatAI API.
+    """
+    AVAILABLE_MODELS = [
+        # Llama Models
+        "llama-3.3-70b-versatile",
+        "llama-3.2-11b-vision-preview",
+        "deepseek-r1-distill-llama-70b",
+        
+        # Cohere Models
+        # "command-r", # >>>> NOT WORKING
+        # "command", # >>>> NOT WORKING
+        
+        # Google Models
+        # "gemini-1.5-flash-002", #>>>> NOT WORKING
+        "gemma2-9b-it",
+        "gemini-2.0-flash",
+        
+        # DeepInfra Models
+        "Sao10K/L3.1-70B-Euryale-v2.2",
+        "Gryphe/MythoMax-L2-13b",
+        "nvidia/Llama-3.1-Nemotron-70B-Instruct",
+        "deepseek-ai/DeepSeek-V3",
+        "meta-llama/Meta-Llama-3.1-405B-Instruct",
+        "NousResearch/Hermes-3-Llama-3.1-405B",
+        # "gemma-2-27b-it", # >>>> NOT WORKING
+        
+        # Mistral Models
+        # "mistral-small-latest", # >>>> NOT WORKING
+        # "codestral-latest", # >>>> NOT WORKING
+        # "open-mistral-7b", # >>>> NOT WORKING
+        # "open-mixtral-8x7b", # >>>> NOT WORKING
+        
+        # Alibaba Models
+        "Qwen/Qwen2.5-72B-Instruct",
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "Qwen/QwQ-32B-Preview"
+    ]
+
+    def __init__(
+        self,
+        is_conversation: bool = True,
+        max_tokens: int = 4000, # Note: max_tokens is not directly used by this API
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+        model: str = "llama-3.3-70b-versatile",
+        system_prompt: str = "You are a friendly, helpful AI assistant.",
+        temperature: float = 0.5,
+        presence_penalty: int = 0, # Note: presence_penalty is not used by this API
+        frequency_penalty: int = 0, # Note: frequency_penalty is not used by this API
+        top_p: float = 1 # Note: top_p is not used by this API
+    ):
+        """Initializes the MultiChatAI API client."""
+        if model not in self.AVAILABLE_MODELS:
+            raise ValueError(f"Invalid model: {model}. Choose from: {self.AVAILABLE_MODELS}")
+        # Initialize curl_cffi Session
+        self.session = Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.timeout = timeout
+        self.last_response = {}
+        self.model = model
+        self.system_prompt = system_prompt
+        self.temperature = temperature
+        self.presence_penalty = presence_penalty
+        self.frequency_penalty = frequency_penalty
+        self.top_p = top_p
+        
+        # Initialize LitAgent for user agent generation (keep if needed for other headers)
+        self.agent = LitAgent()
+        
+        self.headers = {
+            "accept": "*/*",
+            "accept-language": "en-US,en;q=0.9",
+            "content-type": "text/plain;charset=UTF-8", # Keep content-type
+            "origin": "https://www.multichatai.com",
+            "referer": "https://www.multichatai.com/",
+            "user-agent": self.agent.random(),
+            # Add sec-ch-ua headers if needed for impersonation consistency
+        }
+        
+        # Update curl_cffi session headers, proxies, and cookies
+        self.session.headers.update(self.headers)
+        self.session.proxies = proxies # Assign proxies directly
+        # Set cookies on the session object for curl_cffi
+        self.session.cookies.set("session", uuid.uuid4().hex)
+
+        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.provider = self._get_provider_from_model(self.model)
+        self.model_name = self.model
+
+    def _get_endpoint(self) -> str:
+        """Get the API endpoint for the current provider."""
+        return MODEL_CONFIGS[self.provider]["endpoint"]
+
+    def _get_chat_settings(self) -> Dict[str, Any]:
+        """Get chat settings for the current model."""
+        base_settings = MODEL_CONFIGS[self.provider]["models"][self.model_name]
+        return {
+            "model": self.model,
+            "prompt": self.system_prompt,
+            "temperature": self.temperature,
+            "contextLength": base_settings["contextLength"],
+            "includeProfileContext": True,
+            "includeWorkspaceInstructions": True,
+            "embeddingsProvider": "openai"
+        }
+
+    def _get_system_message(self) -> str:
+        """Generate system message with current date."""
+        current_date = datetime.now().strftime("%d/%m/%Y")
+        return f"Today is {current_date}.\n\nUser Instructions:\n{self.system_prompt}"
+
+    def _build_messages(self, conversation_prompt: str) -> list:
+        """Build messages array based on provider type."""
+        if self.provider == "google":
+            return [
+                {"role": "user", "parts": self._get_system_message()},
+                {"role": "model", "parts": "I will follow your instructions."},
+                {"role": "user", "parts": conversation_prompt}
+            ]
+        else:
+            return [
+                {"role": "system", "content": self._get_system_message()},
+                {"role": "user", "content": conversation_prompt}
+            ]
+
+    def _get_provider_from_model(self, model: str) -> str:
+        """Determine the provider based on the model name."""
+        for provider, config in MODEL_CONFIGS.items():
+            if model in config["models"]:
+                return provider
+        
+        available_models = []
+        for provider, config in MODEL_CONFIGS.items():
+            for model_name in config["models"].keys():
+                available_models.append(f"{provider}/{model_name}")
+        
+        error_msg = f"Invalid model: {model}\nAvailable models: {', '.join(available_models)}"
+        raise ValueError(error_msg)
+
+    def _make_request(self, payload: Dict[str, Any]) -> Any:
+        """Make the API request with proper error handling."""
+        try:
+            # Use curl_cffi session post with impersonate
+            # Cookies are handled by the session
+            response = self.session.post(
+                self._get_endpoint(),
+                # headers are set on the session
+                json=payload,
+                timeout=self.timeout,
+                # proxies are set on the session
+                impersonate="chrome110" # Use a common impersonation profile
+            )
+            response.raise_for_status() # Check for HTTP errors
+            return response
+        except CurlError as e: # Catch CurlError
+            raise exceptions.FailedToGenerateResponseError(f"API request failed (CurlError): {e}") from e
+        except Exception as e: # Catch other potential exceptions (like HTTPError)
+            err_text = getattr(e, 'response', None) and getattr(e.response, 'text', '')
+            raise exceptions.FailedToGenerateResponseError(f"API request failed ({type(e).__name__}): {e} - {err_text}") from e
+
+    def ask(
+        self,
+        prompt: str,
+        raw: bool = False, # Keep raw param for interface consistency
+        optimizer: str = None,
+        conversationally: bool = False,
+        # Add stream parameter for consistency, though API doesn't stream
+        stream: bool = False 
+    ) -> Dict[str, Any]:
+        """Sends a prompt to the MultiChatAI 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:
+                error_msg = f"Optimizer is not one of {self.__available_optimizers}"
+                raise exceptions.FailedToGenerateResponseError(error_msg)
+
+        payload = {
+            "chatSettings": self._get_chat_settings(),
+            "messages": self._build_messages(conversation_prompt),
+            "customModelId": "",
+        }
+
+        # API does not stream, implement non-stream logic directly
+        response = self._make_request(payload)
+        try:
+            # Use response.text which is already decoded
+            response_text_raw = response.text # Get raw text
+
+            # Process the text using sanitize_stream (even though it's not streaming)
+            processed_stream = sanitize_stream(
+                data=response_text_raw,
+                intro_value=None, # No prefix
+                to_json=False     # It's plain text
+            )
+            # Aggregate the single result
+            full_response = "".join(list(processed_stream)).strip()
+
+            self.last_response = {"text": full_response} # Store processed text
+            self.conversation.update_chat_history(prompt, full_response)
+            # Return dict or raw string based on raw flag
+            return full_response if raw else self.last_response
+        except Exception as e: # Catch potential errors during text processing
+            raise exceptions.FailedToGenerateResponseError(f"Failed to process response: {e}") from e
+
+    def chat(
+        self,
+        prompt: str,
+        optimizer: str = None,
+        conversationally: bool = False,
+        # Add stream parameter for consistency
+        stream: bool = False
+    ) -> str:
+        """Generate response."""
+        # Since ask() now handles both stream=True/False by returning the full response dict/str:
+        response_data = self.ask(
+            prompt, 
+            stream=False, # Call ask in non-stream mode internally
+            raw=False, # Ensure ask returns dict
+            optimizer=optimizer, 
+            conversationally=conversationally
+        )
+        # If stream=True was requested, simulate streaming by yielding the full message at once
+        if stream:
+            def stream_wrapper():
+                yield self.get_message(response_data)
+            return stream_wrapper()
+        else:
+            # If stream=False, return the full message directly
+            return self.get_message(response_data)
+
+    def get_message(self, response: Union[Dict[str, Any], str]) -> str:
+        """
+        Retrieves message from response.
+        
+        Args:
+            response (Union[Dict[str, Any], str]): The response to extract the message from
+            
+        Returns:
+            str: The extracted message text
+        """
+        if isinstance(response, dict):
+            return response.get("text", "")
+        return str(response)
+
+if __name__ == "__main__":
+    print("-" * 80)
+    print(f"{'Model':<50} {'Status':<10} {'Response'}")
+    print("-" * 80)
+    
+    # Test all available models
+    working = 0
+    total = len(MultiChatAI.AVAILABLE_MODELS)
+    
+    for model in MultiChatAI.AVAILABLE_MODELS:
+        try:
+            test_ai = MultiChatAI(model=model, timeout=60)
+            response = test_ai.chat("Say 'Hello' in one word")
+            response_text = response
+            
+            if response_text and len(response_text.strip()) > 0:
+                status = "✓"
+                # Truncate response if too long
+                display_text = response_text.strip()[:50] + "..." if len(response_text.strip()) > 50 else response_text.strip()
+            else:
+                status = "✗"
+                display_text = "Empty or invalid response"
+            print(f"{model:<50} {status:<10} {display_text}")
+        except Exception as e:
+            print(f"{model:<50} {'✗':<10} {str(e)}")

webscout/Provider/oivscode.py

@@ -0,0 +1,309 @@
+import secrets
+import requests
+import json
+import random
+import string
+from typing import Union, Any, Dict, Optional, Generator
+
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation
+from webscout.AIutel import AwesomePrompts, sanitize_stream
+from webscout.AIbase import Provider
+from webscout import exceptions
+
+
+class oivscode(Provider):
+    """
+    A class to interact with a test API.
+    """
+    AVAILABLE_MODELS = [
+        "*",
+        "Qwen/Qwen2.5-72B-Instruct-Turbo",
+        "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "claude-3-5-sonnet-20240620",
+        "claude-3-5-sonnet-20241022",
+        "claude-3-7-sonnet-20250219",
+        "custom/blackbox-base",
+        "custom/blackbox-pro",
+        "custom/blackbox-pro-designer",
+        "custom/blackbox-pro-plus",
+        "deepseek-r1",
+        "deepseek-v3",
+        "deepseek/deepseek-chat",
+        "gemini-2.5-pro-preview-03-25",
+        "gpt-4o-mini",
+        "grok-3-beta",
+        "image-gen",
+        "llama-4-maverick-17b-128e-instruct-fp8",
+        "o1",
+        "o3-mini",
+        "o4-mini",
+        "transcribe",
+        "anthropic/claude-sonnet-4"
+    ]
+
+
+    def __init__(
+        self,
+        is_conversation: bool = True,
+        max_tokens: int = 1024,
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+        model: str = "claude-3-5-sonnet-20240620",
+        system_prompt: str = "You are a helpful AI assistant.",
+        
+    ):
+        """
+        Initializes the oivscode with given parameters.
+        """
+        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_endpoints = [
+            "https://oi-vscode-server.onrender.com/v1/chat/completions",
+            "https://oi-vscode-server-2.onrender.com/v1/chat/completions",
+            "https://oi-vscode-server-5.onrender.com/v1/chat/completions",
+            "https://oi-vscode-server-0501.onrender.com/v1/chat/completions"
+        ]
+        self.api_endpoint = random.choice(self.api_endpoints)
+        self.timeout = timeout
+        self.last_response = {}
+        self.model = model
+        self.system_prompt = system_prompt
+        self.headers = {
+            "accept": "*/*",
+            "accept-language": "en-US,en;q=0.9,en-GB;q=0.8,en-IN;q=0.7",
+            "cache-control": "no-cache",
+            "content-type": "application/json",
+            "pragma": "no-cache",
+            "priority": "u=1, i",
+            "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-site",
+        }
+        self.userid = ''.join(secrets.choice(string.ascii_letters + string.digits) for _ in range(21))
+        self.headers["userid"] = self.userid
+
+
+        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 _post_with_failover(self, payload, stream, timeout):
+        """Try all endpoints until one succeeds, else raise last error."""
+        endpoints = self.api_endpoints.copy()
+        random.shuffle(endpoints)
+        last_exception = None
+        for endpoint in endpoints:
+            try:
+                response = self.session.post(endpoint, json=payload, stream=stream, timeout=timeout)
+                if not response.ok:
+                    last_exception = exceptions.FailedToGenerateResponseError(
+                        f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+                    )
+                    continue
+                return response
+            except Exception as e:
+                last_exception = e
+                continue
+        if last_exception:
+            raise last_exception
+        raise exceptions.FailedToGenerateResponseError("All API endpoints failed.")
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> Union[Dict[str, Any], Generator[Any, None, None]]:
+        """Chat with AI (DeepInfra-style streaming and non-streaming)"""
+        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 = {
+            "model": self.model,
+            "messages": [
+                {"role": "system", "content": self.system_prompt},
+                {"role": "user", "content": conversation_prompt},
+            ],
+            "stream": stream
+        }
+
+        def for_stream():
+            streaming_text = ""
+            try:
+                response = self._post_with_failover(payload, stream=True, timeout=self.timeout)
+                response.raise_for_status()
+                # Use sanitize_stream for robust OpenAI-style streaming
+                processed_stream = sanitize_stream(
+                    data=response.iter_content(chunk_size=None),
+                    intro_value="data:",
+                    to_json=True,
+                    skip_markers=["[DONE]"],
+                    content_extractor=lambda chunk: chunk.get("choices", [{}])[0].get("delta", {}).get("content") if isinstance(chunk, dict) else None,
+                    yield_raw_on_error=False
+                )
+                for content_chunk in processed_stream:
+                    if content_chunk and isinstance(content_chunk, str):
+                        streaming_text += content_chunk
+                        resp = dict(text=content_chunk)
+                        yield resp if not raw else content_chunk
+            except Exception as e:
+                raise exceptions.FailedToGenerateResponseError(f"Streaming request failed: {e}") from e
+            finally:
+                if streaming_text:
+                    self.last_response = {"text": streaming_text}
+                    self.conversation.update_chat_history(prompt, streaming_text)
+
+        def for_non_stream():
+            try:
+                response = self._post_with_failover(payload, stream=False, timeout=self.timeout)
+                response.raise_for_status()
+                response_text = response.text
+                processed_stream = sanitize_stream(
+                    data=response_text,
+                    to_json=True,
+                    intro_value=None,
+                    content_extractor=lambda chunk: chunk.get("choices", [{}])[0].get("message", {}).get("content") if isinstance(chunk, dict) else None,
+                    yield_raw_on_error=False
+                )
+                content = next(processed_stream, None)
+                content = content if isinstance(content, str) else ""
+                self.last_response = {"text": content}
+                self.conversation.update_chat_history(prompt, content)
+                return self.last_response if not raw else content
+            except Exception as e:
+                raise exceptions.FailedToGenerateResponseError(f"Non-streaming request failed: {e}") from e
+
+        return for_stream() if stream else for_non_stream()
+
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> Union[str, Generator[str, None, None]]:
+        """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 content from response, handling both streaming and non-streaming formats."""
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        # Streaming chunk: choices[0]["delta"]["content"]
+        if "choices" in response and response["choices"]:
+            choice = response["choices"][0]
+            if "delta" in choice and "content" in choice["delta"]:
+                return choice["delta"]["content"]
+            if "message" in choice and "content" in choice["message"]:
+                return choice["message"]["content"]
+        # Fallback for non-standard or legacy responses
+        if "text" in response:
+            return response["text"]
+        return ""
+
+    # def fetch_available_models(self):
+    #     """Fetches available models from the /models endpoint of all API endpoints and prints models per endpoint."""
+    #     endpoints = self.api_endpoints.copy()
+    #     random.shuffle(endpoints)
+    #     results = {}
+    #     errors = []
+    #     for endpoint in endpoints:
+    #         models_url = endpoint.replace('/v1/chat/completions', '/v1/models')
+    #         try:
+    #             response = self.session.get(models_url, timeout=self.timeout)
+    #             if response.ok:
+    #                 data = response.json()
+    #                 if isinstance(data, dict) and "data" in data:
+    #                     models = [m["id"] if isinstance(m, dict) and "id" in m else m for m in data["data"]]
+    #                 elif isinstance(data, list):
+    #                     models = data
+    #                 else:
+    #                     models = list(data.keys()) if isinstance(data, dict) else []
+    #                 results[models_url] = models
+    #             else:
+    #                 errors.append(f"Failed to fetch models from {models_url}: {response.status_code} {response.text}")
+    #         except Exception as e:
+    #             errors.append(f"Error fetching from {models_url}: {e}")
+    #     if results:
+    #         for url, models in results.items():
+    #             print(f"Models from {url}:")
+    #             if models:
+    #                 for m in sorted(models):
+    #                     print(f"  {m}")
+    #             else:
+    #                 print("  No models found.")
+    #         return results
+    #     else:
+    #         print("No models found from any endpoint.")
+    #         for err in errors:
+    #             print(err)
+    #         return {}
+
+if __name__ == "__main__":
+    from rich import print
+    chatbot = oivscode()
+    print(chatbot.fetch_available_models())
+    response = chatbot.chat(input(">>> "), stream=True)
+    for chunk in response:
+        print(chunk, end="", flush=True)