webscout 4.1__py3-none-any.whl → 4.3__py3-none-any.whl

webscout/AIauto.py

@@ -1,8 +1,8 @@
 from webscout.AIbase import Provider, AsyncProvider
 from webscout.Provider.ThinkAnyAI import ThinkAnyAI
 from webscout.Provider.Xjai import Xjai
-from webscout.Provider.Llama2 import LLAMA2
-from webscout.Provider.Llama2 import AsyncLLAMA2
+from webscout.Provider.Llama import LLAMA2
+from webscout.Provider.Llama import AsyncLLAMA2
 from webscout.Provider.Leo import LEO
 from webscout.Provider.Leo import AsyncLEO
 from webscout.Provider.Koboldai import KOBOLDAI

webscout/AIutel.py

@@ -52,6 +52,7 @@ webai = [
    "vtlchat",
    "geminiflash",
    "geminipro",
+   "ollama"
 ]
 
 gpt4free_providers = [
@@ -196,7 +197,7 @@ class Conversation:
         """
         self.status = status
         self.max_tokens_to_sample = max_tokens
-        self.chat_history = ""
+        self.chat_history = self.intro
         self.history_format = "\nUser : %(user)s\nLLM :%(llm)s"
         self.file = filepath
         self.update_file = update_file
@@ -219,17 +220,16 @@ class Conversation:
         ), f"File '{filepath}' does not exist"
         if not os.path.isfile(filepath):
             logging.debug(f"Creating new chat-history file - '{filepath}'")
-            with open(filepath, "w") as fh:  # Try creating new file
-                # lets add intro here
+            with open(filepath, "w", encoding="utf-8") as fh:  # Try creating new file with UTF-8 encoding
                 fh.write(self.intro)
         else:
             logging.debug(f"Loading conversation from '{filepath}'")
-            with open(filepath) as fh:
+            with open(filepath, encoding="utf-8") as fh:  # Open with UTF-8 encoding
                 file_contents = fh.readlines()
                 if file_contents:
                     self.intro = file_contents[0]  # Presume first line is the intro.
                     self.chat_history = "\n".join(file_contents[1:])
-
+    
     def __trim_chat_history(self, chat_history: str, intro: str) -> str:
         """Ensures the len(prompt) and max_tokens_to_sample is not > 4096"""
         len_of_intro = len(intro)
@@ -242,7 +242,6 @@ class Conversation:
             # Remove head of total (n) of chat_history
             trimmed_chat_history = chat_history[truncate_at:]
             return "... " + trimmed_chat_history
-            # print(len(self.chat_history))
         else:
             return chat_history
 
@@ -280,12 +279,12 @@ class Conversation:
         new_history = self.history_format % dict(user=prompt, llm=response)
         if self.file and self.update_file:
             if os.path.exists(self.file):
-                with open(self.file, "w") as fh:
+                with open(self.file, "w", encoding="utf-8") as fh:  # Specify UTF-8 encoding
                     fh.write(self.intro + "\n" + new_history)
             else:
-                with open(self.file, "a") as fh:
+                with open(self.file, "a", encoding="utf-8") as fh:  # Specify UTF-8 encoding
                     fh.write(new_history)
-        self.chat_history += new_history
+            self.chat_history += new_history
 
 
 

webscout/Local/_version.py

@@ -1,3 +1,3 @@
 from llama_cpp import __version__ as __llama_cpp_version__
 
-__version__ = '4.1'
+__version__ = '4.3'

webscout/Provider/FreeGemini.py

@@ -0,0 +1,169 @@
+import time
+import uuid
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+import click
+import requests
+from requests import get
+from uuid import uuid4
+from re import findall
+from requests.exceptions import RequestException
+from curl_cffi.requests import get, RequestsError
+import g4f
+from random import randint
+from PIL import Image
+import io
+import re
+import json
+import yaml
+from ..AIutel import Optimizers
+from ..AIutel import Conversation
+from ..AIutel import AwesomePrompts, sanitize_stream
+from ..AIbase import Provider, AsyncProvider
+from webscout import exceptions
+from typing import Any, AsyncGenerator, Dict
+import logging
+import httpx
+
+class FreeGemini(Provider):
+    def __init__(
+        self,
+        is_conversation: bool = True,
+        max_tokens: int = 600,
+        timeout: int = 60,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+    ):
+        """Instantiates FreeGemini
+
+        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.
+        """
+        self.session = requests.Session()
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.chat_endpoint = "https://api.safone.dev/bard"
+        self.timeout = timeout
+        self.last_response = {}
+
+        self.headers = {
+            "accept": "application/json",
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36',
+        }
+
+        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.
+        """
+        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 = {"message": conversation_prompt}
+
+        response = self.session.post(
+            self.chat_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}"
+            )
+
+        resp = response.json()
+        message_load = self.get_message(resp)
+        self.conversation.update_chat_history(
+            prompt, message_load
+        )
+        return resp
+
+    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
+        """
+        return self.get_message(
+            self.ask(
+                prompt,
+                optimizer=optimizer,
+                conversationally=conversationally,
+            )
+        )
+
+    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["message"]

webscout/Provider/Llama.py

@@ -0,0 +1,211 @@
+import time
+import uuid
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+import click
+import requests
+from requests import get
+from uuid import uuid4
+from re import findall
+from requests.exceptions import RequestException
+from curl_cffi.requests import get, RequestsError
+import g4f
+from random import randint
+from PIL import Image
+import io
+import re
+import json
+import yaml
+from ..AIutel import Optimizers
+from ..AIutel import Conversation
+from ..AIutel import AwesomePrompts, sanitize_stream
+from ..AIbase import Provider, AsyncProvider
+from webscout import exceptions
+from typing import Any, AsyncGenerator, Dict
+import logging
+import httpx
+
+class LLAMA(Provider):
+    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,
+    ):
+        """Instantiates LLAMA
+
+        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): LLM model name. Defaults to "llama3-70b-8192".
+        """
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.timeout = timeout
+        self.last_response = {}
+        self.model = "llama3-70b-8192",
+        self.api_endpoint = "https://api.safone.dev/llama"
+        self.headers = {
+            "accept": "application/json",
+        }
+
+        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 = requests.Session()
+        self.session.proxies = proxies
+
+    def ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> dict | AsyncGenerator:
+        """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|AsyncGenerator : ai content
+        ```json
+        {
+           "text" : "print('How may I help 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 = {
+            "message": conversation_prompt
+        }
+
+        def for_stream():
+            response = self.session.get(
+                self.api_endpoint, params=payload, stream=True, timeout=self.timeout
+            )
+            if not response.ok:
+                raise exceptions.FailedToGenerateResponseError(
+                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+                )
+            
+            message_load = ""
+            for chunk in response.iter_lines():
+                try:
+                    resp = json.loads(chunk)
+                    message_load += resp['message']
+                    yield chunk if raw else dict(text=message_load)
+                    self.last_response.update(resp)
+                except:
+                    pass
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+
+        def for_non_stream():
+            response = self.session.get(
+                self.api_endpoint, params=payload, stream=False, 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 resp
+
+        return for_stream() if stream else for_non_stream()
+
+    def chat(
+        self,
+        prompt: str,
+        stream: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> str | AsyncGenerator:
+        """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["message"]

webscout/Provider/OLLAMA.py

@@ -0,0 +1,187 @@
+import time
+import uuid
+import requests
+from requests import get
+from uuid import uuid4
+from re import findall
+from requests.exceptions import RequestException
+from curl_cffi.requests import get, RequestsError
+import g4f
+from random import randint
+from PIL import Image
+import io
+import re
+import json
+import yaml
+from ..AIutel import Optimizers
+from ..AIutel import Conversation
+from ..AIutel import AwesomePrompts, sanitize_stream
+from ..AIbase import Provider, AsyncProvider
+from webscout import exceptions
+from typing import Any, AsyncGenerator, Dict
+import logging
+import httpx
+import ollama
+
+class OLLAMA(Provider):
+    def __init__(
+        self,
+        model: str = 'qwen2:0.5b',
+        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,
+    ):
+        """Instantiates Ollama
+
+        Args:
+            model (str, optional): Model name. Defaults to 'llama2'.
+            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.
+        """
+        self.model = model
+        self.is_conversation = is_conversation
+        self.max_tokens_to_sample = max_tokens
+        self.timeout = timeout
+        self.last_response = {}
+
+        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 ask(
+        self,
+        prompt: str,
+        stream: bool = False,
+        raw: bool = False,
+        optimizer: str = None,
+        conversationally: bool = False,
+    ) -> dict | AsyncGenerator:
+        """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|AsyncGenerator : ai content
+        ```json
+        {
+           "text" : "print('How may I help 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}"
+                )
+
+        def for_stream():
+            stream = ollama.chat(model=self.model, messages=[
+                {'role': 'user', 'content': conversation_prompt}
+            ], stream=True)
+
+            message_load = ""
+            for chunk in stream:
+                message_load += chunk['message']['content']
+                yield chunk['message']['content'] if raw else dict(text=message_load)
+            self.last_response.update(dict(text=message_load))
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+
+        def for_non_stream():
+            response = ollama.chat(model=self.model, messages=[
+                {'role': 'user', 'content': conversation_prompt}
+            ])
+            self.last_response.update(dict(text=response['message']['content']))
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+            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 | AsyncGenerator:
+        """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["text"]
+if __name__ == "__main__":
+    ollama_provider = OLLAMA(model="qwen2:0.5b")
+    response = ollama_provider.chat("What is the meaning of life?")
+    print(response)

webscout/Provider/__init__.py

@@ -2,8 +2,7 @@
 
 from .ThinkAnyAI import ThinkAnyAI
 from .Xjai import Xjai
-from .Llama2 import LLAMA2
-from .Llama2 import AsyncLLAMA2
+from .Llama import LLAMA
 from .Cohere import Cohere
 from .Reka import REKA
 from .Groq import GROQ
@@ -37,12 +36,12 @@ from .Deepinfra import DeepInfra, VLM, AsyncDeepInfra
 from .VTLchat import VTLchat
 from .Geminipro import GEMINIPRO
 from .Geminiflash import GEMINIFLASH
-
+from .OLLAMA import OLLAMA
+from .FreeGemini import FreeGemini
 __all__ = [
     'ThinkAnyAI',
     'Xjai',
-    'LLAMA2', 
-    'AsyncLLAMA2',
+    'LLAMA', 
     'Cohere',
     'REKA',
     'GROQ',
@@ -78,6 +77,8 @@ __all__ = [
     'OPENGPTv2',
     'GEMINIPRO',
     'GEMINIFLASH',
+    'OLLAMA',
+    'FreeGemini'
 
 
 ]

webscout/__init__.py

@@ -6,7 +6,7 @@ from .transcriber import transcriber
 from .voice import play_audio
 from .websx_search import WEBSX
 
-from .LLM import LLM
+from .LLM import VLM, LLM
 from .YTdownloader import *
 # from .Local import *
 import g4f
@@ -44,6 +44,7 @@ webai = [
    "vtlchat",
    "geminiflash",
    "geminipro",
+   "ollama"
 ]
 
 gpt4free_providers = [

webscout/async_providers.py

@@ -2,7 +2,6 @@ from webscout import AsyncPhindSearch
 from webscout import AsyncYEPCHAT
 from webscout import AsyncOPENGPT
 from webscout import AsyncOPENAI
-from webscout import AsyncLLAMA2
 from webscout import AsyncLEO
 from webscout import AsyncKOBOLDAI
 from webscout import AsyncGROQ
@@ -15,7 +14,6 @@ mapper: dict[str, object] = {
     "koboldai": AsyncKOBOLDAI,
     "blackboxai": AsyncBLACKBOXAI,
     "gpt4free": AsyncGPT4FREE,
-    "llama2": AsyncLLAMA2,
     "yepchat": AsyncYEPCHAT,
     "leo": AsyncLEO,
     "groq": AsyncGROQ,

webscout/version.py

@@ -1,2 +1,2 @@
-__version__ = "4.1"
+__version__ = "4.3"
 __prog__ = "webscout"

webscout/webai.py

@@ -831,7 +831,21 @@ class Main(cmd.Cmd):
                     act=awesome_prompt,
                     quiet=quiet,
                 )
+            elif provider == "ollama":
+                from webscout import OLLAMA
 
+                self.bot = OLLAMA(
+                    is_conversation=disable_conversation,
+                    max_tokens=max_tokens,
+                    timeout=timeout,
+                    intro=intro,
+                    filepath=filepath,
+                    update_file=update_file,
+                    proxies=proxies,
+                    history_offset=history_offset,
+                    act=awesome_prompt,
+                    model=getOr(model, "qwen2:0.5b")
+                )
             else:
                 raise NotImplementedError(
                     f"The provider `{provider}` is not yet implemented."

{webscout-4.1.dist-info → webscout-4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: webscout
-Version: 4.1
+Version: 4.3
 Summary: Search for anything using Google, DuckDuckGo, brave, qwant,  phind.com, Contains AI models, can transcribe yt videos, temporary email and phone number generation, has TTS support, webai (terminal gpt and open interpreter) and offline LLMs and more
 Author: OEvortex
 Author-email: helpingai5@gmail.com
@@ -1463,6 +1463,43 @@ print(response)
 
 ### 21. GeminiFlash and geminipro
 **Usage similar to other providers**
+
+### 22. `Ollama` - chat will AI models locally
+```python
+from webscout import OLLAMA
+ollama_provider = OLLAMA(model="qwen2:0.5b")
+response = ollama_provider.chat("What is the meaning of life?")
+print(response)
+```
+
+### 22. GROQ
+```python
+from webscout import GROQ
+ai = GROQ(api_key="")
+response = ai.chat("What is the meaning of life?")
+print(response)
+
+```
+
+### 23. Freegemini - chat with gemini for free
+```python
+from webscout import FreeGemini
+ai = FreeGemini()
+response = ai.chat("What is the meaning of life?")
+print(response)
+```
+
+### 24. LLama 70b - chat with meta's llama 3 70b
+```python
+
+from webscout import LLAMA
+
+llama = LLAMA()
+
+r = llama.chat("What is the meaning of life?")
+print(r)
+```
+
 ### `LLM` 
 ```python
 from webscout.LLM import LLM

{webscout-4.1.dist-info → webscout-4.3.dist-info}/RECORD

@@ -1,12 +1,12 @@
-webscout/AIauto.py,sha256=DycblRfFsQiLJVeP1sRQ0C-eNX7iO3a_y1wt8wChM8Y,20005
+webscout/AIauto.py,sha256=5ZMoS39Tyy1AZS6s_bgVnng-x9CmvHhWWNB4QMB5v9U,20003
 webscout/AIbase.py,sha256=GoHbN8r0gq2saYRZv6LA-Fr9Jlcjv80STKFXUq2ZeGU,4710
-webscout/AIutel.py,sha256=RIS66j1QP_7zCL7o0uCBbz0A20yunH4onTtTHkkIN-k,33959
+webscout/AIutel.py,sha256=1NQAchS2e6c1SrIq0efsVtX3ANZ5XI1hjKVHGpJG7OU,34076
 webscout/DWEBS.py,sha256=QLuT1IKu0lnwdl7W6c-ctBAO7Jj0Zk3PYm6-13BC7rU,25740
 webscout/LLM.py,sha256=LbGCZdJf8A5dwfoGS4tyy39tAh5BDdhMZP0ScKaaQfU,4184
 webscout/YTdownloader.py,sha256=uWpUWnw9pxeEGw9KJ_3XDyQ5gd38gH1dJpr-HJo4vzU,39144
-webscout/__init__.py,sha256=ibbt9571c1Kv5ZZV784j46i-lvR2WsTx8BXugHFQw2I,2198
+webscout/__init__.py,sha256=DX52bX0RKkXgKAWohQRyBKNdiamZmp2aQuTpsD5ohbY,2216
 webscout/__main__.py,sha256=ZtTRgsRjUi2JOvYFLF1ZCh55Sdoz94I-BS-TlJC7WDU,126
-webscout/async_providers.py,sha256=holBv5SxanxVXc_92CBBaXHlB2IakB_fHnhyZaFjYF8,684
+webscout/async_providers.py,sha256=MRj0klEhBYVQXnzZGG_15d0e-TPA0nOc2nn735H-wR4,622
 webscout/cli.py,sha256=EDxqTmcIshvhg9P0n2ZPaApj2-MEFY3uawS92zbBV_s,14705
 webscout/exceptions.py,sha256=YtIs-vXBwcjbt9TZ_wB7yI0dO7ANYIZAmEEeLmoQ2fI,487
 webscout/g4f.py,sha256=NNcnlOtIWV9R93UsBN4jBGBEJ9sJ-Np1WbgjkGVDcYc,24487
@@ -14,9 +14,9 @@ webscout/models.py,sha256=5iQIdtedT18YuTZ3npoG7kLMwcrKwhQ7928dl_7qZW0,692
 webscout/tempid.py,sha256=5oc3UbXhPGKxrMRTfRABT-V-dNzH_hOKWtLYM6iCWd4,5896
 webscout/transcriber.py,sha256=EddvTSq7dPJ42V3pQVnGuEiYQ7WjJ9uyeR9kMSxN7uY,20622
 webscout/utils.py,sha256=CxeXvp0rWIulUrEaPZMaNfg_tSuQLRSV8uuHA2chyKE,2603
-webscout/version.py,sha256=2jE62l770oovuLzelP3RWCvIn45U-DuZHeNGLvMIszs,44
+webscout/version.py,sha256=Pp5thQN3CvwDpubKz9MHn-UvDhuocamnBfB2VckwBGI,44
 webscout/voice.py,sha256=0QjXTHAQmCK07IDZXRc7JXem47cnPJH7u3X0sVP1-UQ,967
-webscout/webai.py,sha256=4_v28Tg25N71utqg34hFd0vF4zK1lEtaMXj-5H6hw1o,88311
+webscout/webai.py,sha256=LPn9XKvc5SLxJ68slMsPUXxzkzfa4b0kzsiJyWs-yq0,88897
 webscout/webscout_search.py,sha256=lFAot1-Qil_YfXieeLakDVDEX8Ckcima4ueXdOYwiMc,42804
 webscout/webscout_search_async.py,sha256=dooKGwLm0cwTml55Vy6NHPPY-nymEqX2h8laX94Zg5A,14537
 webscout/websx_search.py,sha256=n-qVwiHozJEF-GFRPcAfh4k1d_tscTmDe1dNL-1ngcU,12094
@@ -26,7 +26,7 @@ webscout/Extra/gguf.py,sha256=5zTNE5HxM_VQ5ONoocL8GG5fRXrgyLdEEjNzndG0oUw,7811
 webscout/Extra/weather.py,sha256=ocGwJYp5B9FwVWvIZ9wtoJTQsPFt64Vt8TitxJcdvAU,1687
 webscout/Extra/weather_ascii.py,sha256=sy6EEh2kN1CO1hKda8chD-mVCxH4p0NHyP7Uxr0-rgo,630
 webscout/Local/__init__.py,sha256=RN6klpbabPGNX2YzPm_hdeUcQvieUwvJt22uAO2RKSM,238
-webscout/Local/_version.py,sha256=cDatVldm_Tvfl9Vo4E6_GueNJoFGOBH6PA42hSdBFUA,83
+webscout/Local/_version.py,sha256=yH-h9AKl_KbJwMWeq0PDDOVI2FQ9NutjLDqcCGuAQ6I,83
 webscout/Local/formats.py,sha256=BiZZSoN3e8S6-S-ykBL9ogSUs0vK11GaZ3ghc9U8GRk,18994
 webscout/Local/model.py,sha256=T_bzNNrxEyOyLyhp6fKwiuVBBkXC2a37LzJVCxFIxOU,30710
 webscout/Local/rawdog.py,sha256=ojY_O8Vb1KvR34OwWdfLgllgaAK_7HMf64ElMATvCXs,36689
@@ -40,13 +40,15 @@ webscout/Provider/ChatGPTUK.py,sha256=qmuCb_a71GNE5LelOb5AKJUBndvj7soebiNey4VdDv
 webscout/Provider/Cohere.py,sha256=IXnRosYOaMAA65nvsKmN6ZkJGSdZFYQYBidzuNaCqX8,8711
 webscout/Provider/Deepinfra.py,sha256=kVnWARJdEtIeIsZwGw3POq8B2dO87bDcJso3uOeCeOA,18750
 webscout/Provider/Deepseek.py,sha256=pnOB44ObuOfAsoi_bUGUvha3tfwd0rTJ9rnX-14QkL4,10550
+webscout/Provider/FreeGemini.py,sha256=GbTJEG09vs5IKWKy9FqHBvDNKVq-HdMexOplctpb0RI,6426
 webscout/Provider/Gemini.py,sha256=_4DHWvlWuNAmVHPwHB1RjmryjTZZCthLa6lvPEHLvkQ,8451
 webscout/Provider/Geminiflash.py,sha256=1kMPA-ypi1gmJoms606Z7j_51znpdofM2aAyo4Hl7wU,5951
 webscout/Provider/Geminipro.py,sha256=nOifT5CRmnUg28iifSbOHkNLoKucLRr5zCj607mVrhw,5948
 webscout/Provider/Groq.py,sha256=QfgP3hKUcqq5vUA4Pzuu3HAgpJkKwLWNjjsnxtkCYd8,21094
 webscout/Provider/Koboldai.py,sha256=KwWx2yPlvT9BGx37iNvSbgzWkJ9I8kSOmeg7sL1hb0M,15806
 webscout/Provider/Leo.py,sha256=wbuDR-vFjLptfRC6yDlk74tINqNvCOzpISsK92lIgGg,19987
-webscout/Provider/Llama2.py,sha256=gVMotyiBaDSqliwuDtFefHoOBn9V5m5Ze_YVtV0trt8,17525
+webscout/Provider/Llama.py,sha256=F_srqtdo6ws03tnEaetZOfDolXrQEnLZaIxmQaY_tJQ,8052
+webscout/Provider/OLLAMA.py,sha256=G8sz_P7OZINFI1qGnpDhNPWU789Sv2cpDnShOA5Nbmw,7075
 webscout/Provider/OpenGPT.py,sha256=ZymwLgNJSPlGZHW3msMlnRR7NxmALqJw9yuToqrRrhw,35515
 webscout/Provider/Openai.py,sha256=SjfVOwY94unVnXhvN0Fkome-q2-wi4mPJk_vCGq5Fjc,20617
 webscout/Provider/Perplexity.py,sha256=CPdKqkdlVejXDcf1uycNO4LPCVNUADSCetvyJEGepSw,8826
@@ -58,10 +60,10 @@ webscout/Provider/VTLchat.py,sha256=_sErGr-wOi16ZAfiGOo0bPsAEMkjzzwreEsIqjIZMIU,
 webscout/Provider/Xjai.py,sha256=BIlk2ouz9Kh_0Gg9hPvTqhI7XtcmWdg5vHSX_4uGrIs,9039
 webscout/Provider/Yepchat.py,sha256=2Eit-A7w1ph1GQKNQuur_yaDzI64r0yBGxCIjDefJxQ,19875
 webscout/Provider/Youchat.py,sha256=fhMpt94pIPE_XDbC4z9xyfgA7NbkNE2wlRFJabsjv90,8069
-webscout/Provider/__init__.py,sha256=nFRM7vno2a7y2lG-7mDXvzytI8irb_loC0BPGZtrh7w,1923
-webscout-4.1.dist-info/LICENSE.md,sha256=9P0imsudI7MEvZe2pOcg8rKBn6E5FGHQ-riYozZI-Bk,2942
-webscout-4.1.dist-info/METADATA,sha256=a7qUaB7wlic1oP1ZEIX0p6BTJRpJvRbUqLv3QNgdgSo,56855
-webscout-4.1.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
-webscout-4.1.dist-info/entry_points.txt,sha256=Hh4YIIjvkqB9SVxZ2ri4DZUkgEu_WF_5_r_nZDIvfG8,73
-webscout-4.1.dist-info/top_level.txt,sha256=nYIw7OKBQDr_Z33IzZUKidRD3zQEo8jOJYkMVMeN334,9
-webscout-4.1.dist-info/RECORD,,
+webscout/Provider/__init__.py,sha256=j6lZqjLYext2a-KTnvGEvVm-D3jezHIlnanlj2H37FI,1962
+webscout-4.3.dist-info/LICENSE.md,sha256=9P0imsudI7MEvZe2pOcg8rKBn6E5FGHQ-riYozZI-Bk,2942
+webscout-4.3.dist-info/METADATA,sha256=Wh2IMCZhNgKcxsOqGNPriPzrEYoQ4uWfLakOnteemsc,57597
+webscout-4.3.dist-info/WHEEL,sha256=cpQTJ5IWu9CdaPViMhC9YzF8gZuS5-vlfoFihTBC86A,91
+webscout-4.3.dist-info/entry_points.txt,sha256=Hh4YIIjvkqB9SVxZ2ri4DZUkgEu_WF_5_r_nZDIvfG8,73
+webscout-4.3.dist-info/top_level.txt,sha256=nYIw7OKBQDr_Z33IzZUKidRD3zQEo8jOJYkMVMeN334,9
+webscout-4.3.dist-info/RECORD,,

webscout/Provider/Llama2.py

@@ -1,437 +0,0 @@
-import time
-import uuid
-from selenium import webdriver
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support import expected_conditions as EC
-from selenium.webdriver.support.ui import WebDriverWait
-import click
-import requests
-from requests import get
-from uuid import uuid4
-from re import findall
-from requests.exceptions import RequestException
-from curl_cffi.requests import get, RequestsError
-import g4f
-from random import randint
-from PIL import Image
-import io
-import re
-import json
-import yaml
-from ..AIutel import Optimizers
-from ..AIutel import Conversation
-from ..AIutel import AwesomePrompts, sanitize_stream
-from ..AIbase import  Provider, AsyncProvider
-from Helpingai_T2 import Perplexity
-from webscout import exceptions
-from typing import Any, AsyncGenerator, Dict
-import logging
-import httpx
-
-class AsyncLLAMA2(AsyncProvider):
-    def __init__(
-        self,
-        is_conversation: bool = True,
-        max_tokens: int = 800,
-        temperature: float = 0.75,
-        presence_penalty: int = 0,
-        frequency_penalty: int = 0,
-        top_p: float = 0.9,
-        model: str = "meta/meta-llama-3-70b-instruct",
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-    ):
-        """Instantiates LLAMA2
-
-        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 800.
-            temperature (float, optional): Charge of the generated text's randomness. Defaults to 0.75.
-            presence_penalty (int, optional): Chances of topic being repeated. Defaults to 0.
-            frequency_penalty (int, optional): Chances of word being repeated. Defaults to 0.
-            top_p (float, optional): Sampling threshold during inference time. Defaults to 0.9.
-            model (str, optional): LLM model name. Defaults to "meta/llama-2-70b-chat".
-            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.
-        """
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.model = model
-        self.temperature = temperature
-        self.presence_penalty = presence_penalty
-        self.frequency_penalty = frequency_penalty
-        self.top_p = top_p
-        self.chat_endpoint = "https://www.llama2.ai/api"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "Content-Type": "application/json",
-            "Referer": "https://www.llama2.ai/",
-            "Content-Type": "text/plain;charset=UTF-8",
-            "Origin": "https://www.llama2.ai",
-        }
-
-        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 = httpx.AsyncClient(
-            headers=self.headers,
-            proxies=proxies,
-        )
-
-    async def ask(
-        self,
-        prompt: str,
-        stream: bool = False,
-        raw: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-    ) -> dict | AsyncGenerator:
-        """Chat with AI asynchronously.
-
-        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|AsyncGeneraror[dict] : ai content
-        ```json
-        {
-           "text" : "How may I help 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}"
-                )
-
-        payload = {
-            "prompt": f"{conversation_prompt}<s>[INST] {prompt} [/INST]",
-            "model": self.model,
-            "systemPrompt": "You are a helpful assistant.",
-            "temperature": self.temperature,
-            "topP": self.top_p,
-            "maxTokens": self.max_tokens_to_sample,
-            "image": None,
-            "audio": None,
-        }
-
-        async def for_stream():
-            async with self.session.stream(
-                "POST", self.chat_endpoint, json=payload, timeout=self.timeout
-            ) as response:
-                if (
-                    not response.is_success
-                    or not response.headers.get("Content-Type")
-                    == "text/plain; charset=utf-8"
-                ):
-                    raise exceptions.FailedToGenerateResponseError(
-                        f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
-                    )
-                message_load: str = ""
-                async for value in response.aiter_lines():
-                    try:
-                        if bool(value.strip()):
-                            message_load += value + "\n"
-                            resp: dict = dict(text=message_load)
-                            yield value if raw else resp
-                            self.last_response.update(resp)
-                    except json.decoder.JSONDecodeError:
-                        pass
-            self.conversation.update_chat_history(
-                prompt, await self.get_message(self.last_response)
-            )
-
-        async def for_non_stream():
-            async for _ in for_stream():
-                pass
-            return self.last_response
-
-        return for_stream() if stream else await for_non_stream()
-
-    async def chat(
-        self,
-        prompt: str,
-        stream: bool = False,
-        optimizer: str = None,
-        conversationally: bool = False,
-    ) -> str | AsyncGenerator:
-        """Generate response `str` asynchronously.
-        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|AsyncGenerator: Response generated
-        """
-
-        async def for_stream():
-            async_ask = await self.ask(
-                prompt, True, optimizer=optimizer, conversationally=conversationally
-            )
-            async for response in async_ask:
-                yield await self.get_message(response)
-
-        async def for_non_stream():
-            return await self.get_message(
-                await self.ask(
-                    prompt,
-                    False,
-                    optimizer=optimizer,
-                    conversationally=conversationally,
-                )
-            )
-
-        return for_stream() if stream else await for_non_stream()
-
-    async def get_message(self, response: dict) -> str:
-        """Retrieves message only from response
-
-        Args:
-            response (str): Response generated by `self.ask`
-
-        Returns:
-            str: Message extracted
-        """
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response["text"]
-class LLAMA2(Provider):
-    def __init__(
-        self,
-        is_conversation: bool = True,
-        max_tokens: int = 800,
-        temperature: float = 0.75,
-        presence_penalty: int = 0,
-        frequency_penalty: int = 0,
-        top_p: float = 0.9,
-        model: str = "meta/meta-llama-3-70b-instruct",
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-    ):
-        """Instantiates LLAMA2
-
-        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 800.
-            temperature (float, optional): Charge of the generated text's randomness. Defaults to 0.75.
-            presence_penalty (int, optional): Chances of topic being repeated. Defaults to 0.
-            frequency_penalty (int, optional): Chances of word being repeated. Defaults to 0.
-            top_p (float, optional): Sampling threshold during inference time. Defaults to 0.9.
-            model (str, optional): LLM model name. Defaults to "meta/llama-2-70b-chat".
-            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.
-        """
-        self.session = requests.Session()
-        self.is_conversation = is_conversation
-        self.max_tokens_to_sample = max_tokens
-        self.model = model
-        self.temperature = temperature
-        self.presence_penalty = presence_penalty
-        self.frequency_penalty = frequency_penalty
-        self.top_p = top_p
-        self.chat_endpoint = "https://www.llama2.ai/api"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "Content-Type": "application/json",
-            "Referer": "https://www.llama2.ai/",
-            "Content-Type": "text/plain;charset=UTF-8",
-            "Origin": "https://www.llama2.ai",
-        }
-
-        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 help 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 = {
-            "prompt": f"{conversation_prompt}<s>[INST] {prompt} [/INST]",
-            "model": self.model,
-            "systemPrompt": "You are a helpful assistant.",
-            "temperature": self.temperature,
-            "topP": self.top_p,
-            "maxTokens": self.max_tokens_to_sample,
-            "image": None,
-            "audio": None,
-        }
-
-        def for_stream():
-            response = self.session.post(
-                self.chat_endpoint, json=payload, stream=True, timeout=self.timeout
-            )
-            if (
-                not response.ok
-                or not response.headers.get("Content-Type")
-                == "text/plain; charset=utf-8"
-            ):
-                raise exceptions.FailedToGenerateResponseError(
-                    f"Failed to generate response - ({response.status_code}, {response.reason})"
-                )
-
-            message_load: str = ""
-            for value in response.iter_lines(
-                decode_unicode=True,
-                delimiter="\n",
-                chunk_size=self.stream_chunk_size,
-            ):
-                try:
-                    if bool(value.strip()):
-                        message_load += value + "\n"
-                        resp: dict = dict(text=message_load)
-                        yield value if raw else resp
-                        self.last_response.update(resp)
-                except json.decoder.JSONDecodeError:
-                    pass
-            self.conversation.update_chat_history(
-                prompt, self.get_message(self.last_response)
-            )
-
-        def for_non_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 (str): Response generated by `self.ask`
-
-        Returns:
-            str: Message extracted
-        """
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        return response["text"]