webscout 2.8__py3-none-any.whl → 3.0__py3-none-any.whl

webscout/Provider/Groq.py

@@ -1,512 +1,512 @@
-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 GROQ(Provider):
-    def __init__(
-        self,
-        api_key: str,
-        is_conversation: bool = True,
-        max_tokens: int = 600,
-        temperature: float = 1,
-        presence_penalty: int = 0,
-        frequency_penalty: int = 0,
-        top_p: float = 1,
-        model: str = "mixtral-8x7b-32768",
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-    ):
-        """Instantiates GROQ
-
-        Args:
-            api_key (key): GROQ's API key.
-            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.
-            temperature (float, optional): Charge of the generated text's randomness. Defaults to 1.
-            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 0.999.
-            model (str, optional): LLM model name. Defaults to "gpt-3.5-turbo".
-            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.api_key = api_key
-        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://api.groq.com/openai/v1/chat/completions"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}",
-        }
-
-        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
-        {
-            "id": "c0c8d139-d2b9-9909-8aa1-14948bc28404",
-            "object": "chat.completion",
-            "created": 1710852779,
-            "model": "mixtral-8x7b-32768",
-            "choices": [
-                {
-                    "index": 0,
-                    "message": {
-                        "role": "assistant",
-                        "content": "Hello! How can I assist you today? I'm here to help answer your questions and engage in conversation on a wide variety of topics. Feel free to ask me anything!"
-                    },
-                    "logprobs": null,
-                    "finish_reason": "stop"
-                }
-            ],
-            "usage": {
-                "prompt_tokens": 47,
-                "prompt_time": 0.03,
-                "completion_tokens": 37,
-                "completion_time": 0.069,
-                "total_tokens": 84,
-                "total_time": 0.099
-            },
-            "system_fingerprint": null
-        }
-                ```
-        """
-        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 = {
-            "frequency_penalty": self.frequency_penalty,
-            "messages": [{"content": conversation_prompt, "role": "user"}],
-            "model": self.model,
-            "presence_penalty": self.presence_penalty,
-            "stream": stream,
-            "temperature": self.temperature,
-            "top_p": self.top_p,
-        }
-
-        def for_stream():
-            response = self.session.post(
-                self.chat_endpoint, json=payload, stream=True, timeout=self.timeout
-            )
-            if not response.ok:
-                raise Exception(
-                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
-                )
-
-            message_load = ""
-            for value in response.iter_lines(
-                decode_unicode=True,
-                delimiter="" if raw else "data:",
-                chunk_size=self.stream_chunk_size,
-            ):
-                try:
-                    resp = json.loads(value)
-                    incomplete_message = self.get_message(resp)
-                    if incomplete_message:
-                        message_load += incomplete_message
-                        resp["choices"][0]["delta"]["content"] = message_load
-                        self.last_response.update(resp)
-                        yield value if raw else resp
-                    elif raw:
-                        yield value
-                except json.decoder.JSONDecodeError:
-                    pass
-            self.conversation.update_chat_history(
-                prompt, self.get_message(self.last_response)
-            )
-
-        def for_non_stream():
-            response = self.session.post(
-                self.chat_endpoint, json=payload, stream=False, timeout=self.timeout
-            )
-            if not response.ok:
-                raise Exception(
-                    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:
-        """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"
-        try:
-            if response["choices"][0].get("delta"):
-                return response["choices"][0]["delta"]["content"]
-            return response["choices"][0]["message"]["content"]
-        except KeyError:
-            return ""
-class AsyncGROQ(AsyncProvider):
-    def __init__(
-        self,
-        api_key: str,
-        is_conversation: bool = True,
-        max_tokens: int = 600,
-        temperature: float = 1,
-        presence_penalty: int = 0,
-        frequency_penalty: int = 0,
-        top_p: float = 1,
-        model: str = "mixtral-8x7b-32768",
-        timeout: int = 30,
-        intro: str = None,
-        filepath: str = None,
-        update_file: bool = True,
-        proxies: dict = {},
-        history_offset: int = 10250,
-        act: str = None,
-    ):
-        """Instantiates GROQ
-
-        Args:
-            api_key (key): GROQ's API key.
-            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.
-            temperature (float, optional): Charge of the generated text's randomness. Defaults to 1.
-            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 0.999.
-            model (str, optional): LLM model name. Defaults to "gpt-3.5-turbo".
-            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.api_key = api_key
-        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://api.groq.com/openai/v1/chat/completions"
-        self.stream_chunk_size = 64
-        self.timeout = timeout
-        self.last_response = {}
-        self.headers = {
-            "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}",
-        }
-
-        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|AsyncGenerator : ai content
-                ```json
-        {
-            "id": "c0c8d139-d2b9-9909-8aa1-14948bc28404",
-            "object": "chat.completion",
-            "created": 1710852779,
-            "model": "mixtral-8x7b-32768",
-            "choices": [
-                {
-                    "index": 0,
-                    "message": {
-                        "role": "assistant",
-                        "content": "Hello! How can I assist you today? I'm here to help answer your questions and engage in conversation on a wide variety of topics. Feel free to ask me anything!"
-                    },
-                    "logprobs": null,
-                    "finish_reason": "stop"
-                }
-            ],
-            "usage": {
-                "prompt_tokens": 47,
-                "prompt_time": 0.03,
-                "completion_tokens": 37,
-                "completion_time": 0.069,
-                "total_tokens": 84,
-                "total_time": 0.099
-            },
-            "system_fingerprint": null
-        }
-                ```
-        """
-        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 = {
-            "frequency_penalty": self.frequency_penalty,
-            "messages": [{"content": conversation_prompt, "role": "user"}],
-            "model": self.model,
-            "presence_penalty": self.presence_penalty,
-            "stream": stream,
-            "temperature": self.temperature,
-            "top_p": self.top_p,
-        }
-
-        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:
-                    raise Exception(
-                        f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
-                    )
-
-                message_load = ""
-                intro_value = "data:"
-                async for value in response.aiter_lines():
-                    try:
-                        if value.startswith(intro_value):
-                            value = value[len(intro_value) :]
-                        resp = json.loads(value)
-                        incomplete_message = await self.get_message(resp)
-                        if incomplete_message:
-                            message_load += incomplete_message
-                            resp["choices"][0]["delta"]["content"] = message_load
-                            self.last_response.update(resp)
-                            yield value if raw else resp
-                        elif raw:
-                            yield value
-                    except json.decoder.JSONDecodeError:
-                        pass
-            self.conversation.update_chat_history(
-                prompt, await self.get_message(self.last_response)
-            )
-
-        async def for_non_stream():
-            response = httpx.post(
-                self.chat_endpoint, json=payload, timeout=self.timeout
-            )
-            if not response.is_success:
-                raise Exception(
-                    f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
-                )
-            resp = response.json()
-            self.last_response.update(resp)
-            self.conversation.update_chat_history(
-                prompt, await self.get_message(self.last_response)
-            )
-            return resp
-
-        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 (dict): Response generated by `self.ask`
-
-        Returns:
-            str: Message extracted
-        """
-        assert isinstance(response, dict), "Response should be of dict data-type only"
-        try:
-            if response["choices"][0].get("delta"):
-                return response["choices"][0]["delta"]["content"]
-            return response["choices"][0]["message"]["content"]
-        except KeyError:
+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 GROQ(Provider):
+    def __init__(
+        self,
+        api_key: str,
+        is_conversation: bool = True,
+        max_tokens: int = 600,
+        temperature: float = 1,
+        presence_penalty: int = 0,
+        frequency_penalty: int = 0,
+        top_p: float = 1,
+        model: str = "mixtral-8x7b-32768",
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+    ):
+        """Instantiates GROQ
+
+        Args:
+            api_key (key): GROQ's API key.
+            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.
+            temperature (float, optional): Charge of the generated text's randomness. Defaults to 1.
+            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 0.999.
+            model (str, optional): LLM model name. Defaults to "gpt-3.5-turbo".
+            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.api_key = api_key
+        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://api.groq.com/openai/v1/chat/completions"
+        self.stream_chunk_size = 64
+        self.timeout = timeout
+        self.last_response = {}
+        self.headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+        }
+
+        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
+        {
+            "id": "c0c8d139-d2b9-9909-8aa1-14948bc28404",
+            "object": "chat.completion",
+            "created": 1710852779,
+            "model": "mixtral-8x7b-32768",
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": "Hello! How can I assist you today? I'm here to help answer your questions and engage in conversation on a wide variety of topics. Feel free to ask me anything!"
+                    },
+                    "logprobs": null,
+                    "finish_reason": "stop"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": 47,
+                "prompt_time": 0.03,
+                "completion_tokens": 37,
+                "completion_time": 0.069,
+                "total_tokens": 84,
+                "total_time": 0.099
+            },
+            "system_fingerprint": null
+        }
+                ```
+        """
+        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 = {
+            "frequency_penalty": self.frequency_penalty,
+            "messages": [{"content": conversation_prompt, "role": "user"}],
+            "model": self.model,
+            "presence_penalty": self.presence_penalty,
+            "stream": stream,
+            "temperature": self.temperature,
+            "top_p": self.top_p,
+        }
+
+        def for_stream():
+            response = self.session.post(
+                self.chat_endpoint, json=payload, stream=True, timeout=self.timeout
+            )
+            if not response.ok:
+                raise Exception(
+                    f"Failed to generate response - ({response.status_code}, {response.reason}) - {response.text}"
+                )
+
+            message_load = ""
+            for value in response.iter_lines(
+                decode_unicode=True,
+                delimiter="" if raw else "data:",
+                chunk_size=self.stream_chunk_size,
+            ):
+                try:
+                    resp = json.loads(value)
+                    incomplete_message = self.get_message(resp)
+                    if incomplete_message:
+                        message_load += incomplete_message
+                        resp["choices"][0]["delta"]["content"] = message_load
+                        self.last_response.update(resp)
+                        yield value if raw else resp
+                    elif raw:
+                        yield value
+                except json.decoder.JSONDecodeError:
+                    pass
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+
+        def for_non_stream():
+            response = self.session.post(
+                self.chat_endpoint, json=payload, stream=False, timeout=self.timeout
+            )
+            if not response.ok:
+                raise Exception(
+                    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:
+        """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"
+        try:
+            if response["choices"][0].get("delta"):
+                return response["choices"][0]["delta"]["content"]
+            return response["choices"][0]["message"]["content"]
+        except KeyError:
+            return ""
+class AsyncGROQ(AsyncProvider):
+    def __init__(
+        self,
+        api_key: str,
+        is_conversation: bool = True,
+        max_tokens: int = 600,
+        temperature: float = 1,
+        presence_penalty: int = 0,
+        frequency_penalty: int = 0,
+        top_p: float = 1,
+        model: str = "mixtral-8x7b-32768",
+        timeout: int = 30,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        proxies: dict = {},
+        history_offset: int = 10250,
+        act: str = None,
+    ):
+        """Instantiates GROQ
+
+        Args:
+            api_key (key): GROQ's API key.
+            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.
+            temperature (float, optional): Charge of the generated text's randomness. Defaults to 1.
+            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 0.999.
+            model (str, optional): LLM model name. Defaults to "gpt-3.5-turbo".
+            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.api_key = api_key
+        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://api.groq.com/openai/v1/chat/completions"
+        self.stream_chunk_size = 64
+        self.timeout = timeout
+        self.last_response = {}
+        self.headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+        }
+
+        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|AsyncGenerator : ai content
+                ```json
+        {
+            "id": "c0c8d139-d2b9-9909-8aa1-14948bc28404",
+            "object": "chat.completion",
+            "created": 1710852779,
+            "model": "mixtral-8x7b-32768",
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": "Hello! How can I assist you today? I'm here to help answer your questions and engage in conversation on a wide variety of topics. Feel free to ask me anything!"
+                    },
+                    "logprobs": null,
+                    "finish_reason": "stop"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": 47,
+                "prompt_time": 0.03,
+                "completion_tokens": 37,
+                "completion_time": 0.069,
+                "total_tokens": 84,
+                "total_time": 0.099
+            },
+            "system_fingerprint": null
+        }
+                ```
+        """
+        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 = {
+            "frequency_penalty": self.frequency_penalty,
+            "messages": [{"content": conversation_prompt, "role": "user"}],
+            "model": self.model,
+            "presence_penalty": self.presence_penalty,
+            "stream": stream,
+            "temperature": self.temperature,
+            "top_p": self.top_p,
+        }
+
+        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:
+                    raise Exception(
+                        f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
+                    )
+
+                message_load = ""
+                intro_value = "data:"
+                async for value in response.aiter_lines():
+                    try:
+                        if value.startswith(intro_value):
+                            value = value[len(intro_value) :]
+                        resp = json.loads(value)
+                        incomplete_message = await self.get_message(resp)
+                        if incomplete_message:
+                            message_load += incomplete_message
+                            resp["choices"][0]["delta"]["content"] = message_load
+                            self.last_response.update(resp)
+                            yield value if raw else resp
+                        elif raw:
+                            yield value
+                    except json.decoder.JSONDecodeError:
+                        pass
+            self.conversation.update_chat_history(
+                prompt, await self.get_message(self.last_response)
+            )
+
+        async def for_non_stream():
+            response = httpx.post(
+                self.chat_endpoint, json=payload, timeout=self.timeout
+            )
+            if not response.is_success:
+                raise Exception(
+                    f"Failed to generate response - ({response.status_code}, {response.reason_phrase})"
+                )
+            resp = response.json()
+            self.last_response.update(resp)
+            self.conversation.update_chat_history(
+                prompt, await self.get_message(self.last_response)
+            )
+            return resp
+
+        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 (dict): Response generated by `self.ask`
+
+        Returns:
+            str: Message extracted
+        """
+        assert isinstance(response, dict), "Response should be of dict data-type only"
+        try:
+            if response["choices"][0].get("delta"):
+                return response["choices"][0]["delta"]["content"]
+            return response["choices"][0]["message"]["content"]
+        except KeyError:
             return ""