WEBSCOUT

Search for anything using Google, DuckDuckGo, 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

Install

pip install -U webscout

CLI version

python -m webscout --help

Go To TOP

Regions

xa-ar for Arabia
xa-en for Arabia (en)
ar-es for Argentina
au-en for Australia
at-de for Austria
be-fr for Belgium (fr)
be-nl for Belgium (nl)
br-pt for Brazil
bg-bg for Bulgaria
ca-en for Canada
ca-fr for Canada (fr)
ct-ca for Catalan
cl-es for Chile
cn-zh for China
co-es for Colombia
hr-hr for Croatia
cz-cs for Czech Republic
dk-da for Denmark
ee-et for Estonia
fi-fi for Finland
fr-fr for France
de-de for Germany
gr-el for Greece
hk-tzh for Hong Kong
hu-hu for Hungary
in-en for India
id-id for Indonesia
id-en for Indonesia (en)
ie-en for Ireland
il-he for Israel
it-it for Italy
jp-jp for Japan
kr-kr for Korea
lv-lv for Latvia
lt-lt for Lithuania
xl-es for Latin America
my-ms for Malaysia
my-en for Malaysia (en)
mx-es for Mexico
nl-nl for Netherlands
nz-en for New Zealand
no-no for Norway
pe-es for Peru
ph-en for Philippines
ph-tl for Philippines (tl)
pl-pl for Poland
pt-pt for Portugal
ro-ro for Romania
ru-ru for Russia
sg-en for Singapore
sk-sk for Slovak Republic
sl-sl for Slovenia
za-en for South Africa
es-es for Spain
se-sv for Sweden
ch-de for Switzerland (de)
ch-fr for Switzerland (fr)
ch-it for Switzerland (it)
tw-tzh for Taiwan
th-th for Thailand
tr-tr for Turkey
ua-uk for Ukraine
uk-en for United Kingdom
us-en for United States
ue-es for United States (es)
ve-es for Venezuela
vn-vi for Vietnam
wt-wt for No region

Go To TOP

YTdownloader

from os import rename, getcwd
from webscout import YTdownloader
def download_audio(video_id):
    youtube_link = video_id 
    handler = YTdownloader.Handler(query=youtube_link)
    for third_query_data in handler.run(format='mp3', quality='128kbps', limit=1):
        audio_path = handler.save(third_query_data, dir=getcwd())  
        rename(audio_path, "audio.mp3")

def download_video(video_id):
    youtube_link = video_id 
    handler = YTdownloader.Handler(query=youtube_link)
    for third_query_data in handler.run(format='mp4', quality='auto', limit=1):
        video_path = handler.save(third_query_data, dir=getcwd())  
        rename(video_path, "video.mp4")
        
if __name__ == "__main__":
    # download_audio("https://www.youtube.com/watch?v=c0tMvzB0OKw")
    download_video("https://www.youtube.com/watch?v=c0tMvzB0OKw")

Weather

1. weather

from webscout import weather as w
weather = w.get("Qazigund")
w.print_weather(weather)

2. weather ascii

from webscout import weather_ascii as w
weather = w.get("Qazigund")
print(weather)

Tempmail and Temp number

Temp number

from rich.console import Console
from webscout import tempid

def main():
    console = Console()
    phone = tempid.TemporaryPhoneNumber()

    try:
        # Get a temporary phone number for a specific country (or random)
        number = phone.get_number(country="Finland")
        console.print(f"Your temporary phone number: [bold cyan]{number}[/bold cyan]")

        # Pause execution briefly (replace with your actual logic)
        # import time module
        import time
        time.sleep(30)  # Adjust the waiting time as needed

        # Retrieve and print messages
        messages = phone.get_messages(number)
        if messages:
            # Access individual messages using indexing:
            console.print(f"[bold green]{messages[0].frm}:[/] {messages[0].content}")
            # (Add more lines if you expect multiple messages)
        else:
            console.print("No messages received.")

    except Exception as e:
        console.print(f"[bold red]An error occurred: {e}")

if __name__ == "__main__":
    main()

Tempmail

import asyncio
from rich.console import Console
from rich.table import Table
from rich.text import Text
from webscout import tempid

async def main() -> None:
    console = Console()
    client = tempid.Client()
    
    try:
        domains = await client.get_domains()
        if not domains:
            console.print("[bold red]No domains available. Please try again later.")
            return

        email = await client.create_email(domain=domains[0].name)
        console.print(f"Your temporary email: [bold cyan]{email.email}[/bold cyan]")
        console.print(f"Token for accessing the email: [bold cyan]{email.token}[/bold cyan]")

        while True:
            messages = await client.get_messages(email.email)
            if messages is not None:
                break

        if messages:
            table = Table(show_header=True, header_style="bold magenta")
            table.add_column("From", style="bold cyan")
            table.add_column("Subject", style="bold yellow")
            table.add_column("Body", style="bold green")
            for message in messages:
                body_preview = Text(message.body_text if message.body_text else "No body")
                table.add_row(message.email_from or "Unknown", message.subject or "No Subject", body_preview)
            console.print(table)
        else:
            console.print("No messages found.")
    
    except Exception as e:
        console.print(f"[bold red]An error occurred: {e}")
    
    finally:
        await client.close()

if __name__ == '__main__':
    asyncio.run(main())

Transcriber

The transcriber function in webscout is a handy tool that transcribes YouTube videos. Here's an example code demonstrating its usage:

from webscout import YTTranscriber
yt = YTTranscriber()
from rich import print
video_url = input("Enter the YouTube video URL: ") 
transcript = yt.get_transcript(video_url, languages=None) 
print(transcript)

GoogleS -- formerly DWEBS

from webscout import GoogleS
from rich import print
searcher = GoogleS()
results = searcher.search("HelpingAI-9B", max_results=20, extract_text=False, max_text_length=200)
for result in results:
    print(result)

BingS

from webscout import BingS
from rich import print
searcher = BingS()
results = searcher.search("HelpingAI-9B", max_results=20, extract_webpage_text=True, max_extract_characters=1000)
for result in results:
    print(result)

The WEBS and AsyncWEBS classes are used to retrieve search results from DuckDuckGo.com To use the AsyncWEBS class, you can perform asynchronous operations using Python's asyncio library. To initialize an instance of the WEBS or AsyncWEBS classes, you can provide the following optional arguments:

Here is an example of initializing the WEBS class:

from webscout import WEBS

R = WEBS().text("python programming", max_results=5)
print(R)

Here is an example of initializing the AsyncWEBS class:

import asyncio
import logging
import sys
from itertools import chain
from random import shuffle
import requests
from webscout import AsyncWEBS

# If you have proxies, define them here
proxies = None

if sys.platform.lower().startswith("win"):
    asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())

def get_words():
    word_site = "https://www.mit.edu/~ecprice/wordlist.10000"
    resp = requests.get(word_site)
    words = resp.text.splitlines()
    return words

async def aget_results(word):
    async with AsyncWEBS(proxies=proxies) as WEBS:
        results = await WEBS.text(word, max_results=None)
        return results

async def main():
    words = get_words()
    shuffle(words)
    tasks = [aget_results(word) for word in words[:10]]
    results = await asyncio.gather(*tasks)
    print(f"Done")
    for r in chain.from_iterable(results):
        print(r)

logging.basicConfig(level=logging.DEBUG)

await main()

It is important to note that the WEBS and AsyncWEBS classes should always be used as a context manager (with statement). This ensures proper resource management and cleanup, as the context manager will automatically handle opening and closing the HTTP client connection.

Exceptions

Exceptions:

• WebscoutE: Raised when there is a generic exception during the API request.

usage of WEBS

1. text() - text search by DuckDuckGo.com

from webscout import WEBS

# Text search for 'live free or die' using DuckDuckGo.com 
with WEBS() as WEBS:
    for r in WEBS.text('live free or die', region='wt-wt', safesearch='off', timelimit='y', max_results=10):
        print(r)

    for r in WEBS.text('live free or die', region='wt-wt', safesearch='off', timelimit='y', max_results=10):
        print(r)

2. answers() - instant answers by DuckDuckGo.com

from webscout import WEBS

# Instant answers for the query "sun" using DuckDuckGo.com 
with WEBS() as WEBS:
    for r in WEBS.answers("sun"):
        print(r)

3. images() - image search by DuckDuckGo.com

from webscout import WEBS

# Image search for the keyword 'butterfly' using DuckDuckGo.com 
with WEBS() as WEBS:
    keywords = 'butterfly'
    WEBS_images_gen = WEBS.images(
      keywords,
      region="wt-wt",
      safesearch="off",
      size=None,
      type_image=None,
      layout=None,
      license_image=None,
      max_results=10,
    )
    for r in WEBS_images_gen:
        print(r)

4. videos() - video search by DuckDuckGo.com

from webscout import WEBS

# Video search for the keyword 'tesla' using DuckDuckGo.com 
with WEBS() as WEBS:
    keywords = 'tesla'
    WEBS_videos_gen = WEBS.videos(
      keywords,
      region="wt-wt",
      safesearch="off",
      timelimit="w",
      resolution="high",
      duration="medium",
      max_results=10,
    )
    for r in WEBS_videos_gen:
        print(r)

5. news() - news search by DuckDuckGo.com

from webscout import WEBS
import datetime

def fetch_news(keywords, timelimit):
    news_list = []
    with WEBS() as webs_instance:
        WEBS_news_gen = webs_instance.news(
            keywords,
            region="wt-wt",
            safesearch="off",
            timelimit=timelimit,
            max_results=20
        )
        for r in WEBS_news_gen:
            # Convert the date to a human-readable format using datetime
            r['date'] = datetime.datetime.fromisoformat(r['date']).strftime('%B %d, %Y')
            news_list.append(r)
    return news_list

def _format_headlines(news_list, max_headlines: int = 100):
    headlines = []
    for idx, news_item in enumerate(news_list):
        if idx >= max_headlines:
            break
        new_headline = f"{idx + 1}. {news_item['title'].strip()} "
        new_headline += f"(URL: {news_item['url'].strip()}) "
        new_headline += f"{news_item['body'].strip()}"
        new_headline += "\n"
        headlines.append(new_headline)

    headlines = "\n".join(headlines)
    return headlines

# Example usage
keywords = 'latest AI news'
timelimit = 'd'
news_list = fetch_news(keywords, timelimit)

# Format and print the headlines
formatted_headlines = _format_headlines(news_list)
print(formatted_headlines)

6. maps() - map search by DuckDuckGo.com

from webscout import WEBS

# Map search for the keyword 'school' in 'anantnag' using DuckDuckGo.com
with WEBS() as WEBS:
    for r in WEBS.maps("school", place="anantnag", max_results=50):
        print(r)

7. translate() - translation by DuckDuckGo.com

from webscout import WEBS

# Translation of the keyword 'school' to German ('hi') using DuckDuckGo.com
with WEBS() as WEBS:
    keywords = 'school'
    r = WEBS.translate(keywords, to="hi")
    print(r)

8. suggestions() - suggestions by DuckDuckGo.com

from webscout import WEBS

# Suggestions for the keyword 'fly' using DuckDuckGo.com
with WEBS() as WEBS:
    for r in WEBS.suggestions("fly"):
        print(r)

usage of WEBSX -- Another Websearch thing

from webscout import WEBSX
s = "Python development tools"

result = WEBSX(s)

print(result)

ALL acts

Text to images - DeepInfraImager, PollinationsAI, BlackboxAIImager, AiForceimagger, NexraImager

**Every TTI provider have same usage code just u need to change import **

from webscout import DeepInfraImager
bot = DeepInfraImager()
resp = bot.generate("AI-generated image - webscout", 1)
print(bot.save(resp))

Text to speech - Voicepods, StreamElements

from webscout import Voicepods
voicepods = Voicepods()
text = "Hello, this is a test of the Voicepods text-to-speech"

print("Generating audio...")
audio_file = voicepods.tts(text)

print("Playing audio...")
voicepods.play_audio(audio_file)

Duckchat - chat with LLM

from webscout import WEBS as w
R = w().chat("Who are you", model='gpt-4o-mini') # GPT-3.5 Turbo, mixtral-8x7b, llama-3-70b, claude-3-haiku, gpt-4o-mini
print(R)

PhindSearch - Search using Phind.com

from webscout import PhindSearch

# Create an instance of the PHIND class
ph = PhindSearch()

# Define a prompt to send to the AI
prompt = "write a essay on phind"

# Use the 'ask' method to send the prompt and receive a response
response = ph.ask(prompt)

# Extract and print the message from the response
message = ph.get_message(response)
print(message)

Using phindv2

from webscout import Phindv2

# Create an instance of the PHIND class
ph = Phindv2()

# Define a prompt to send to the AI
prompt = ""

# Use the 'ask' method to send the prompt and receive a response
response = ph.ask(prompt)

# Extract and print the message from the response
message = ph.get_message(response)
print(message)

Gemini - search with google gemini

import webscout
from webscout import GEMINI
from rich import print
COOKIE_FILE = "cookies.json"

# Optional: Provide proxy details if needed
PROXIES = {}

# Initialize GEMINI with cookie file and optional proxies
gemini = GEMINI(cookie_file=COOKIE_FILE, proxy=PROXIES)

# Ask a question and print the response
response = gemini.chat("websearch about HelpingAI and who is its developer")
print(response)

YEPCHAT

from webscout import YEPCHAT
ai = YEPCHAT(Tools=False)
response = ai.chat(input(">>> "))
for chunk in response:
    print(chunk, end="", flush=True)
#---------------Tool Call-------------

from rich import print
from webscout import YEPCHAT
def get_current_time():
    import datetime
    return f"The current time is {datetime.datetime.now().strftime('%H:%M:%S')}"
def get_weather(location: str) -> str:
    return f"The weather in {location} is sunny."


ai = YEPCHAT(Tools=True) # Set Tools=True to use tools in the chat.

ai.tool_registry.register_tool("get_current_time", get_current_time, "Gets the current time.")
ai.tool_registry.register_tool(
    "get_weather",
    get_weather,
    "Gets the weather for a given location.",
    parameters={
        "type": "object",
        "properties": {
            "location": {"type": "string", "description": "The city and state, or zip code"}
        },
        "required": ["location"],
    },
)

response = ai.chat(input(">>> "))
for chunk in response:
    print(chunk, end="", flush=True)

BlackBox - Search/chat With BlackBox

from webscout import BLACKBOXAI
from rich import print

ai = BLACKBOXAI(
    is_conversation=True,
    max_tokens=800,
    timeout=30,
    intro=None,
    filepath=None,
    update_file=True,
    proxies={},
    history_offset=10250,
    act=None,
    model=None # You can specify a model if needed
)

# Start an infinite loop for continuous interaction
while True:
    # Define a prompt to send to the AI
    prompt = input("Enter your prompt: ")
    
    # Check if the user wants to exit the loop
    if prompt.lower() == "exit":
        break
    
    # Use the 'chat' method to send the prompt and receive a response
    r = ai.chat(prompt)
    print(r)

PERPLEXITY - Search With PERPLEXITY

from webscout import Perplexity
from rich import print

perplexity = Perplexity() 
# Stream the response
response = perplexity.chat(input(">>> "))
for chunk in response:
    print(chunk, end="", flush=True)

perplexity.close()

meta ai - chat With meta ai

from webscout import Meta
from rich import print
# **For unauthenticated usage**
meta_ai = Meta()

# Simple text prompt
response = meta_ai.chat("What is the capital of France?")
print(response)

# Streaming response
for chunk in meta_ai.chat("Tell me a story about a cat."):
    print(chunk, end="", flush=True)

# **For authenticated usage (including image generation)**
fb_email = "abcd@abc.com"
fb_password = "qwertfdsa"
meta_ai = Meta(fb_email=fb_email, fb_password=fb_password)

# Text prompt with web search
response = meta_ai.ask("what is currently happning in bangladesh in aug 2024")
print(response["message"]) # Access the text message
print("Sources:", response["sources"]) # Access sources (if any)

# Image generation
response = meta_ai.ask("Create an image of a cat wearing a hat.") 
print(response["message"]) # Print the text message from the response
for media in response["media"]:
    print(media["url"])  # Access image URLs

KOBOLDAI -

from webscout import KOBOLDAI

# Instantiate the KOBOLDAI class with default parameters
koboldai = KOBOLDAI()

# Define a prompt to send to the AI
prompt = "What is the capital of France?"

# Use the 'ask' method to get a response from the AI
response = koboldai.ask(prompt)

# Extract and print the message from the response
message = koboldai.get_message(response)
print(message)

Reka - chat with reka

from webscout import REKA

a = REKA(is_conversation=True, max_tokens=8000, timeout=30,api_key="")

prompt = "tell me about india"
response_str = a.chat(prompt)
print(response_str)

Cohere - chat with cohere

from webscout import Cohere

a = Cohere(is_conversation=True, max_tokens=8000, timeout=30,api_key="")

prompt = "tell me about india"
response_str = a.chat(prompt)
print(response_str)

poe- chat with poe

Usage code similar to other proviers

BasedGPT - chat with GPT

from webscout import BasedGPT

# Initialize the BasedGPT provider
basedgpt = BasedGPT(
    is_conversation=True,  # Chat conversationally
    max_tokens=600,  # Maximum tokens to generate
    timeout=30,  # HTTP request timeout
    intro="You are a helpful and friendly AI.",  # Introductory prompt
    filepath="chat_history.txt",  # File to store conversation history
    update_file=True,  # Update the chat history file
)

# Send a prompt to the AI
prompt = "What is the meaning of life?"
response = basedgpt.chat(prompt)

# Print the AI's response
print(response)

DeepSeek -chat with deepseek

from webscout import DeepSeek
from rich import print

ai = DeepSeek(
    is_conversation=True,
    api_key='cookie, 
    max_tokens=800,
    timeout=30,
    intro=None,
    filepath=None,
    update_file=True,
    proxies={},
    history_offset=10250,
    act=None,
    model="deepseek_chat"
)


# Define a prompt to send to the AI
prompt = "Tell me about india"
# Use the 'chat' method to send the prompt and receive a response
r = ai.chat(prompt)
print(r)

Deepinfra

from webscout import DeepInfra

ai = DeepInfra(
    is_conversation=True,
    model= "Qwen/Qwen2-72B-Instruct",
    max_tokens=800,
    timeout=30,
    intro=None,
    filepath=None,
    update_file=True,
    proxies={},
    history_offset=10250,
    act=None,
)

prompt = "what is meaning of life"

response = ai.ask(prompt)

# Extract and print the message from the response
message = ai.get_message(response)
print(message)

Deepinfra - VLM

from webscout.Provider import VLM 

# Load your image
image_path = r"C:\Users\koula\OneDrive\Desktop\Webscout\photo_2024-03-25_19-23-40.jpg"

vlm_instance = VLM(model="llava-hf/llava-1.5-7b-hf", is_conversation=True, max_tokens=600, timeout=30, system_prompt="You are a Helpful AI.")
image_base64 = vlm_instance.encode_image_to_base64(image_path)

prompt = {
    "content": "What is in this image?",
    "image": image_base64
}

# Generate a response
response = vlm_instance.chat(prompt)
print(response)

GROQ

from webscout import GROQ
ai = GROQ(api_key="")
response = ai.chat("What is the meaning of life?")
print(response)
#----------------------TOOL CALL------------------
from webscout import GROQ  # Adjust import based on your project structure
from webscout import WEBS
import json

# Initialize the GROQ client
client = GROQ(api_key="")
MODEL = 'llama3-groq-70b-8192-tool-use-preview'

# Function to evaluate a mathematical expression
def calculate(expression):
    """Evaluate a mathematical expression"""
    try:
        result = eval(expression)
        return json.dumps({"result": result})
    except Exception as e:
        return json.dumps({"error": str(e)})

# Function to perform a text search using DuckDuckGo.com
def search(query):
    """Perform a text search using DuckDuckGo.com"""
    try:
        results = WEBS().text(query, max_results=5)
        return json.dumps({"results": results})
    except Exception as e:
        return json.dumps({"error": str(e)})

# Add the functions to the provider
client.add_function("calculate", calculate)
client.add_function("search", search)

# Define the tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "calculate",
            "description": "Evaluate a mathematical expression",
            "parameters": {
                "type": "object",
                "properties": {
                    "expression": {
                        "type": "string",
                        "description": "The mathematical expression to evaluate",
                    }
                },
                "required": ["expression"],
            },
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search",
            "description": "Perform a text search using DuckDuckGo.com and Yep.com",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "The search query to execute",
                    }
                },
                "required": ["query"],
            },
        }
    }
]


user_prompt_calculate = "What is 25 * 4 + 10?"
response_calculate = client.chat(user_prompt_calculate, tools=tools)
print(response_calculate)

user_prompt_search = "Find information on HelpingAI and who is its developer"
response_search = client.chat(user_prompt_search, tools=tools)
print(response_search)

LLama 70b - chat with meta's llama 3 70b

from webscout import LLAMA

llama = LLAMA()

r = llama.chat("What is the meaning of life?")
print(r)

AndiSearch

from webscout import AndiSearch
a = AndiSearch()
print(a.chat("HelpingAI-9B"))

Function calling-beta

import json
import logging
from webscout import LLAMA3, WEBS
from webscout.Agents.functioncall import FunctionCallingAgent

# Define tools that the agent can use
tools = [
    {
        "type": "function",
        "function": {
            "name": "UserDetail",
            "parameters": {
                "type": "object",
                "title": "UserDetail",
                "properties": {
                    "name": {
                        "title": "Name",
                        "type": "string"
                    },
                    "age": {
                        "title": "Age",
                        "type": "integer"
                    }
                },
                "required": ["name", "age"]
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "web_search",
            "description": "Search query on google",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "web search query"
                    }
                },
                "required": ["query"]
            }
        }
    },
    {  # New general AI tool
        "type": "function",
        "function": {
            "name": "general_ai",
            "description": "Use general AI knowledge to answer the question",
            "parameters": {
                "type": "object",
                "properties": {
                    "question": {
                        "type": "string",
                        "description": "The question to answer"
                    }
                },
                "required": ["question"]
            }
        }
    }
]

# Initialize the FunctionCallingAgent with the specified tools
agent = FunctionCallingAgent(tools=tools)
llama = LLAMA3()
from rich import print
# Input message from the user
user = input(">>> ")
message = user
function_call_data = agent.function_call_handler(message)
print(f"Function Call Data: {function_call_data}")

# Check for errors in the function call data
if "error" not in function_call_data:
    function_name = function_call_data.get("tool_name")  # Use 'tool_name' instead of 'name'
    if function_name == "web_search":
        arguments = function_call_data.get("tool_input", {})  # Get tool input arguments
        query = arguments.get("query")
        if query:
            with WEBS() as webs:
                search_results = webs.text(query, max_results=5) 
            prompt = (
                f"Based on the following search results:\n\n{search_results}\n\n"
                f"Question: {user}\n\n"
                "Please provide a comprehensive answer to the question based on the search results above. "
                "Include relevant webpage URLs in your answer when appropriate. "
                "If the search results don't contain relevant information, please state that and provide the best answer you can based on your general knowledge."
            )
            response = llama.chat(prompt)
            for c in response:
                print(c, end="", flush=True)

        else:
            print("Please provide a search query.")
    elif function_name == "general_ai":  # Handle general AI tool
        arguments = function_call_data.get("tool_input", {})
        question = arguments.get("question")
        if question:
            response = llama.chat(question)  # Use LLM directly
            for c in response:
                print(c, end="", flush=True)
        else:
            print("Please provide a question.")
    else:
        result = agent.execute_function(function_call_data)
        print(f"Function Execution Result: {result}") 
else:
    print(f"Error: {function_call_data['error']}")

LLAMA3, pizzagpt, RUBIKSAI, Koala, Darkai, AI4Chat, Farfalle, PIAI, Felo, XDASH, Julius, YouChat, YEPCHAT, Cloudflare, TurboSeek, Editee, AI21, Chatify, Cerebras, X0GPT, Lepton, GEMINIAPI, Cleeai, Elmo, Genspark, Upstage, Free2GPT, Bing, DiscordRocks, GPTWeb, AIGameIO

code similar to other provider

LLM

from webscout.LLM import LLM

# Read the system message from the file
with open('system.txt', 'r') as file:
    system_message = file.read()

# Initialize the LLM class with the model name and system message
llm = LLM(model="microsoft/WizardLM-2-8x22B", system_message=system_message)

while True:
    # Get the user input
    user_input = input("User: ")

    # Define the messages to be sent
    messages = [
        {"role": "user", "content": user_input}
    ]

    # Use the mistral_chat method to get the response
    response = llm.chat(messages)

    # Print the response
    print("AI: ", response)

Local-LLM

Webscout can now run GGUF models locally. You can download and run your favorite models with minimal configuration.

Example:

from webscout.Local.utils import download_model
from webscout.Local.model import Model
from webscout.Local.thread import Thread
from webscout.Local import formats

# 1. Download the model
repo_id = "microsoft/Phi-3-mini-4k-instruct-gguf"  # Replace with the desired Hugging Face repo
filename = "Phi-3-mini-4k-instruct-q4.gguf" # Replace with the correct filename
model_path = download_model(repo_id, filename, token="")

# 2. Load the model 
model = Model(model_path, n_gpu_layers=4)  

# 3. Create a Thread for conversation
thread = Thread(model, formats.phi3)

# 4. Start interacting with the model
thread.interact()

Local-rawdog

Webscout's local raw-dog feature allows you to run Python scripts within your terminal prompt.

Example:

import webscout.Local as ws
from webscout.Local.rawdog import RawDog
from webscout.Local.samplers import DefaultSampling
from webscout.Local.formats import chatml, AdvancedFormat
from webscout.Local.utils import download_model
import datetime
import sys
import os

repo_id = "YorkieOH10/granite-8b-code-instruct-Q8_0-GGUF" 
filename = "granite-8b-code-instruct.Q8_0.gguf"
model_path = download_model(repo_id, filename, token='')

# Load the model using the downloaded path
model = ws.Model(model_path, n_gpu_layers=10)

rawdog = RawDog()

# Create an AdvancedFormat and modify the system content
# Use a lambda to generate the prompt dynamically:
chat_format = AdvancedFormat(chatml)
#  **Pre-format the intro_prompt string:**
system_content = f"""
You are a command-line coding assistant called Rawdog that generates and auto-executes Python scripts.

A typical interaction goes like this:
1. The user gives you a natural language PROMPT.
2. You:
    i. Determine what needs to be done
    ii. Write a short Python SCRIPT to do it
    iii. Communicate back to the user by printing to the console in that SCRIPT
3. The compiler extracts the script and then runs it using exec(). If there will be an exception raised,
 it will be send back to you starting with "PREVIOUS SCRIPT EXCEPTION:".
4. In case of exception, regenerate error free script.

If you need to review script outputs before completing the task, you can print the word "CONTINUE" at the end of your SCRIPT.
This can be useful for summarizing documents or technical readouts, reading instructions before
deciding what to do, or other tasks that require multi-step reasoning.
A typical 'CONTINUE' interaction looks like this:
1. The user gives you a natural language PROMPT.
2. You:
    i. Determine what needs to be done
    ii. Determine that you need to see the output of some subprocess call to complete the task
    iii. Write a short Python SCRIPT to print that and then print the word "CONTINUE"
3. The compiler
    i. Checks and runs your SCRIPT
    ii. Captures the output and appends it to the conversation as "LAST SCRIPT OUTPUT:"
    iii. Finds the word "CONTINUE" and sends control back to you
4. You again:
    i. Look at the original PROMPT + the "LAST SCRIPT OUTPUT:" to determine what needs to be done
    ii. Write a short Python SCRIPT to do it
    iii. Communicate back to the user by printing to the console in that SCRIPT
5. The compiler...

Please follow these conventions carefully:
- Decline any tasks that seem dangerous, irreversible, or that you don't understand.
- Always review the full conversation prior to answering and maintain continuity.
- If asked for information, just print the information clearly and concisely.
- If asked to do something, print a concise summary of what you've done as confirmation.
- If asked a question, respond in a friendly, conversational way. Use programmatically-generated and natural language responses as appropriate.
- If you need clarification, return a SCRIPT that prints your question. In the next interaction, continue based on the user's response.
- Assume the user would like something concise. For example rather than printing a massive table, filter or summarize it to what's likely of interest.
- Actively clean up any temporary processes or files you use.
- When looking through files, use git as available to skip files, and skip hidden files (.env, .git, etc) by default.
- You can plot anything with matplotlib.
- ALWAYS Return your SCRIPT inside of a single pair of ``` delimiters. Only the console output of the first such SCRIPT is visible to the user, so make sure that it's complete and don't bother returning anything else.
"""
chat_format.override('system_content', lambda: system_content)

thread = ws.Thread(model, format=chat_format, sampler=DefaultSampling)

while True:
    prompt = input(">: ")
    if prompt.lower() == "q":
        break

    response = thread.send(prompt)

    # Process the response using RawDog
    script_output = rawdog.main(response)

    if script_output:
        print(script_output)

GGUF

Webscout provides tools to convert and quantize Hugging Face models into the GGUF format for use with offline LLMs.

Example:

from webscout import gguf
"""
Valid quantization methods:
"q2_k", "q3_k_l", "q3_k_m", "q3_k_s", 
"q4_0", "q4_1", "q4_k_m", "q4_k_s", 
"q5_0", "q5_1", "q5_k_m", "q5_k_s", 
"q6_k", "q8_0"
"""
gguf.convert(
    model_id="OEvortex/HelpingAI-Lite-1.5T",  # Replace with your model ID
    username="Abhaykoul",  # Replace with your Hugging Face username
    token="hf_token_write",  # Replace with your Hugging Face token
    quantization_methods="q4_k_m"  # Optional, adjust quantization methods
)

Autollama

Webscout's autollama utility download model from huggingface and then automatically makes it ollama ready

from webscout import autollama

model_path = "Vortex4ai/Jarvis-0.5B"
gguf_file = "test2-q4_k_m.gguf"

autollama.main(model_path, gguf_file)  

Command Line Usage:

• GGUF Conversion:

  python -m webscout.Extra.gguf -m "OEvortex/HelpingAI-Lite-1.5T" -u "your_username" -t "your_hf_token" -q "q4_k_m,q5_k_m" 
  

• Autollama:

  python -m webscout.Extra.autollama -m "OEvortex/HelpingAI-Lite-1.5T" -g "HelpingAI-Lite-1.5T.q4_k_m.gguf" 
  

Note:

• Replace "your_username" and "your_hf_token" with your actual Hugging Face credentials.
• The model_path in autollama is the Hugging Face model ID, and gguf_file is the GGUF file ID.

Webai - terminal gpt and a open interpeter

```shell
python -m webscout.webai webai --provider "phind" --rawdog