webscout 1.2.3__tar.gz → 1.2.4__tar.gz

{webscout-1.2.3 → webscout-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: webscout
-Version: 1.2.3
+Version: 1.2.4
 Summary: Search for words, documents, images, videos, news, maps and text translation using the Google, DuckDuckGo.com, yep.com, phind.com, you.com, etc Also containes AI models
 Author: OEvortex
 Author-email: helpingai5@gmail.com
@@ -45,6 +45,8 @@ Requires-Dist: sse_starlette
 Requires-Dist: termcolor
 Requires-Dist: tiktoken
 Requires-Dist: tldextract
+Requires-Dist: gpt4all
+Requires-Dist: orjson
 Provides-Extra: dev
 Requires-Dist: ruff>=0.1.6; extra == "dev"
 Requires-Dist: pytest>=7.4.2; extra == "dev"
@@ -92,6 +94,7 @@ Also containes AI models that you can use
     - [6. `BlackBox` - Search/chat With BlackBox](#6-blackbox---searchchat-with-blackbox)
     - [7. `PERPLEXITY` - Search With PERPLEXITY](#7-perplexity---search-with-perplexity)
     - [8. `OpenGPT` - chat With OPENGPT](#8-opengpt---chat-with-opengpt)
+    - [9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout](#9-gpt4all---chat-offline-with-language-models-using-gpt4all-from-webscout)
   - [usage of special .LLM file from webscout (webscout.LLM)](#usage-of-special-llm-file-from-webscout-webscoutllm)
     - [`LLM`](#llm)
 
@@ -605,6 +608,37 @@ prompt = "tell me about india"
 response_str = opengpt.chat(prompt)
 print(response_str)
 ```
+### 9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout
+```python
+from webscout import GPT4ALL
+
+# Initialize the GPT4ALL class with your model path and other optional parameters
+gpt4all_instance = GPT4ALL(
+    model="path/to/your/model/file", # Replace with the actual path to your model file
+    is_conversation=True,
+    max_tokens=800,
+    temperature=0.7,
+    presence_penalty=0,
+    frequency_penalty=1.18,
+    top_p=0.4,
+    intro="Hello, how can I assist you today?",
+    filepath="path/to/conversation/history/file", # Optional, for conversation history
+    update_file=True,
+    history_offset=10250,
+    act=None # Optional, for using an awesome prompt as intro
+)
+
+# Generate a response from the AI model
+response = gpt4all_instance.chat(
+    prompt="What is the weather like today?",
+    stream=False, # Set to True if you want to stream the response
+    optimizer=None, # Optional, specify an optimizer if needed
+    conversationally=False # Set to True for conversationally generated responses
+)
+
+# Print the generated response
+print(response)
+```
 
 ## usage of special .LLM file from webscout (webscout.LLM)
 

{webscout-1.2.3 → webscout-1.2.4}/README.md

@@ -41,6 +41,7 @@ Also containes AI models that you can use
     - [6. `BlackBox` - Search/chat With BlackBox](#6-blackbox---searchchat-with-blackbox)
     - [7. `PERPLEXITY` - Search With PERPLEXITY](#7-perplexity---search-with-perplexity)
     - [8. `OpenGPT` - chat With OPENGPT](#8-opengpt---chat-with-opengpt)
+    - [9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout](#9-gpt4all---chat-offline-with-language-models-using-gpt4all-from-webscout)
   - [usage of special .LLM file from webscout (webscout.LLM)](#usage-of-special-llm-file-from-webscout-webscoutllm)
     - [`LLM`](#llm)
 
@@ -554,6 +555,37 @@ prompt = "tell me about india"
 response_str = opengpt.chat(prompt)
 print(response_str)
 ```
+### 9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout
+```python
+from webscout import GPT4ALL
+
+# Initialize the GPT4ALL class with your model path and other optional parameters
+gpt4all_instance = GPT4ALL(
+    model="path/to/your/model/file", # Replace with the actual path to your model file
+    is_conversation=True,
+    max_tokens=800,
+    temperature=0.7,
+    presence_penalty=0,
+    frequency_penalty=1.18,
+    top_p=0.4,
+    intro="Hello, how can I assist you today?",
+    filepath="path/to/conversation/history/file", # Optional, for conversation history
+    update_file=True,
+    history_offset=10250,
+    act=None # Optional, for using an awesome prompt as intro
+)
+
+# Generate a response from the AI model
+response = gpt4all_instance.chat(
+    prompt="What is the weather like today?",
+    stream=False, # Set to True if you want to stream the response
+    optimizer=None, # Optional, specify an optimizer if needed
+    conversationally=False # Set to True for conversationally generated responses
+)
+
+# Print the generated response
+print(response)
+```
 
 ## usage of special .LLM file from webscout (webscout.LLM)
 

{webscout-1.2.3 → webscout-1.2.4}/setup.py

@@ -9,7 +9,7 @@ with open("README.md", encoding="utf-8") as f:
 
 setup(
     name="webscout",
-    version="1.2.3", # Use the version variable from the version.py file
+    version="1.2.4", # Use the version variable from the version.py file
     description="Search for words, documents, images, videos, news, maps and text translation using the Google, DuckDuckGo.com, yep.com, phind.com, you.com, etc Also containes AI models",
     long_description=README,
     long_description_content_type="text/markdown",
@@ -53,6 +53,8 @@ setup(
         "termcolor",
         "tiktoken",
         "tldextract",
+        "gpt4all",
+        "orjson",
     ],
     entry_points={
         "console_scripts": [

{webscout-1.2.3 → webscout-1.2.4}/webscout/DWEBS.py

@@ -1,197 +1,197 @@
-
-from pydantic import BaseModel, Field
-from typing import Union
-
-from DeepWEBS.utilsdw.logger import logger
-from DeepWEBS.networks.google_searcher import GoogleSearcher
-from DeepWEBS.networks.webpage_fetcher import BatchWebpageFetcher
-from DeepWEBS.documents.query_results_extractor import QueryResultsExtractor
-from DeepWEBS.documents.webpage_content_extractor import BatchWebpageContentExtractor
-from DeepWEBS.utilsdw.logger import logger
-import argparse
-
-class DeepWEBS:
-    def __init__(self):
-        pass
-
-    class DeepSearch(BaseModel):
-        queries: list = Field(
-            default=[""],
-            description="(list[str]) Queries to search",
-        )
-        result_num: int = Field(
-            default=10,
-            description="(int) Number of search results",
-        )
-        safe: bool = Field(
-            default=False,
-            description="(bool) Enable SafeSearch",
-        )
-        types: list = Field(
-            default=["web"],
-            description="(list[str]) Types of search results: `web`, `image`, `videos`, `news`",
-        )
-        extract_webpage: bool = Field(
-            default=False,
-            description="(bool) Enable extracting main text contents from webpage, will add `text` filed in each `query_result` dict",
-        )
-        overwrite_query_html: bool = Field(
-            default=False,
-            description="(bool) Overwrite HTML file of query results",
-        )
-        overwrite_webpage_html: bool = Field(
-            default=False,
-            description="(bool) Overwrite HTML files of webpages from query results",
-        )
-
-    def queries_to_search_results(self, item: DeepSearch):
-        google_searcher = GoogleSearcher()
-        queries_search_results = []
-        for query in item.queries:
-            query_results_extractor = QueryResultsExtractor()
-            if not query.strip():
-                continue
-            try:
-                query_html_path = google_searcher.search(
-                    query=query,
-                    result_num=item.result_num,
-                    safe=item.safe,
-                    overwrite=item.overwrite_query_html,
-                )
-            except Exception as e:
-                logger.error(f"Failed to search for query '{query}': {e}")
-                continue
-
-            try:
-                query_search_results = query_results_extractor.extract(query_html_path)
-            except Exception as e:
-                logger.error(f"Failed to extract search results for query '{query}': {e}")
-                continue
-
-            queries_search_results.append(query_search_results)
-        logger.note(queries_search_results)
-
-        if item.extract_webpage:
-            queries_search_results = self.extract_webpages(
-                queries_search_results,
-                overwrite_webpage_html=item.overwrite_webpage_html,
-            )
-        return queries_search_results
-
-    def extract_webpages(self, queries_search_results, overwrite_webpage_html=False):
-        for query_idx, query_search_results in enumerate(queries_search_results):
-            try:
-                # Fetch webpages with urls
-                batch_webpage_fetcher = BatchWebpageFetcher()
-                urls = [
-                    query_result["url"]
-                    for query_result in query_search_results["query_results"]
-                ]
-                url_and_html_path_list = batch_webpage_fetcher.fetch(
-                    urls,
-                    overwrite=overwrite_webpage_html,
-                    output_parent=query_search_results["query"],
-                )
-            except Exception as e:
-                logger.error(f"Failed to fetch webpages for query '{query_search_results['query']}': {e}")
-                continue
-
-            # Extract webpage contents from htmls
-            html_paths = [
-                str(url_and_html_path["html_path"])
-                for url_and_html_path in url_and_html_path_list
-            ]
-            batch_webpage_content_extractor = BatchWebpageContentExtractor()
-            try:
-                html_path_and_extracted_content_list = (
-                    batch_webpage_content_extractor.extract(html_paths)
-                )
-            except Exception as e:
-                logger.error(f"Failed to extract webpage contents for query '{query_search_results['query']}': {e}")
-                continue
-
-            # Build the map of url to extracted_content
-            html_path_to_url_dict = {
-                str(url_and_html_path["html_path"]): url_and_html_path["url"]
-                for url_and_html_path in url_and_html_path_list
-            }
-            url_to_extracted_content_dict = {
-                html_path_to_url_dict[
-                    html_path_and_extracted_content["html_path"]
-                ]: html_path_and_extracted_content["extracted_content"]
-                for html_path_and_extracted_content in html_path_and_extracted_content_list
-            }
-
-            # Write extracted contents (as 'text' field) to query_search_results
-            for query_result_idx, query_result in enumerate(
-                query_search_results["query_results"]
-            ):
-                url = query_result["url"]
-                extracted_content = url_to_extracted_content_dict.get(url, "")
-                queries_search_results[query_idx]["query_results"][query_result_idx][
-                    "text"
-                ] = extracted_content
-
-        return queries_search_results
-
-
-class ArgParser(argparse.ArgumentParser):
-    def __init__(self, *args, **kwargs):
-        super(ArgParser, self).__init__(*args, **kwargs)
-
-        self.add_argument(
-            "-q",
-            "--queries",
-            type=str,
-            nargs="+",
-            required=True,
-            help="Queries to search",
-        )
-        self.add_argument(
-            "-n",
-            "--result_num",
-            type=int,
-            default=10,
-            help="Number of search results",
-        )
-        self.add_argument(
-            "-s",
-            "--safe",
-            default=False,
-            action="store_true",
-            help="Enable SafeSearch",
-        )
-        self.add_argument(
-            "-t",
-            "--types",
-            type=str,
-            nargs="+",
-            default=["web"],
-            choices=["web", "image", "videos", "news"],
-            help="Types of search results",
-        )
-        self.add_argument(
-            "-e",
-            "--extract_webpage",
-            default=False,
-            action="store_true",
-            help="Enable extracting main text contents from webpage",
-        )
-        self.add_argument(
-            "-o",
-            "--overwrite_query_html",
-            default=False,
-            action="store_true",
-            help="Overwrite HTML file of query results",
-        )
-        self.add_argument(
-            "-w",
-            "--overwrite_webpage_html",
-            default=False,
-            action="store_true",
-            help="Overwrite HTML files of webpages from query results",
-        )
-
-        self.args = self.parse_args()
-
-
+
+from pydantic import BaseModel, Field
+from typing import Union
+
+from DeepWEBS.utilsdw.logger import logger
+from DeepWEBS.networks.google_searcher import GoogleSearcher
+from DeepWEBS.networks.webpage_fetcher import BatchWebpageFetcher
+from DeepWEBS.documents.query_results_extractor import QueryResultsExtractor
+from DeepWEBS.documents.webpage_content_extractor import BatchWebpageContentExtractor
+from DeepWEBS.utilsdw.logger import logger
+import argparse
+
+class DeepWEBS:
+    def __init__(self):
+        pass
+
+    class DeepSearch(BaseModel):
+        queries: list = Field(
+            default=[""],
+            description="(list[str]) Queries to search",
+        )
+        result_num: int = Field(
+            default=10,
+            description="(int) Number of search results",
+        )
+        safe: bool = Field(
+            default=False,
+            description="(bool) Enable SafeSearch",
+        )
+        types: list = Field(
+            default=["web"],
+            description="(list[str]) Types of search results: `web`, `image`, `videos`, `news`",
+        )
+        extract_webpage: bool = Field(
+            default=False,
+            description="(bool) Enable extracting main text contents from webpage, will add `text` filed in each `query_result` dict",
+        )
+        overwrite_query_html: bool = Field(
+            default=False,
+            description="(bool) Overwrite HTML file of query results",
+        )
+        overwrite_webpage_html: bool = Field(
+            default=False,
+            description="(bool) Overwrite HTML files of webpages from query results",
+        )
+
+    def queries_to_search_results(self, item: DeepSearch):
+        google_searcher = GoogleSearcher()
+        queries_search_results = []
+        for query in item.queries:
+            query_results_extractor = QueryResultsExtractor()
+            if not query.strip():
+                continue
+            try:
+                query_html_path = google_searcher.search(
+                    query=query,
+                    result_num=item.result_num,
+                    safe=item.safe,
+                    overwrite=item.overwrite_query_html,
+                )
+            except Exception as e:
+                logger.error(f"Failed to search for query '{query}': {e}")
+                continue
+
+            try:
+                query_search_results = query_results_extractor.extract(query_html_path)
+            except Exception as e:
+                logger.error(f"Failed to extract search results for query '{query}': {e}")
+                continue
+
+            queries_search_results.append(query_search_results)
+        logger.note(queries_search_results)
+
+        if item.extract_webpage:
+            queries_search_results = self.extract_webpages(
+                queries_search_results,
+                overwrite_webpage_html=item.overwrite_webpage_html,
+            )
+        return queries_search_results
+
+    def extract_webpages(self, queries_search_results, overwrite_webpage_html=False):
+        for query_idx, query_search_results in enumerate(queries_search_results):
+            try:
+                # Fetch webpages with urls
+                batch_webpage_fetcher = BatchWebpageFetcher()
+                urls = [
+                    query_result["url"]
+                    for query_result in query_search_results["query_results"]
+                ]
+                url_and_html_path_list = batch_webpage_fetcher.fetch(
+                    urls,
+                    overwrite=overwrite_webpage_html,
+                    output_parent=query_search_results["query"],
+                )
+            except Exception as e:
+                logger.error(f"Failed to fetch webpages for query '{query_search_results['query']}': {e}")
+                continue
+
+            # Extract webpage contents from htmls
+            html_paths = [
+                str(url_and_html_path["html_path"])
+                for url_and_html_path in url_and_html_path_list
+            ]
+            batch_webpage_content_extractor = BatchWebpageContentExtractor()
+            try:
+                html_path_and_extracted_content_list = (
+                    batch_webpage_content_extractor.extract(html_paths)
+                )
+            except Exception as e:
+                logger.error(f"Failed to extract webpage contents for query '{query_search_results['query']}': {e}")
+                continue
+
+            # Build the map of url to extracted_content
+            html_path_to_url_dict = {
+                str(url_and_html_path["html_path"]): url_and_html_path["url"]
+                for url_and_html_path in url_and_html_path_list
+            }
+            url_to_extracted_content_dict = {
+                html_path_to_url_dict[
+                    html_path_and_extracted_content["html_path"]
+                ]: html_path_and_extracted_content["extracted_content"]
+                for html_path_and_extracted_content in html_path_and_extracted_content_list
+            }
+
+            # Write extracted contents (as 'text' field) to query_search_results
+            for query_result_idx, query_result in enumerate(
+                query_search_results["query_results"]
+            ):
+                url = query_result["url"]
+                extracted_content = url_to_extracted_content_dict.get(url, "")
+                queries_search_results[query_idx]["query_results"][query_result_idx][
+                    "text"
+                ] = extracted_content
+
+        return queries_search_results
+
+
+class ArgParser(argparse.ArgumentParser):
+    def __init__(self, *args, **kwargs):
+        super(ArgParser, self).__init__(*args, **kwargs)
+
+        self.add_argument(
+            "-q",
+            "--queries",
+            type=str,
+            nargs="+",
+            required=True,
+            help="Queries to search",
+        )
+        self.add_argument(
+            "-n",
+            "--result_num",
+            type=int,
+            default=10,
+            help="Number of search results",
+        )
+        self.add_argument(
+            "-s",
+            "--safe",
+            default=False,
+            action="store_true",
+            help="Enable SafeSearch",
+        )
+        self.add_argument(
+            "-t",
+            "--types",
+            type=str,
+            nargs="+",
+            default=["web"],
+            choices=["web", "image", "videos", "news"],
+            help="Types of search results",
+        )
+        self.add_argument(
+            "-e",
+            "--extract_webpage",
+            default=False,
+            action="store_true",
+            help="Enable extracting main text contents from webpage",
+        )
+        self.add_argument(
+            "-o",
+            "--overwrite_query_html",
+            default=False,
+            action="store_true",
+            help="Overwrite HTML file of query results",
+        )
+        self.add_argument(
+            "-w",
+            "--overwrite_webpage_html",
+            default=False,
+            action="store_true",
+            help="Overwrite HTML files of webpages from query results",
+        )
+
+        self.args = self.parse_args()
+
+

{webscout-1.2.3 → webscout-1.2.4}/webscout/__init__.py

@@ -9,6 +9,7 @@ from .webscout_search import WEBS
 from .webscout_search_async import AsyncWEBS
 from .version import __version__
 from .DWEBS import DeepWEBS
+from .offlineAI import GPT4ALL
 __all__ = ["WEBS", "AsyncWEBS", "__version__", "cli"]
 
 logging.getLogger("webscout").addHandler(logging.NullHandler())

webscout-1.2.4/webscout/offlineAI.py

@@ -0,0 +1,206 @@
+from webscout.AIutel import Optimizers
+from webscout.AIutel import Conversation
+from webscout.AIutel import AwesomePrompts
+from webscout.AIbase import Provider
+from gpt4all import GPT4All
+from gpt4all.gpt4all import empty_chat_session
+from gpt4all.gpt4all import append_extension_if_missing
+
+
+import logging
+
+my_logger = logging.getLogger("gpt4all")
+my_logger.setLevel(logging.CRITICAL)
+
+
+class GPT4ALL(Provider):
+    def __init__(
+        self,
+        model: str,
+        is_conversation: bool = True,
+        max_tokens: int = 800,
+        temperature: float = 0.7,
+        presence_penalty: int = 0,
+        frequency_penalty: int = 1.18,
+        top_p: float = 0.4,
+        intro: str = None,
+        filepath: str = None,
+        update_file: bool = True,
+        history_offset: int = 10250,
+        act: str = None,
+    ):
+        """Instantiates GPT4ALL
+
+        Args:
+            model (str, optional): Path to LLM model (.gguf or .bin).
+            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 0.7.
+            presence_penalty (int, optional): Chances of topic being repeated. Defaults to 0.
+            frequency_penalty (int, optional): Chances of word being repeated. Defaults to 1.18.
+            top_p (float, optional): Sampling threshold during inference time. Defaults to 0.4.
+            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.
+            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.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 get_model_name_path():
+            import os
+            from pathlib import Path
+
+            initial_model_path = Path(append_extension_if_missing(model))
+            if initial_model_path.exists:
+                if not initial_model_path.is_absolute():
+                    initial_model_path = Path(os.getcwd()) / initial_model_path
+                return os.path.split(initial_model_path.as_posix())
+            else:
+                raise FileNotFoundError(
+                    "File does not exist " + initial_model_path.as_posix()
+                )
+
+        model_dir, model_name = get_model_name_path()
+
+        self.gpt4all = GPT4All(
+            model_name=model_name,
+            model_path=model_dir,
+            allow_download=False,
+            verbose=False,
+        )
+
+    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}"
+                )
+
+        def for_stream():
+            response = self.gpt4all.generate(
+                prompt=conversation_prompt,
+                max_tokens=self.max_tokens_to_sample,
+                temp=self.temperature,
+                top_p=self.top_p,
+                repeat_penalty=self.frequency_penalty,
+                streaming=True,
+            )
+
+            message_load: str = ""
+            for token in response:
+                message_load += token
+                resp: dict = dict(text=message_load)
+                yield token if raw else resp
+                self.last_response.update(resp)
+
+            self.conversation.update_chat_history(
+                prompt, self.get_message(self.last_response)
+            )
+            self.gpt4all.current_chat_session = empty_chat_session()
+
+        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"]

webscout-1.2.4/webscout/version.py

@@ -0,0 +1,2 @@
+__version__ = "1.2.4"
+

{webscout-1.2.3 → webscout-1.2.4}/webscout.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: webscout
-Version: 1.2.3
+Version: 1.2.4
 Summary: Search for words, documents, images, videos, news, maps and text translation using the Google, DuckDuckGo.com, yep.com, phind.com, you.com, etc Also containes AI models
 Author: OEvortex
 Author-email: helpingai5@gmail.com
@@ -45,6 +45,8 @@ Requires-Dist: sse_starlette
 Requires-Dist: termcolor
 Requires-Dist: tiktoken
 Requires-Dist: tldextract
+Requires-Dist: gpt4all
+Requires-Dist: orjson
 Provides-Extra: dev
 Requires-Dist: ruff>=0.1.6; extra == "dev"
 Requires-Dist: pytest>=7.4.2; extra == "dev"
@@ -92,6 +94,7 @@ Also containes AI models that you can use
     - [6. `BlackBox` - Search/chat With BlackBox](#6-blackbox---searchchat-with-blackbox)
     - [7. `PERPLEXITY` - Search With PERPLEXITY](#7-perplexity---search-with-perplexity)
     - [8. `OpenGPT` - chat With OPENGPT](#8-opengpt---chat-with-opengpt)
+    - [9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout](#9-gpt4all---chat-offline-with-language-models-using-gpt4all-from-webscout)
   - [usage of special .LLM file from webscout (webscout.LLM)](#usage-of-special-llm-file-from-webscout-webscoutllm)
     - [`LLM`](#llm)
 
@@ -605,6 +608,37 @@ prompt = "tell me about india"
 response_str = opengpt.chat(prompt)
 print(response_str)
 ```
+### 9. `GPT4ALL` - chat offline with Language models using gpt4all from webscout
+```python
+from webscout import GPT4ALL
+
+# Initialize the GPT4ALL class with your model path and other optional parameters
+gpt4all_instance = GPT4ALL(
+    model="path/to/your/model/file", # Replace with the actual path to your model file
+    is_conversation=True,
+    max_tokens=800,
+    temperature=0.7,
+    presence_penalty=0,
+    frequency_penalty=1.18,
+    top_p=0.4,
+    intro="Hello, how can I assist you today?",
+    filepath="path/to/conversation/history/file", # Optional, for conversation history
+    update_file=True,
+    history_offset=10250,
+    act=None # Optional, for using an awesome prompt as intro
+)
+
+# Generate a response from the AI model
+response = gpt4all_instance.chat(
+    prompt="What is the weather like today?",
+    stream=False, # Set to True if you want to stream the response
+    optimizer=None, # Optional, specify an optimizer if needed
+    conversationally=False # Set to True for conversationally generated responses
+)
+
+# Print the generated response
+print(response)
+```
 
 ## usage of special .LLM file from webscout (webscout.LLM)
 

{webscout-1.2.3 → webscout-1.2.4}/webscout.egg-info/SOURCES.txt

@@ -24,6 +24,7 @@ webscout/__main__.py
 webscout/cli.py
 webscout/exceptions.py
 webscout/models.py
+webscout/offlineAI.py
 webscout/utils.py
 webscout/version.py
 webscout/webscout_search.py

{webscout-1.2.3 → webscout-1.2.4}/webscout.egg-info/requires.txt

@@ -19,6 +19,8 @@ sse_starlette
 termcolor
 tiktoken
 tldextract
+gpt4all
+orjson
 
 [dev]
 ruff>=0.1.6

webscout-1.2.3/webscout/version.py

@@ -1,2 +0,0 @@
-__version__ = "1.2.3"
-