Returns the execution information of the graph. Returns: dict: The execution information of the graph.

Formats the execution information of a graph showing node statistics. Args: complete_result (list[dict]): The execution information

Safely create a deep copy of an object, handling special cases. Args: obj: Object to copy Returns: Deep copy of the obj

Executes the graph by either using BurrBridge or the standard method. Args: initial_state (dict): The initial state to p

Lazily load text content from the provided URLs. This method yields Documents one at a time as they're scraped, instead of w

Determines the necessary state keys based on the input specification. Args: state (dict): The current state of the graph

Executes the scraping process and returns the answer to the prompt. Returns: str: The answer to the prompt.

Assert that a scraping result is valid. Args: result: The scraping result to validate expected_keys: Optional list of keys that s

Get full URL for a given path.

Asynchronously scrape the content of a given URL by rendering JavaScript using Playwright. Args: url (str): The URL to s

Asynchronously load text content from the provided URLs. This method leverages asyncio to initiate the scraping of all provided URLs

Get a logger with the specified name. If no name is provided, the root logger for the library is returned. Args: name (Optional

Fetches the IP address of the machine associated with the given URL using Scrape.do. Args: token (str): The API token for Scrape.do

Asynchronously scrape the content of a given URL using Playwright's sync API and scrolling. Notes: - The user gets to decide

Return a mock subprocess.CompletedProcess.

Executes the node's logic to fetch HTML content from a specified URL and update the state with this content.

Get the root logger for the library. Returns: logging.Logger: The root logger for the library.

Asynchronously scrape the content of a given URL using Playwright's async API. Args: url (str): The URL to scrape.

Convert HTML to Markdown. This function uses the html2text library to convert the provided HTML content to Markdown format. The function r

Load all documents synchronously.

Send HTML response.

Asynchronously scrape the content of a given URL using undetected chrome with Selenium. Args: url (str): The URL to scra

Get the correct output parser for the LLM model. Returns: JsonOutputParser: The output parser object.

Executes the web scraping process and returns the answer to the prompt. Returns: str: The answer to the prompt.

Executes the web scraping and searching process. Returns: str: The answer to the prompt.

Executes the web scraping process and returns the answer to the prompt. Returns: str: The answer to the prompt.

Executes the scraping process and returns the answer to the prompt. Returns: str: The answer to the prompt.

Search web function with improved error handling, validation, and security features. Args: query (str): Search query search_

Convert to a JSONL line for the Batch API input file.

Set up the root logger for the library. This function sets up the default handler for the root logger, if it has not already been set up

Module for extracting code

minify_html function

Parses a proxy configuration or searches for a matching one via broker.

Reduces the size of the HTML content based on the specified level of reduction. Args: html (str): The HTML content to reduce.

Executes the web scraping and searching process. Returns: str: The answer to the prompt.

Set the verbosity level of the root logger for the library. Args: verbosity (int): The verbosity level to set.

Build the plasmate CLI command for a given URL.

imports a python module at runtime Args: modname: The module name in the scope message: The display message in case of error

Returns the optimal prompt template based on the error type. Args: error_type (str): Type of error to analyze. Returns:

Returns the optimal prompt template for code correction based on the error type. Results are cached for performance. Args: error

Get the correct output parser for the LLM model. Returns: Callable: The output parser function.

Helper method to invoke chain with timeout

If a proxy address conforms to a IPv4 address

Record a benchmark result.

Retrieve and parse results from a completed batch. Args: client: An initialized OpenAI client. batch_info: A BatchJobInfo from a

Test scraper for the given backend and URLs, then analyze content with ScrapegraphAI. Args: scraper (ChromiumLoader): The ChromiumLo

Creates the graph of nodes representing the workflow for web scraping and searching. Returns: BaseGraph: A graph instance

Extract the OpenAI model name from the LLM configuration. Returns: The model name string (e.g., 'gpt-4o-mini').

parses a proxy configuration with known server Args: proxy: The proxy configuration to parse. Returns: A 'playwright' compli

Processes HTML content by removing unnecessary tags, minifying the HTML, and extracting the title and body content. Args: html_c

"" Get the final state of the graph. Args: key (str, optional): The key of the final state to retrieve. Returns

Recursively normalizes the values in a dictionary. Args: d (Dict[str, Any]): The dictionary to normalize. Returns: Dict

Returns the number of tokens in a text string.

Process the input state and generate an answer.

Executes the web scraping and searching process. Returns: str: The answer to the prompt.

search for proxy servers that match the specified broker criteria Args: anonymous: whether proxy servers should have minimum level-1 anon

Pass parameters to every node in the graph unless otherwise defined in the graph. Args: params (dict): Common parameters

Splits the text into chunks based on the number of tokens. Args: text (str): The text to split. chunk_size (int): The maximu

imports a python module from its srcfile Args: modpath: The srcfile absolute path modname: The module name in the scope

Start the mock server in a background thread.

Transform the pydantic schema into a more comprehensible JSON schema. Args: pydantic_schema (dict): The pydantic schema. Return

asynchronously executes the node's logic with multiple graph instances running in parallel, using a semaphore of some size for concurrency reg

Helper method to create a dictionary of edges from the given iterable of tuples. Args: edges (iterable): An iterable of

creates a sample file at some path with some content

deletes a sample file at some path

Extracts URLs from the given text. Args: text (str): The text to extract URLs from. Returns: Tuple[

Fall back to ChromiumLoader when Plasmate returns empty content.

Get format instructions based on the schema configuration.

searches for a proxy server matching the specified broker criteria Args: proxy: The proxy configuration to search for. Returns:

Serve 404 error.

Assert that execution info is valid and contains expected fields. Args: exec_info: Execution info dictionary

BrowserBase Fetch This module provides an interface to the BrowserBase API. Args: api_key (str): The API key provided by Browse

Execute the Burr application with the given initial state. Args: initial_state (dict): The initial state to pass to the

Processes images from the state, generates answers, consolidates the results, and updates the state asynchronously.

Extracts all hyperlinks from the HTML content. Args: html_content (str): The HTML content to extract links from.