Get cached response if available and not expired.

Clean up environment resources.

Execute a web search via the Chat API. Args: objective: Natural language description of the search goal. model: Chat

Make API request with retry logic.

Log message if verbose mode is enabled.

Log message if verbose mode is enabled.

Safely extract text from XML element

Log message if verbose mode is enabled.

Generic query method for any FDA endpoint. Args: category: API category (drug, device, food, animalandveterinary, other)

Make API request with retry logic. Args: endpoint: API endpoint (e.g., '/works', '/authors') params: Query p

Parse a BRENDA Km value entry into structured data.

Validate that required dependencies are installed.

Make API call with error handling and exponential backoff retry. Args: url: API endpoint URL params: Query parameters

Print verbose logging messages.

Make an API request with error handling and retries. Args: endpoint: API endpoint path params: Query paramet

Format DICOM values for display.

Validate that required dependencies are installed.

Get observations (data values) for an economic data series. Args: series_id: The FRED series ID. observation

Search PubMed and return PMIDs. Args: query: Search query max_results: Maximum number of results

Validate that required dependencies are installed.

Convert PDF to images using PyMuPDF.

Execute a GraphQL query against the Open Targets Platform API. Args: query: GraphQL query string variables: Optional diction

Perform a research lookup, routing to the best backend. Parallel Chat API is used by default. Perplexity sonar-pro-search is used onl

Load tree from file.

Search for patents. Args: query: Query dictionary (see PatentSearch API docs for syntax) fields: Fields to r

Get trademark information by registration number. Args: registration_number: Trademark registration number (e.g., "56789

Get trademark information by serial number. Args: serial_number: Trademark serial number (e.g., "87654321") Ret

Make a rate-limited request to PubChem API. Args: url: Request URL method: HTTP method ('GET' or 'POST') **kwargs: A

Apply structural alert filters.

Compare enzyme properties across different organisms.

Find drug element by DrugBank ID Args: drugbank_id: DrugBank ID (e.g., 'DB00001') Returns: XML elem

Infer the type of transformation based on substrate and product.

Paginate through all results. Args: endpoint: API endpoint params: Query parameters max_results:

Parse a BRENDA reaction entry into structured data.

Render the environment. Returns: Rendered frame (if render_mode is 'rgb_array')

Print summary statistics for all resources.

Make an API request with error handling and rate limiting.

Check if file exists and is readable.

Classify confidence score into categories.

Convert a structure file to a different format. Args: input_path: Path to input structure file output_path: Path to output f

Count and aggregate results by a specific field. Args: category: API category endpoint: Specific endpoint

Create SMARTS query from string or SMILES.

Find enzymes that catalyze a specific transformation.

Convert DataFrame to LaTeX table code. Returns: String with LaTeX table code

Generate comprehensive evaluation report.

Get patent application data by application number. Args: application_number: Application number (e.g., "16123456")

Get all drug-drug interactions Args: drugbank_id: DrugBank ID Returns: List of interaction dictiona

Get chemical properties Args: drugbank_id: DrugBank ID Returns: Dictionary with 'calculated' and 'e

Get the path to the venue-templates skill directory.

Get substrate specificity data for an enzyme.

Get transaction history for an application. Args: application_number: Application number Returns: L

List all notebooks, optionally filtering by archived status.

List available templates.

Parse timeframe string to start and end days. Examples: "Week 1-4" -> (0, 28), "Month 3" -> (60, 90)

Query drug adverse events.

Reset environment to initial state. Returns: observation: Initial observation

Reset all agents.

Reset the environment to initial state. Args: seed: Random seed for reproducibility options: Additional opti

Search for preprints within a date range. Args: start_date: Start date in YYYY-MM-DD format end_date: End da

Search works with filters. Args: search: Full-text search query filter_params: Dictionary of filter paramete

Execute one environment step. Args: action: Action to take Returns: observation: New observation

Execute one step in the environment. Args: action: Action to take Returns: observation: New observa

Upload a file attachment to an entry

Calculate exact binomial confidence interval (Clopper-Pearson method). Returns: Lower and upper bounds as percentages

Check if slide count is appropriate for duration.

Detect venue tier from URL to indicate source quality.

Extract DOIs and academic URLs from response text as fallback.

Extract DOIs and academic URLs from response text as fallback.

Format raw PEDS data into cleaner structure.

Format validation results.

Validate and return the Parallel API key.