Build leaderboard snapshots at different time points. Args: df: Full voting DataFrame time_slices: List of (end_date, sl

Build historical leaderboards using parallel processing. Args: df: Full voting DataFrame time_slices: List of (end_date,

Recursively build tree structure.

Calculate win rates for a chunk of model pairs. Args: args: Tuple of (model_pairs, df) Returns: List of win

Calculate min, max, mean, median for a list of values

Calculate win probability using fast NumPy operations. Args: model_a: First model identifier model_b

Calculate empirical win rate matrix directly from vote data. Args: df: DataFrame with columns 'model_a', 'model_b', 'winner'

Calculate win rate matrix using parallel processing. Args: df: DataFrame with match data models: List of models to inclu

Get calendar events.

Capture an action in the current trajectory. Args: action: The action to capture

Chat interface that maintains conversation history Args: message: User message **kwargs: Generation

Chat using OpenAI-compatible endpoint

Quick configuration check Returns: True if configuration is valid

Check if OpenAI API key is available.

Chunk all conversations in a test case Args: test_case: Test case containing conversation histories

Chunk all conversations in a test case Args: test_case: Test case containing conversation histories

* Cleanup resources

Clear all documents.

Clear all documents from the store.

Clear all documents from the pipeline (for testing).

Clear all workflows from the knowledge base (use with caution).

Clear all memories for this user - useful for testing

Clear all memories for this user

Clear all memory cards

Clear the conversation history

Clear conversation history

Clear conversation history

Clear conversation history

Clear all indexed documents

Clear the specified indexes.

Execute Python code directly without restrictions

Execute Python code in a full Python environment. This provides unrestricted access to Python's built-in functions and standard libra

Enter code interpreter mode

Compare contextual vs non-contextual modes for the same query. Educational method to demonstrate the difference in retrieval

Compare contextual vs non-contextual retrieval. Educational Note: This method demonstrates the improvement that cont

Compare contextual vs non-contextual retrieval. Educational Note: This method demonstrates the improvement that cont

Compare predicted win rates from Elo with empirical win rates. Args: elo_system: Trained Elo rating system empirical_df:

Side-by-side comparison diagram.

Compute similarity between two vectors. Args: vec1: First vector vec2: Second vector met

Convert currency using live exchange rates (simulated)

Convert currency using live exchange rates (simulated)

Create a complex task that requires multiple tool calls and reasoning Returns: Task description

Create necessary directories if they don't exist

Create embeddings for texts using sentence transformers.

Create interactive Plotly visualization of ranking evolution. Args: history_df: DataFrame with columns: date, model, rating, ran

Create interactive rank evolution chart (lower rank number is better). Args: history_df: DataFrame with columns: date, model, ra

Convenience function to create animation in one step. Args: history_df: DataFrame with rating history output_path: Path

Parse CSV data.

Convert currency.

Circular cycle diagram with arrows between nodes.

Delete a document from all services.

Delete a document from the index. This endpoint: 1. Removes the document from the document store 2. Removes the embedding from t

Delete a document from all services. Args: doc_id: Document ID to delete Returns: Deleti

Delete a document from both services.

Delete an item from the index.

Delete an item from the index. Note: ANNOY doesn't support deletion, so we need to rebuild without the item.

Delete a note

Delete a memory card

Delete a memory card

Display memory operations from processing results Args: results: Processing results containing operations verbose: Wheth

Read document content.

Extract content from DOCX.

Download a file from URL.

Ensures that all memory is cleared for a given memory manager. Used primarily for testing and evaluation to ensure clean state before each te

Estimate token count for text (rough approximation) Args: text: Text to estimate tokens for