easydel.inference.tools.parsers.phi4mini_tool_parser

easydel.inference.tools.parsers.phi4mini_tool_parser#

class easydel.inference.tools.parsers.phi4mini_tool_parser.Phi4MiniJsonToolParser(tokenizer: PreTrainedTokenizerBase)[source]#

Bases: ToolParser

Tool call parser for Phi-4-mini models.

Handles the functools format used by Phi-4-mini models. Extracts function calls from functools[…] wrapper with JSON array content. Currently supports non-streaming extraction only.

Features: - Regex-based extraction of functools wrapper - JSON array parsing of function calls - Support for both ‘arguments’ and ‘parameters’ fields - Automatic tool ID generation

Format: functools[{“name”: “func”, “arguments”: {…}}, …]

Used when –enable-auto-tool-choice –tool-call-parser phi4_mini_json are all set.

Note: Streaming extraction is not yet implemented (returns None).

extract_tool_calls(model_output: str, request: ChatCompletionRequest) → ExtractedToolCallInformation[source]#

Extract the tool calls from a complete model response.

extract_tool_calls_streaming(previous_text: str, current_text: str, delta_text: str, previous_token_ids: Sequence[int], current_token_ids: Sequence[int], delta_token_ids: Sequence[int], request: ChatCompletionRequest) → easydel.inference.openai_api_modules.DeltaMessage | None[source]#

Extract tool calls from streaming model output.

Processes incremental model output to identify partial tool calls and emit appropriate streaming updates. Maintains state across calls to handle incomplete JSON/XML structures.

Parameters

  • previous_text – Text accumulated up to previous call

  • current_text – Text accumulated including current chunk

  • delta_text – New text in current chunk

  • previous_token_ids – Token IDs up to previous call

  • current_token_ids – Token IDs including current chunk

  • delta_token_ids – New token IDs in current chunk

  • request – Original request with tool definitions

Returns

Incremental tool call update, or None if no update

Return type

DeltaMessage

Raises

NotImplementedError – Must be implemented by subclasses

Note

This method is stateful - it uses instance variables to track parsing progress across streaming chunks.

Contents