vibe.llm_providers.ollama

Ollama LLM provider integration.

OllamaProvider

LLM Provider for Ollama locally hosted models.

Configuration options (common - via ProviderConfig): - model: Model name (e.g., "llama3.2", "mistral") - required - base_url: Ollama server URL (default: "http://localhost:11434") - temperature: Controls randomness (0.0 - 1.0, default: 0.7) - timeout: Request timeout in seconds (default: 30) - tools: Enable native tool calling (default: False for JSON mode) - api_key: Not used by Ollama (local models don't need authentication)

Configuration options (Ollama-specific): - system: System message override

convert_messages_to_provider_format 

convert_messages_to_provider_format(messages: list[Message], tools: list[Tool] | None = None) -> list[dict[str, Any]]

Convert internal messages and tools to Ollama-compatible format.

Uses InternalFormatConverter (message_to_dict) for conversion.

Parameters:
  • messages (list[Message]) –

    List of typed Message objects

  • tools (list[Tool] | None, default: None ) –

    Optional list of Tool objects (uses self.tools if not provided)
Returns:
  • list[dict[str, Any]] –

    List of message dicts in Ollama format

stream_generate 

stream_generate(messages: list[Message], sequence_number: int, *, session_id: str, assistant_name: str, endpoint_name: str, turn_id: str, previous_response_id: str | None = None, tool_outputs: list[ToolOutput] | None = None, unanswered_predefined_questions: list[dict[str, Any]] | None = None) -> Generator[StreamChunk, None, None]

Stream LLM responses with tool call support.

Uses tools if enabled, otherwise falls back to basic string parsing.

Parameters:
  • messages (list[Message]) –

    Conversation history as typed Message objects

  • sequence_number (int) –

    Turn sequence number for conversation ordering

  • session_id (str) –

    Session identifier for logging and correlation

  • assistant_name (str) –

    Assistant display name for logging

  • endpoint_name (str) –

    LLM endpoint identifier for logging and metrics

  • turn_id (str) –

    Unique turn identifier for request/response correlation

  • previous_response_id (str | None, default: None ) –

    Not used by Ollama provider

  • tool_outputs (list[ToolOutput] | None, default: None ) –

    Not used by Ollama provider (tool results in message history)

  • unanswered_predefined_questions (list[dict[str, Any]] | None, default: None ) –

    Not used by Ollama provider
Yields:
  • StreamChunk –

    StreamChunk objects containing text deltas or tool call invocations

get_capabilities 

get_capabilities() -> ProviderCapabilities

Return Ollama (local) provider capabilities.

get_usage_stats 

get_usage_stats() -> UsageStats | None

Return usage statistics from the last API call.