neurocore.llm.provider
======================

.. py:module:: neurocore.llm.provider

.. autoapi-nested-parse::

   LLM provider protocol and implementations.



Classes
-------

.. toctree::
   :hidden:

   /autoapi/neurocore/llm/provider/LLMMessage
   /autoapi/neurocore/llm/provider/LLMResponse
   /autoapi/neurocore/llm/provider/LLMProvider
   /autoapi/neurocore/llm/provider/AnthropicProvider
   /autoapi/neurocore/llm/provider/OpenAIProvider
   /autoapi/neurocore/llm/provider/GeminiProvider
   /autoapi/neurocore/llm/provider/MockProvider
   /autoapi/neurocore/llm/provider/LiteLLMProvider

.. autoapisummary::

   neurocore.llm.provider.LLMMessage
   neurocore.llm.provider.LLMResponse
   neurocore.llm.provider.LLMProvider
   neurocore.llm.provider.AnthropicProvider
   neurocore.llm.provider.OpenAIProvider
   neurocore.llm.provider.GeminiProvider
   neurocore.llm.provider.MockProvider
   neurocore.llm.provider.LiteLLMProvider


Functions
---------

.. autoapisummary::

   neurocore.llm.provider.build_provider


Module Contents
---------------

.. py:function:: build_provider(config: dict[str, Any]) -> LLMProvider | None

   Build an LLMProvider from a config dict.

   Keys read:
       llm_provider: provider name (required to build). One of
                     anthropic | openai | openai-compatible | ollama |
                     vllm | litellm | gemini | mock.
       llm_model:    model identifier (optional, uses provider default)
       llm_api_key:  API key (optional for mock/local gateways)
       llm_base_url: endpoint for openai-compatible/ollama/vllm/litellm

   Returns None if llm_provider is not set.