src.dackar.RCA.orchestrators.llm_clients

llm_clients — LLM client Protocol and concrete implementations.

Extracted from rca_reasoning_orchestrator.py. The parent module re-exports all three names for backward-compatible imports.

Attributes

JsonDict

Classes

LLMClient	Base class for protocol classes.
DummyLLMClient	Development-only LLM client used by build_dev_orchestrator().
OllamaLLMClient

Module Contents

src.dackar.RCA.orchestrators.llm_clients.JsonDict

class src.dackar.RCA.orchestrators.llm_clients.LLMClient

Bases: Protocol

Base class for protocol classes.

Protocol classes are defined as:

class Proto(Protocol):
    def meth(self) -> int:
        ...

Such classes are primarily used with static type checkers that recognize structural subtyping (static duck-typing).

For example:

class C:
    def meth(self) -> int:
        return 0

def func(x: Proto) -> int:
    return x.meth()

func(C())  # Passes static type check

See PEP 544 for details. Protocol classes decorated with @typing.runtime_checkable act as simple-minded runtime protocols that check only the presence of given attributes, ignoring their type signatures. Protocol classes can be generic, they are defined as:

class GenProto[T](Protocol):
    def meth(self) -> T:
        ...

generate_json(model, prompt, temperature=0.1)

Parameters:

• model (str)

• prompt (str)

• temperature (float)

Return type:

Dict[str, Any]

class src.dackar.RCA.orchestrators.llm_clients.DummyLLMClient

Development-only LLM client used by build_dev_orchestrator().

Intentionally raises so the real synthesizer falls back to the deterministic template path. This lets the pipeline run end-to-end before Ollama or another real LLM backend is wired in.

generate_json(model, prompt, temperature=0.1)

Parameters:

• model (str)

• prompt (str)

• temperature (float)

Return type:

JsonDict

class src.dackar.RCA.orchestrators.llm_clients.OllamaLLMClient(base_url='http://localhost:11434')

Parameters:

base_url (str)

base_url = ''

generate_json(model, prompt, temperature=0.1)

Parameters:

• model (str)

• prompt (str)

• temperature (float)

Return type:

Dict[str, Any]