dataflow.registries.model_registry

Model Registry Client for Haive.

This module provides a client interface for working with the registry system to access LLM and embedding models with dynamic environment variable detection.

Attributes

CORE_LLM_AVAILABLE
logger

Classes

ModelRegistry

Client for working with registered LLM and embedding models.

Module Contents

class dataflow.registries.model_registry.ModelRegistry

Client for working with registered LLM and embedding models.

detect_environment_variables()

Detect available environment variables for LLM and embedding. providers.

Returns:

Dict mapping provider names to available environment variables

get_available_embedding_providers() → list[dict[str, Any]]

Get all available embedding providers.

Returns:

List of available embedding providers

get_available_llm_providers() → list[dict[str, Any]]

Get all available LLM providers.

Returns:

List of available LLM providers

get_embedding_model(model_id: str) → dict[str, Any] | None

Get a specific embedding model by ID.

Parameters:

model_id – ID of the model

Returns:

Model data or None if not found

get_embedding_models(provider: str | None = None, only_available: bool = False) → list[dict[str, Any]]

Get all embedding models, optionally filtered by provider.

Parameters:

• provider – Optional provider name to filter by

• only_available – If True, only return models from available providers

Returns:

List of embedding model data

get_llm_model(model_id: str) → dict[str, Any] | None

Get a specific LLM model by ID.

Parameters:

model_id – ID of the model

Returns:

Model data or None if not found

get_llm_models(provider: str | None = None, only_available: bool = False) → list[dict[str, Any]]

Get all LLM models, optionally filtered by provider.

Parameters:

• provider – Optional provider name to filter by

• only_available – If True, only return models from available providers

Returns:

List of LLM model data

get_required_environment_vars() → list[dict[str, Any]]

Scan source code to detect environment variables used by LLM. providers.

Returns:

List of environment variables with provider mapping

get_secret_from_vault(var_name: str) → str | None

Get a secret value from the vault.

Parameters:

var_name – Name of the environment variable

Returns:

Secret value or None if not found

normalize_model_data(model: dict[str, Any]) → dict[str, Any]

Normalize model data to ensure consistent field access.

Parameters:

model – Model data to normalize

Returns:

Normalized model data

update_provider_availability()

Scan environment variables and update provider availability. status.

dataflow.registries.model_registry.CORE_LLM_AVAILABLE = True

dataflow.registries.model_registry.logger