haive.core.engine.retriever.providers.ArceeRetrieverConfig

Arcee Retriever implementation for the Haive framework.

from typing import Any This module provides a configuration class for the Arcee retriever, which provides AI/ML focused retrieval capabilities through the Arcee service for domain-specific artificial intelligence and machine learning content.

The ArceeRetriever works by: 1. Connecting to the Arcee API service for AI/ML domain retrieval 2. Performing specialized search across AI/ML focused content 3. Retrieving relevant documents with domain-specific understanding 4. Providing high-quality results for technical AI/ML queries

This retriever is particularly useful when: - Building AI/ML focused applications and research tools - Need specialized retrieval for technical AI/ML content - Working with domain-specific artificial intelligence queries - Building systems that require expert-level AI/ML knowledge retrieval

The implementation integrates with LangChain Community’s ArceeRetriever while providing a consistent Haive configuration interface with secure API management.

Classes

ArceeRetrieverConfig

Configuration for Arcee retriever in the Haive framework.

Module Contents

class haive.core.engine.retriever.providers.ArceeRetrieverConfig.ArceeRetrieverConfig

Bases: haive.core.common.mixins.secure_config.SecureConfigMixin, haive.core.engine.retriever.retriever.BaseRetrieverConfig

Configuration for Arcee retriever in the Haive framework.

This retriever provides AI/ML focused retrieval capabilities through the Arcee service for domain-specific artificial intelligence and machine learning content.

retriever_type

The type of retriever (always ARCEE).

Type:

RetrieverType

api_key

API key for Arcee service (auto-resolved).

Type:

Optional[SecretStr]

model_name

Arcee model name to use for retrieval.

Type:

str

k

Number of documents to return.

Type:

int

endpoint_url

Custom endpoint URL for Arcee service.

Type:

Optional[str]

Examples

>>> from haive.core.engine.retriever import ArceeRetrieverConfig
>>>
>>> # Create Arcee retriever
>>> config = ArceeRetrieverConfig(
...     name="arcee_retriever",
...     model_name="arcee-ai/AI-Retriever-v1",
...     k=5
... )
>>>
>>> # Instantiate and use the retriever
>>> retriever = config.instantiate()
>>> docs = retriever.get_relevant_documents("latest transformer architectures")

get_input_fields()

Return input field definitions for Arcee retriever.

Return type:

dict[str, tuple[type, Any]]

get_output_fields()

Return output field definitions for Arcee retriever.

Return type:

dict[str, tuple[type, Any]]

instantiate()

Create an Arcee retriever from this configuration.

Returns:

Instantiated retriever ready for AI/ML focused retrieval.

Return type:

ArceeRetriever

Raises:

• ImportError – If required packages are not available.

• ValueError – If API key or configuration is invalid.