haive.core.engine.retriever.providers.ZepCloudRetrieverConfig

Zep Cloud Retriever implementation for the Haive framework.

from typing import Any This module provides a configuration class for the Zep Cloud retriever, which retrieves conversation history and memory from Zep’s cloud-hosted memory service. Zep Cloud provides managed long-term memory storage for conversational AI applications with enhanced features and reliability.

The ZepCloudRetriever works by: 1. Connecting to Zep Cloud service 2. Searching conversation history using semantic similarity 3. Retrieving relevant chat messages and context 4. Providing managed conversation memory

This retriever is particularly useful when: - Building conversational AI with cloud-hosted memory - Need reliable managed memory infrastructure - Want enhanced Zep features and performance - Building scalable chatbot applications - Need conversation history across sessions

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

Classes

ZepCloudRetrieverConfig

Configuration for Zep Cloud retriever in the Haive framework.

Module Contents

class haive.core.engine.retriever.providers.ZepCloudRetrieverConfig.ZepCloudRetrieverConfig

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

Configuration for Zep Cloud retriever in the Haive framework.

This retriever searches conversational memory stored in Zep Cloud and returns relevant chat history and context for AI applications.

retriever_type

The type of retriever (always ZEP_CLOUD).

Type:

RetrieverType

session_id

Zep session ID for conversation history.

Type:

str

api_key

Zep Cloud API key (auto-resolved from ZEP_API_KEY).

Type:

Optional[SecretStr]

api_url

Zep Cloud API URL.

Type:

str

top_k

Number of memory entries to retrieve.

Type:

int

search_type

Type of search to perform.

Type:

str

Examples

>>> from haive.core.engine.retriever import ZepCloudRetrieverConfig
>>>
>>> # Create the Zep Cloud retriever config
>>> config = ZepCloudRetrieverConfig(
...     name="zep_cloud_retriever",
...     session_id="user-123-session",
...     api_url="https://api.getzep.com",
...     top_k=10,
...     search_type="similarity"
... )
>>>
>>> # Instantiate and use the retriever
>>> retriever = config.instantiate()
>>> docs = retriever.get_relevant_documents("what did we discuss about AI?")
>>>
>>> # Example for MMR search
>>> mmr_config = ZepCloudRetrieverConfig(
...     name="zep_cloud_mmr_retriever",
...     session_id="user-123-session",
...     api_url="https://api.getzep.com",
...     search_type="mmr",
...     mmr_lambda=0.7
... )

get_input_fields()

Return input field definitions for Zep Cloud retriever.

Return type:

dict[str, tuple[type, Any]]

get_output_fields()

Return output field definitions for Zep Cloud retriever.

Return type:

dict[str, tuple[type, Any]]

instantiate()

Create a Zep Cloud retriever from this configuration.

Returns:

Instantiated retriever ready for cloud memory search.

Return type:

ZepCloudRetriever

Raises:

• ImportError – If required packages are not available.

• ValueError – If API key or session configuration is invalid.