julee.services.knowledge_service.memory

Memory-based implementation of KnowledgeService for testing and development.

This module provides an in-memory implementation of the KnowledgeService protocol that stores file registrations in memory and returns configurable canned responses for queries.

Submodules

Classes

MemoryKnowledgeService

In-memory implementation of the KnowledgeService protocol.

Package Contents

class julee.services.knowledge_service.memory.MemoryKnowledgeService(config)[source]

Bases: julee.services.knowledge_service.knowledge_service.KnowledgeService

In-memory implementation of the KnowledgeService protocol.

This class stores file registrations in memory using a dictionary keyed by knowledge_service_file_id. Query results are returned from a configurable queue of canned responses.

Useful for testing and development scenarios where you want to avoid external service dependencies while still exercising the full knowledge service workflow.

add_canned_query_result(query_result)[source]

Add a canned query result to be returned by execute_query.

Parameters:

query_result (julee.services.knowledge_service.knowledge_service.QueryResult) – QueryResult to return from future execute_query calls

add_canned_query_results(query_results)[source]

Add multiple canned query results to be returned by execute_query.

Parameters:

query_results (list[julee.services.knowledge_service.knowledge_service.QueryResult]) – List of QueryResult objects to return from future execute_query calls

clear_canned_query_results()[source]

Clear all canned query results.

async execute_query(config, query_text, output_schema=None, service_file_ids=None, query_metadata=None, assistant_prompt=None)[source]

Execute a query by returning a canned response.

Parameters:

  • config (julee.domain.models.knowledge_service_config.KnowledgeServiceConfig) – KnowledgeServiceConfig for this operation

  • query_text (str) – The query to execute

  • output_schema (dict[str, Any] | None) – Optional JSON schema for structured response

  • service_file_ids (list[str] | None) – Optional list of service file IDs for query

  • query_metadata (dict[str, Any] | None) – Optional service-specific metadata

  • assistant_prompt (str | None) – Optional assistant message content (ignored in memory implementation)

Returns:

QueryResult from the queue of canned responses

Raises:

ValueError – If no canned query results are available

Return type:

julee.services.knowledge_service.knowledge_service.QueryResult

get_all_registered_files()[source]

Get all registered files.

Returns:

Dictionary mapping knowledge_service_file_id to FileRegistrationResult

Return type:

dict[str, julee.services.knowledge_service.knowledge_service.FileRegistrationResult]

get_registered_file(knowledge_service_file_id)[source]

Get a registered file by its knowledge service file ID.

Parameters:

knowledge_service_file_id (str) – The file ID assigned by this service

Returns:

FileRegistrationResult if found, None otherwise

Return type:

julee.services.knowledge_service.knowledge_service.FileRegistrationResult | None

async register_file(config, document)[source]

Register a document file by storing metadata in memory.

Parameters:
Returns:

FileRegistrationResult with memory-specific details

Return type:

julee.services.knowledge_service.knowledge_service.FileRegistrationResult

config