mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 08:26:21 +02:00
RabbitMQ pub/sub backend with topic exchange architecture (#752)
Adds a RabbitMQ backend as an alternative to Pulsar, selectable via PUBSUB_BACKEND=rabbitmq. Both backends implement the same PubSubBackend protocol — no application code changes needed to switch. RabbitMQ topology: - Single topic exchange per topicspace (e.g. 'tg') - Routing key derived from queue class and topic name - Shared consumers: named queue bound to exchange (competing, round-robin) - Exclusive consumers: anonymous auto-delete queue (broadcast, each gets every message). Used by Subscriber and config push consumer. - Thread-local producer connections (pika is not thread-safe) - Push-based consumption via basic_consume with process_data_events for heartbeat processing Consumer model changes: - Consumer class creates one backend consumer per concurrent task (required for pika thread safety, harmless for Pulsar) - Consumer class accepts consumer_type parameter - Subscriber passes consumer_type='exclusive' for broadcast semantics - Config push consumer uses consumer_type='exclusive' so every processor instance receives config updates - handle_one_from_queue receives consumer as parameter for correct per-connection ack/nack LibrarianClient: - New shared client class replacing duplicated librarian request-response code across 6+ services (chunking, decoders, RAG, etc.) - Uses stream-document instead of get-document-content for fetching document content in 1MB chunks (avoids broker message size limits) - Standalone object (self.librarian = LibrarianClient(...)) not a mixin - get-document-content marked deprecated in schema and OpenAPI spec Serialisation: - Extracted dataclass_to_dict/dict_to_dataclass to shared serialization.py (used by both Pulsar and RabbitMQ backends) Librarian queues: - Changed from flow class (persistent) back to request/response class now that stream-document eliminates large single messages - API upload chunk size reduced from 5MB to 3MB to stay under broker limits after base64 encoding Factory and CLI: - get_pubsub() handles 'rabbitmq' backend with RabbitMQ connection params - add_pubsub_args() includes RabbitMQ options (host, port, credentials) - add_pubsub_args(standalone=True) defaults to localhost for CLI tools - init_trustgraph skips Pulsar admin setup for non-Pulsar backends - tg-dump-queues and tg-monitor-prompts use backend abstraction - BaseClient and ConfigClient accept generic pubsub config
This commit is contained in:
cybermaggedon
GitHub
parent
4fb0b4d8e8
commit
24f0190ce7
36 changed files with 1277 additions and 1313 deletions
|
|
@ -24,8 +24,8 @@ class MockAsyncProcessor:
|
|||
class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
||||
"""Test Recursive chunker functionality"""
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
def test_processor_initialization_basic(self, mock_producer, mock_consumer):
|
||||
"""Test basic processor initialization"""
|
||||
|
|
@ -51,8 +51,8 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
if hasattr(spec, 'name') and spec.name in ['chunk-size', 'chunk-overlap']]
|
||||
assert len(param_specs) == 2
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
async def test_chunk_document_with_chunk_size_override(self, mock_producer, mock_consumer):
|
||||
"""Test chunk_document with chunk-size parameter override"""
|
||||
|
|
@ -71,7 +71,7 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
mock_message = MagicMock()
|
||||
mock_consumer = MagicMock()
|
||||
mock_flow = MagicMock()
|
||||
mock_flow.side_effect = lambda param: {
|
||||
mock_flow.parameters.get.side_effect = lambda param: {
|
||||
"chunk-size": 2000, # Override chunk size
|
||||
"chunk-overlap": None # Use default chunk overlap
|
||||
}.get(param)
|
||||
|
|
@ -85,8 +85,8 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
assert chunk_size == 2000 # Should use overridden value
|
||||
assert chunk_overlap == 100 # Should use default value
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
async def test_chunk_document_with_chunk_overlap_override(self, mock_producer, mock_consumer):
|
||||
"""Test chunk_document with chunk-overlap parameter override"""
|
||||
|
|
@ -105,7 +105,7 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
mock_message = MagicMock()
|
||||
mock_consumer = MagicMock()
|
||||
mock_flow = MagicMock()
|
||||
mock_flow.side_effect = lambda param: {
|
||||
mock_flow.parameters.get.side_effect = lambda param: {
|
||||
"chunk-size": None, # Use default chunk size
|
||||
"chunk-overlap": 200 # Override chunk overlap
|
||||
}.get(param)
|
||||
|
|
@ -119,8 +119,8 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
assert chunk_size == 1000 # Should use default value
|
||||
assert chunk_overlap == 200 # Should use overridden value
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
async def test_chunk_document_with_both_parameters_override(self, mock_producer, mock_consumer):
|
||||
"""Test chunk_document with both chunk-size and chunk-overlap overrides"""
|
||||
|
|
@ -139,7 +139,7 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
mock_message = MagicMock()
|
||||
mock_consumer = MagicMock()
|
||||
mock_flow = MagicMock()
|
||||
mock_flow.side_effect = lambda param: {
|
||||
mock_flow.parameters.get.side_effect = lambda param: {
|
||||
"chunk-size": 1500, # Override chunk size
|
||||
"chunk-overlap": 150 # Override chunk overlap
|
||||
}.get(param)
|
||||
|
|
@ -153,8 +153,8 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
assert chunk_size == 1500 # Should use overridden value
|
||||
assert chunk_overlap == 150 # Should use overridden value
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.chunking.recursive.chunker.RecursiveCharacterTextSplitter')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
async def test_on_message_uses_flow_parameters(self, mock_splitter_class, mock_producer, mock_consumer):
|
||||
|
|
@ -177,7 +177,7 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
processor = Processor(**config)
|
||||
|
||||
# Mock save_child_document to avoid waiting for librarian response
|
||||
processor.save_child_document = AsyncMock(return_value="mock-doc-id")
|
||||
processor.librarian.save_child_document = AsyncMock(return_value="mock-doc-id")
|
||||
|
||||
# Mock message with TextDocument
|
||||
mock_message = MagicMock()
|
||||
|
|
@ -196,12 +196,14 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
mock_producer = AsyncMock()
|
||||
mock_triples_producer = AsyncMock()
|
||||
mock_flow = MagicMock()
|
||||
mock_flow.side_effect = lambda param: {
|
||||
mock_flow.parameters.get.side_effect = lambda param: {
|
||||
"chunk-size": 1500,
|
||||
"chunk-overlap": 150,
|
||||
}.get(param)
|
||||
mock_flow.side_effect = lambda name: {
|
||||
"output": mock_producer,
|
||||
"triples": mock_triples_producer,
|
||||
}.get(param)
|
||||
}.get(name)
|
||||
|
||||
# Act
|
||||
await processor.on_message(mock_message, mock_consumer, mock_flow)
|
||||
|
|
@ -219,8 +221,8 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
sent_chunk = mock_producer.send.call_args[0][0]
|
||||
assert isinstance(sent_chunk, Chunk)
|
||||
|
||||
@patch('trustgraph.base.chunking_service.Consumer')
|
||||
@patch('trustgraph.base.chunking_service.Producer')
|
||||
@patch('trustgraph.base.librarian_client.Consumer')
|
||||
@patch('trustgraph.base.librarian_client.Producer')
|
||||
@patch('trustgraph.base.async_processor.AsyncProcessor', MockAsyncProcessor)
|
||||
async def test_chunk_document_with_no_overrides(self, mock_producer, mock_consumer):
|
||||
"""Test chunk_document when no parameters are overridden (flow returns None)"""
|
||||
|
|
@ -239,7 +241,7 @@ class TestRecursiveChunkerSimple(IsolatedAsyncioTestCase):
|
|||
mock_message = MagicMock()
|
||||
mock_consumer = MagicMock()
|
||||
mock_flow = MagicMock()
|
||||
mock_flow.return_value = None # No overrides
|
||||
mock_flow.parameters.get.return_value = None # No overrides
|
||||
|
||||
# Act
|
||||
chunk_size, chunk_overlap = await processor.chunk_document(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue