mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +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
|
|
@ -7,19 +7,15 @@ Supports both inline document data and fetching from librarian via Pulsar
|
|||
for large documents.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import base64
|
||||
import logging
|
||||
import uuid
|
||||
import pytesseract
|
||||
from pdf2image import convert_from_bytes
|
||||
|
||||
from ... schema import Document, TextDocument, Metadata
|
||||
from ... schema import LibrarianRequest, LibrarianResponse, DocumentMetadata
|
||||
from ... schema import librarian_request_queue, librarian_response_queue
|
||||
from ... schema import Triples
|
||||
from ... base import FlowProcessor, ConsumerSpec, ProducerSpec
|
||||
from ... base import Consumer, Producer, ConsumerMetrics, ProducerMetrics
|
||||
from ... base import FlowProcessor, ConsumerSpec, ProducerSpec, LibrarianClient
|
||||
|
||||
from ... provenance import (
|
||||
document_uri, page_uri as make_page_uri, derived_entity_triples,
|
||||
|
|
@ -72,173 +68,16 @@ class Processor(FlowProcessor):
|
|||
)
|
||||
)
|
||||
|
||||
# Librarian client for fetching document content
|
||||
librarian_request_q = params.get(
|
||||
"librarian_request_queue", default_librarian_request_queue
|
||||
# Librarian client
|
||||
self.librarian = LibrarianClient(
|
||||
id=id, backend=self.pubsub, taskgroup=self.taskgroup,
|
||||
)
|
||||
librarian_response_q = params.get(
|
||||
"librarian_response_queue", default_librarian_response_queue
|
||||
)
|
||||
|
||||
librarian_request_metrics = ProducerMetrics(
|
||||
processor = id, flow = None, name = "librarian-request"
|
||||
)
|
||||
|
||||
self.librarian_request_producer = Producer(
|
||||
backend = self.pubsub,
|
||||
topic = librarian_request_q,
|
||||
schema = LibrarianRequest,
|
||||
metrics = librarian_request_metrics,
|
||||
)
|
||||
|
||||
librarian_response_metrics = ConsumerMetrics(
|
||||
processor = id, flow = None, name = "librarian-response"
|
||||
)
|
||||
|
||||
self.librarian_response_consumer = Consumer(
|
||||
taskgroup = self.taskgroup,
|
||||
backend = self.pubsub,
|
||||
flow = None,
|
||||
topic = librarian_response_q,
|
||||
subscriber = f"{id}-librarian",
|
||||
schema = LibrarianResponse,
|
||||
handler = self.on_librarian_response,
|
||||
metrics = librarian_response_metrics,
|
||||
)
|
||||
|
||||
# Pending librarian requests: request_id -> asyncio.Future
|
||||
self.pending_requests = {}
|
||||
|
||||
logger.info("PDF OCR processor initialized")
|
||||
|
||||
async def start(self):
|
||||
await super(Processor, self).start()
|
||||
await self.librarian_request_producer.start()
|
||||
await self.librarian_response_consumer.start()
|
||||
|
||||
async def on_librarian_response(self, msg, consumer, flow):
|
||||
"""Handle responses from the librarian service."""
|
||||
response = msg.value()
|
||||
request_id = msg.properties().get("id")
|
||||
|
||||
if request_id and request_id in self.pending_requests:
|
||||
future = self.pending_requests.pop(request_id)
|
||||
future.set_result(response)
|
||||
|
||||
async def fetch_document_metadata(self, document_id, user, timeout=120):
|
||||
"""
|
||||
Fetch document metadata from librarian via Pulsar.
|
||||
"""
|
||||
request_id = str(uuid.uuid4())
|
||||
|
||||
request = LibrarianRequest(
|
||||
operation="get-document-metadata",
|
||||
document_id=document_id,
|
||||
user=user,
|
||||
)
|
||||
|
||||
future = asyncio.get_event_loop().create_future()
|
||||
self.pending_requests[request_id] = future
|
||||
|
||||
try:
|
||||
await self.librarian_request_producer.send(
|
||||
request, properties={"id": request_id}
|
||||
)
|
||||
|
||||
response = await asyncio.wait_for(future, timeout=timeout)
|
||||
|
||||
if response.error:
|
||||
raise RuntimeError(
|
||||
f"Librarian error: {response.error.type}: {response.error.message}"
|
||||
)
|
||||
|
||||
return response.document_metadata
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
self.pending_requests.pop(request_id, None)
|
||||
raise RuntimeError(f"Timeout fetching metadata for {document_id}")
|
||||
|
||||
async def fetch_document_content(self, document_id, user, timeout=120):
|
||||
"""
|
||||
Fetch document content from librarian via Pulsar.
|
||||
"""
|
||||
request_id = str(uuid.uuid4())
|
||||
|
||||
request = LibrarianRequest(
|
||||
operation="get-document-content",
|
||||
document_id=document_id,
|
||||
user=user,
|
||||
)
|
||||
|
||||
# Create future for response
|
||||
future = asyncio.get_event_loop().create_future()
|
||||
self.pending_requests[request_id] = future
|
||||
|
||||
try:
|
||||
# Send request
|
||||
await self.librarian_request_producer.send(
|
||||
request, properties={"id": request_id}
|
||||
)
|
||||
|
||||
# Wait for response
|
||||
response = await asyncio.wait_for(future, timeout=timeout)
|
||||
|
||||
if response.error:
|
||||
raise RuntimeError(
|
||||
f"Librarian error: {response.error.type}: {response.error.message}"
|
||||
)
|
||||
|
||||
return response.content
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
self.pending_requests.pop(request_id, None)
|
||||
raise RuntimeError(f"Timeout fetching document {document_id}")
|
||||
|
||||
async def save_child_document(self, doc_id, parent_id, user, content,
|
||||
document_type="page", title=None, timeout=120):
|
||||
"""
|
||||
Save a child document to the librarian.
|
||||
"""
|
||||
request_id = str(uuid.uuid4())
|
||||
|
||||
doc_metadata = DocumentMetadata(
|
||||
id=doc_id,
|
||||
user=user,
|
||||
kind="text/plain",
|
||||
title=title or doc_id,
|
||||
parent_id=parent_id,
|
||||
document_type=document_type,
|
||||
)
|
||||
|
||||
request = LibrarianRequest(
|
||||
operation="add-child-document",
|
||||
document_metadata=doc_metadata,
|
||||
content=base64.b64encode(content).decode("utf-8"),
|
||||
)
|
||||
|
||||
# Create future for response
|
||||
future = asyncio.get_event_loop().create_future()
|
||||
self.pending_requests[request_id] = future
|
||||
|
||||
try:
|
||||
# Send request
|
||||
await self.librarian_request_producer.send(
|
||||
request, properties={"id": request_id}
|
||||
)
|
||||
|
||||
# Wait for response
|
||||
response = await asyncio.wait_for(future, timeout=timeout)
|
||||
|
||||
if response.error:
|
||||
raise RuntimeError(
|
||||
f"Librarian error saving child document: {response.error.type}: {response.error.message}"
|
||||
)
|
||||
|
||||
return doc_id
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
self.pending_requests.pop(request_id, None)
|
||||
raise RuntimeError(f"Timeout saving child document {doc_id}")
|
||||
await self.librarian.start()
|
||||
|
||||
async def on_message(self, msg, consumer, flow):
|
||||
|
||||
|
|
@ -250,7 +89,7 @@ class Processor(FlowProcessor):
|
|||
|
||||
# Check MIME type if fetching from librarian
|
||||
if v.document_id:
|
||||
doc_meta = await self.fetch_document_metadata(
|
||||
doc_meta = await self.librarian.fetch_document_metadata(
|
||||
document_id=v.document_id,
|
||||
user=v.metadata.user,
|
||||
)
|
||||
|
|
@ -265,7 +104,7 @@ class Processor(FlowProcessor):
|
|||
# Get PDF content - fetch from librarian or use inline data
|
||||
if v.document_id:
|
||||
logger.info(f"Fetching document {v.document_id} from librarian...")
|
||||
content = await self.fetch_document_content(
|
||||
content = await self.librarian.fetch_document_content(
|
||||
document_id=v.document_id,
|
||||
user=v.metadata.user,
|
||||
)
|
||||
|
|
@ -299,7 +138,7 @@ class Processor(FlowProcessor):
|
|||
page_content = text.encode("utf-8")
|
||||
|
||||
# Save page as child document in librarian
|
||||
await self.save_child_document(
|
||||
await self.librarian.save_child_document(
|
||||
doc_id=page_doc_id,
|
||||
parent_id=source_doc_id,
|
||||
user=v.metadata.user,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue