Merge branch 'main' into feature/rabbitmq_worker

README.rst

@@ -91,7 +91,7 @@
 - `Чат поддержки <https://t.me/protollm_helpdesk>`_
 
 Статьи о решениях, основанных на ProtoLLM:
-========================================
+==========================================
 - Zakharov K. et al. Forecasting Population Migration in Small Settlements Using Generative Models under Conditions of Data Scarcity //Smart Cities. – 2024. – Т. 7. – №. 5. – С. 2495-2513.
 - Kovalchuk M. A. et al. SemConvTree: Semantic Convolutional Quadtrees for Multi-Scale Event Detection in Smart City //Smart Cities. – 2024. – Т. 7. – №. 5. – С. 2763-2780.
 - Kalyuzhnaya A. et al. LLM Agents for Smart City Management: Enhancing Decision Support through Multi-Agent AI Systems - 2024 - Under Review

README_en.rst

@@ -25,24 +25,24 @@ Intro
 Proto LLM features
 ==================
 - Rapid prototyping of information retrieval systems based on LLM using RAG:
-Implementations of architectural patterns for interacting with different databases and web service interfaces;
-Methods for optimising RAG pipelines to eliminate redundancy.
+   Implementations of architectural patterns for interacting with different databases and web service interfaces;
+   Methods for optimising RAG pipelines to eliminate redundancy.
 
 - Development and integration of applications with LLM with connection of external services and models through plugin system:
-Integration with AutoML solutions for predictive tasks;
-Providing structured output generation and validation;
+   Integration with AutoML solutions for predictive tasks;
+   Providing structured output generation and validation;
 
 - Implementation of ensemble methods and multi-agent approaches to improve the efficiency of LLMs:
-Possibility of combining arbitrary LLMs into ensembles to improve generation quality, automatic selection of ensemble composition;
-Work with model-agents and ensemble pipelines;
+   Possibility of combining arbitrary LLMs into ensembles to improve generation quality, automatic selection of ensemble composition;
+   Work with model-agents and ensemble pipelines;
 
 - Generation of complex synthetic data for further training and improvement of LLM:
-Generating examples from existing models and data sets;
-Evolutionary optimisation to increase the diversity of examples; Integration with Label Studio;
+   Generating examples from existing models and data sets;
+   Evolutionary optimisation to increase the diversity of examples; Integration with Label Studio;
 
 - Providing interoperability with various LLM providers:
-Support for native models (GigaChat, YandexGPT, vsegpt, etc.).
-Interaction with open-source models deployed locally.
+   Support for native models (GigaChat, YandexGPT, vsegpt, etc.).
+   Interaction with open-source models deployed locally.
 
 
 Installation
@@ -106,7 +106,7 @@ Contacts
 - `Helpdesk chat <https://t.me/protollm_helpdesk>`_
 
 Papers about ProtoLLM-based solutions:
-=====================================
+======================================
 - Zakharov K. et al. Forecasting Population Migration in Small Settlements Using Generative Models under Conditions of Data Scarcity //Smart Cities. – 2024. – Т. 7. – №. 5. – С. 2495-2513.
 - Kovalchuk M. A. et al. SemConvTree: Semantic Convolutional Quadtrees for Multi-Scale Event Detection in Smart City //Smart Cities. – 2024. – Т. 7. – №. 5. – С. 2763-2780.
 - Kalyuzhnaya A. et al. LLM Agents for Smart City Management: Enhancing Decision Support through Multi-Agent AI Systems - 2024 - Under Review

protollm_tools/sdk/protollm_sdk/object_interface/rabbit_mq_wrapper.py

@@ -49,19 +49,16 @@ def publish_message(self, queue_name: str, message: dict, priority: int = None):
         """
         try:
             with self.get_channel() as channel:
-                # Declare the queue with priority if specified
                 arguments = {}
                 if priority is not None:
-                    arguments['x-max-priority'] = 10  # Set the maximum priority level
+                    arguments['x-max-priority'] = 10
 
                 channel.queue_declare(queue=queue_name, durable=True, arguments=arguments)
 
-                # Publish the message with the specified priority
                 properties = pika.BasicProperties(
-                    delivery_mode=2,  # Make message persistent
-                    priority=priority if priority is not None else 0  # Default to 0 if no priority
+                    delivery_mode=2,
+                    priority=priority if priority is not None else 0
                 )
-
                 channel.basic_publish(
                     exchange='',
                     routing_key=queue_name,

protollm_tools/sdk/tests/protollm_sdk/object_interface/unit/test_rabbit_mq_wrapper.py

@@ -46,20 +46,18 @@ def test_publish_message_with_priority(rabbit_wrapper, mock_pika):
 
     rabbit_wrapper.publish_message(queue_name, message, priority=priority)
 
-    # Проверяем, что очередь была объявлена с аргументом 'x-max-priority'
     mock_pika.queue_declare.assert_called_once_with(
         queue=queue_name,
         durable=True,
-        arguments={"x-max-priority": 10}  # Убедитесь, что максимальный приоритет соответствует вашему коду
+        arguments={"x-max-priority": 10}
     )
 
-    # Проверяем, что сообщение было опубликовано с заданным приоритетом
     mock_pika.basic_publish.assert_called_once_with(
         exchange="",
         routing_key=queue_name,
         body=json.dumps(message),
         properties=pika.BasicProperties(
-            delivery_mode=2,  # Сделать сообщение постоянным
+            delivery_mode=2,
             priority=priority
         ),
     )

pyproject.toml

@@ -1,9 +1,9 @@
 [tool.poetry]
+readme = "README_en.rst"
 name = "ProtoLLM"
 version = "0.1.0"
 description = ""
 authors = ["aimclub"]
-readme = "README.rst"
 
 
 [tool.poetry.dependencies]