Update tests data

motleycrew/tools/simple_retriever_tool.py

@@ -1,11 +1,12 @@
-import os.path
+import os
+from typing import List, Optional
 
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_core.tools import StructuredTool
 from llama_index.core import (
-    VectorStoreIndex,
     SimpleDirectoryReader,
     StorageContext,
+    VectorStoreIndex,
     load_index_from_storage,
 )
 from llama_index.core.node_parser import SentenceSplitter

tests/itest_golden_data/advanced_output_handling_ipynb.json

@@ -1 +1 @@
-"def bubble_sort(arr):\n    n = len(arr)\n    for i in range(n):\n        for j in range(0, n-i-1):\n            if arr[j] > arr[j+1]:\n                arr[j], arr[j+1] = arr[j+1], arr[j]\n    return arr\n\n# Test the bubble sort implementation\nsample_list = [64, 34, 25, 12, 22, 11, 90]\nsorted_list = bubble_sort(sample_list)\nprint(sorted_list)\n\nThe `bubble_sort` function sorts a list of numbers in ascending order using the bubble sort algorithm. The algorithm works by repeatedly stepping through the list, comparing adjacent elements, and swapping them if they are in the wrong order. This process is repeated until the list is sorted. The outer loop runs `n` times, where `n` is the length of the list, and the inner loop runs `n-i-1` times, where `i` is the current iteration of the outer loop. This ensures that the largest unsorted element \"bubbles\" to its correct position in each iteration."
+"from typing import List\n\ndef bubble_sort(arr: List[int]) -> None:\n    \"\"\"\n    Sorts a list of integers in ascending order using the bubble sort algorithm.\n    \n    Args:\n        arr (List[int]): The list of integers to be sorted.\n    \"\"\"\n    n = len(arr)\n    while n > 1:\n        new_n = 0\n        for i in range(1, n):\n            if arr[i-1] > arr[i]:\n                arr[i-1], arr[i] = arr[i], arr[i-1]\n                new_n = i\n        if new_n == 0:\n            break\n        n = new_n\n\ndef main() -> None:\n    \"\"\"\n    Test the bubble sort implementation with sample lists.\n    \"\"\"\n    test_cases = [\n        ([64, 34, 25, 12, 22, 11, 90], \"Sorted list\"),\n        ([], \"Sorted empty list\"),\n        ([1], \"Sorted single element list\"),\n        ([1, 2, 3, 4, 5], \"Sorted already sorted list\"),\n        ([3, 1, 2, 3, 1], \"Sorted list with duplicates\"),\n        ([3, -1, 2, -3, 1], \"Sorted list with negative numbers\"),\n        ([5, 5, 5, 5], \"Sorted list with identical elements\")\n    ]\n    \n    for lst, description in test_cases:\n        bubble_sort(lst)\n        print(f\"{description}: {lst}\")\n\nif __name__ == \"__main__\":\n    main()\n\nThe bubble sort implementation sorts a list of integers in ascending order by repeatedly comparing and swapping adjacent elements if they are in the wrong order. An optimization is added to detect the last position where a swap was made, allowing the loop to break early if the list is already sorted. The `main` function tests the implementation with various sample lists, including edge cases, and prints the sorted results."

tests/itest_golden_data/math_via_python_code_with_a_single_agent_ipynb.json

@@ -1 +1 @@
-"To solve the system of linear equations:\n\n\\[ 725x + 727y = 1500 \\]\n\\[ 729x + 731y = 1508 \\]\n\nwe first use the sympy library to solve for \\( x \\) and \\( y \\). The solutions are:\n\n\\[ x = -23 \\]\n\\[ y = 25 \\]\n\nNext, we calculate \\( x - y \\):\n\n\\[ x - y = -23 - 25 = -48 \\]\n\nThus, the values are:\n\n\\[ x = -23 \\]\n\\[ y = 25 \\]\n\\[ x - y = -48 \\]"
+"The system of linear equations is given by:\n\n\\[ 725x + 727y = 1500 \\]\n\\[ 729x + 731y = 1508 \\]\n\nTo solve for \\( x \\) and \\( y \\), we use the method of solving simultaneous equations. Using sympy, we find:\n\n\\[ x = -23 \\]\n\\[ y = 25 \\]\n\nNext, we calculate \\( x - y \\):\n\n\\[ x - y = -23 - 25 = -48 \\]\n\nThus, the values are:\n\n\\[ x = -23 \\]\n\\[ y = 25 \\]\n\\[ x - y = -48 \\]"

tests/itest_golden_data/multi_step_research_agent_ipynb.json

@@ -1 +1 @@
-"Why did Arjuna kill Karna, his half-brother?\n\nKrishna played a crucial role in Arjuna's decision to kill Karna. As Karna struggled to free his chariot wheel from the mud, he called out to Arjuna and Krishna, claiming they were honor-bound to let him fix his chariot. Krishna responded by questioning the honor in Karna's past actions, specifically the humiliation of Draupadi and the killing of Abhimanyu. When Karna attempted to launch the Brahmastra but forgot the mantra, as foretold by Parashurama, Krishna saw the opportunity and commanded Arjuna to kill Karna. Despite seeing Karna defenseless, Arjuna hesitated but ultimately obeyed Krishna's command and killed Karna with an arrow."
+"Why did Arjuna kill Karna, his half-brother?\n\nKrishna played a pivotal role in Arjuna's decision to kill Karna. When Karna's chariot got stuck in the mud, he appealed to Arjuna and Krishna for honor, asking them to let him fix his chariot. Krishna responded by questioning Karna's sense of honor, reminding him of his past actions: \"What kind of honor was it to humiliate Draupadi? What honor was there in butchering Abhimanyu?\" These rhetorical questions highlighted Karna's dishonorable deeds, thereby justifying his death. Additionally, Krishna emphasized the importance of dharma (duty) over personal feelings, urging Arjuna to act according to his warrior duty. Ultimately, Krishna's arguments about Karna's past dishonorable actions and the necessity of fulfilling one's duty convinced Arjuna to kill Karna."

tests/itest_golden_data/validating_agent_output_ipynb.json

@@ -1 +1 @@
-"### Comprehensive Analysis of AI Advancements in 2024\n\n#### Key Trends\n1. **Generative AI**: Generative AI continues to evolve, becoming more accessible and useful for the general public. This technology, which gained significant traction in 2023, is now being integrated into various applications, from creative tools to business solutions.\n\n2. **Multimodal AI**: This trend involves AI systems that can process and integrate multiple types of data inputs, such as text, images, and sound. This advancement aims to mimic human sensory processing and is expected to enhance the capabilities of AI in understanding and interacting with the world.\n\n3. **AI Integration in Daily Life**: AI is becoming more embedded in everyday activities, with companies like Microsoft and Google incorporating AI assistants into their products. This trend is making AI more ubiquitous and user-friendly.\n\n#### Breakthrough Technologies\n1. **Advanced Generative Models**: New generative models are being developed that offer improved performance and versatility. These models are capable of creating more realistic and complex outputs, which can be used in various fields such as entertainment, design, and content creation.\n\n2. **AI in Healthcare**: AI technologies are making significant strides in healthcare, with applications ranging from diagnostic tools to personalized treatment plans. These advancements are expected to improve patient outcomes and streamline healthcare processes.\n\n3. **AI for Decision-Making**: Cutting-edge AI technologies are being designed to assist in decision-making processes across industries. These systems can analyze large datasets, identify patterns, and provide insights that help businesses and organizations make informed decisions.\n\n4. **AI in Physics**: AI is being applied in physics to develop new techniques for classifying phase transitions in materials, coupling AI with fundamental physics for faster calculations, and aiding theoretical investigations in pure mathematics and theoretical physics. These applications are driving a new paradigm in AI discovery and enhancing our understanding of physical systems.\n\n#### Potential Industry Impacts\n1. **Manufacturing**: The manufacturing sector is poised to benefit greatly from AI, with applications in demand forecasting, supply chain optimization, and product development. AI's ability to analyze data and predict trends can lead to more efficient and cost-effective manufacturing processes.\n\n2. **Finance**: AI is transforming the finance industry by enhancing risk management, fraud detection, and customer service. Financial institutions are leveraging AI to improve their operations and offer better services to their clients.\n\n3. **Healthcare**: As mentioned earlier, AI's impact on healthcare is profound. From improving diagnostic accuracy to personalizing treatment plans, AI is set to revolutionize the healthcare industry, making it more efficient and patient-centric.\n\n4. **Public Perception and Regulation**: There is a growing awareness and nervousness about AI's potential impact on society. Surveys indicate an increase in public concern about AI products and services, which may lead to more stringent regulations and ethical considerations in AI development and deployment.\n\n### Conclusion\nThe advancements in AI in 2024 are marked by significant technological breakthroughs and widespread integration into various industries. Generative AI, multimodal AI, and AI-driven decision-making are some of the key trends shaping the future. These technologies are expected to bring about substantial benefits, particularly in manufacturing, finance, healthcare, and physics. However, the increasing public concern about AI's impact highlights the need for responsible development and regulation to ensure that AI technologies are used ethically and beneficially."
+"**Comprehensive Analysis of the Latest Advancements in AI in 2024**\n\n**1. Key Trends in AI:**\n\n- **Generative AI:**\n  Generative AI has seen significant advancements in 2024, becoming more integrated into enterprise applications and daily life. According to the latest McKinsey Global Survey on AI, 65% of organizations are regularly using generative AI, nearly double the percentage from the previous year. Generative AI tools like ChatGPT have reached mass adoption, resetting the course of the industry. By 2024, 40% of enterprise applications are expected to come with conversational AI as an embedded feature, enhancing user interaction and productivity.\n\n- **Multimodal AI:**\n  Multimodal AI is evolving significantly, incorporating multiple input types such as text, images, and sound. This advancement mimics the human ability to process diverse sensory information, leading to more nuanced and holistic AI models. Multimodal AI is expected to enhance generative AI capabilities, allowing AI to support humans in performing more tasks across various environments. This trend is identified in the 2024 Gartner Hype Cycle for Generative AI, highlighting its potential for competitive advantage and time-to-market benefits.\n\n**2. Breakthrough Technologies:**\n\n- **Conversational AI:**\n  Conversational AI is becoming more intuitive, dynamic, and human-like, thanks to advancements in machine learning (ML) and natural language processing (NLP). These technologies are making AI-powered chatbots more sophisticated, offering personalized customer service and support 24/7. The rise of conversational AI is transforming customer service, providing faster and more accurate responses to customer queries.\n\n- **Generative AI-Augmented Apps and Services:**\n  Generative AI is being embedded into various applications and services, enhancing their functionality and user experience. This integration is making generative AI more accessible to non-tech users, allowing them to leverage AI capabilities in their daily tasks. The proliferation of generative AI-augmented apps is expected to drive innovation and efficiency across multiple industries.\n\n**3. Potential Industry Impacts:**\n\n- **Customer Service:**\n  The integration of generative AI and conversational AI is revolutionizing customer service. AI-powered chatbots are providing faster, more accurate, and personalized responses to customer queries, improving customer satisfaction and reducing operational costs for businesses.\n\n- **Healthcare:**\n  Multimodal AI is expected to have a significant impact on healthcare, enabling more accurate diagnostics and personalized treatment plans. By processing diverse data types, AI can provide a comprehensive understanding of patient conditions, leading to better healthcare outcomes.\n\n- **Enterprise Applications:**\n  The embedding of generative AI into enterprise applications is enhancing productivity and efficiency. AI-powered tools are automating routine tasks, providing intelligent insights, and improving decision-making processes. This trend is expected to drive significant business value and competitive advantage.\n\n- **Physics:**\n  AI is making substantial contributions to the field of physics. Researchers are using generative AI to develop physics-informed techniques for classifying phase transitions in materials, which are more efficient than existing machine-learning approaches. AI is also aiding theoretical investigations in pure mathematics and theoretical physics, and assisting with complex tasks in particle physics and astrophysics. These applications are accelerating research and providing deeper insights into fundamental physical phenomena.\n\n**Conclusion:**\nThe advancements in AI in 2024 are marked by the rise of generative AI, the evolution of multimodal AI, and their integration into various applications and industries. These trends are driving innovation, improving efficiency, and transforming customer experiences. As AI continues to evolve, its impact on industries and daily life is expected to grow, offering new possibilities and opportunities for businesses and individuals alike."