chore: update roadmap content json

Author: saga

public/roadmap-content/ai-engineer.json

@@ -471,17 +471,6 @@
       }
     ]
   },
-  "5ShWZl1QUqPwO-NRGN85V": {
-    "title": "OpenAI Models",
-    "description": "OpenAI provides a variety of models designed for diverse tasks. GPT models like GPT-3 and GPT-4 handle text generation, conversation, and translation, offering context-aware responses, while Codex specializes in generating and debugging code across multiple languages. DALL-E creates images from text descriptions, supporting applications in design and content creation, and Whisper is a speech recognition model that converts spoken language to text for transcription and voice-to-text tasks.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "OpenAI Models Overview",
-        "url": "https://platform.openai.com/docs/models",
-        "type": "article"
-      }
-    ]
-  },
   "zdeuA4GbdBl2DwKgiOA4G": {
     "title": "OpenAI API",
     "description": "The OpenAI API provides access to powerful AI models like GPT, Codex, DALL-E, and Whisper, enabling developers to integrate capabilities such as text generation, code assistance, image creation, and speech recognition into their applications via a simple, scalable interface.\n\nLearn more from the following resources:",
@@ -1323,21 +1312,10 @@
       }
     ]
   },
-  "lVhWhZGR558O-ljHobxIi": {
-    "title": "RAG & Implementation",
-    "description": "Retrieval-Augmented Generation (RAG) combines information retrieval with language generation to produce more accurate, context-aware responses. It uses two components: a retriever, which searches a database to find relevant information, and a generator, which crafts a response based on the retrieved data. Implementing RAG involves using a retrieval model (e.g., embeddings and vector search) alongside a generative language model (like GPT). The process starts by converting a query into embeddings, retrieving relevant documents from a vector database, and feeding them to the language model, which then generates a coherent, informed response. This approach grounds outputs in real-world data, resulting in more reliable and detailed answers.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "What is RAG?",
-        "url": "https://aws.amazon.com/what-is/retrieval-augmented-generation/",
-        "type": "article"
-      },
-      {
-        "title": "What is Retrieval-Augmented Generation? IBM",
-        "url": "https://www.youtube.com/watch?v=T-D1OfcDW1M",
-        "type": "video"
-      }
-    ]
+  "[email protected]": {
+    "title": "What are RAGs?",
+    "description": "",
+    "links": []
   },
   "GCn4LGNEtPI0NWYAZCRE-": {
     "title": "RAG Usecases",
@@ -1487,53 +1465,20 @@
       }
     ]
   },
-  "ebXXEhNRROjbbof-Gym4p": {
+  "[email protected]": {
     "title": "Langchain",
-    "description": "LangChain is a development framework that simplifies building applications powered by language models, enabling seamless integration of multiple AI models and data sources. It focuses on creating chains, or sequences, of operations where language models can interact with databases, APIs, and other models to perform complex tasks. LangChain offers tools for prompt management, data retrieval, and workflow orchestration, making it easier to develop robust, scalable applications like chatbots, automated data analysis, and multi-step reasoning systems.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "LangChain",
-        "url": "https://www.langchain.com/",
-        "type": "article"
-      },
-      {
-        "title": "What is LangChain?",
-        "url": "https://www.youtube.com/watch?v=1bUy-1hGZpI",
-        "type": "video"
-      }
-    ]
+    "description": "",
+    "links": []
   },
-  "d0ontCII8KI8wfP-8Y45R": {
+  "[email protected]": {
     "title": "Llama Index",
-    "description": "LlamaIndex, formerly known as GPT Index, is a tool designed to facilitate the integration of large language models (LLMs) with structured and unstructured data sources. It acts as a data framework that helps developers build retrieval-augmented generation (RAG) applications by indexing various types of data, such as documents, databases, and APIs, enabling LLMs to query and retrieve relevant information efficiently.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "Llama Index",
-        "url": "https://docs.llamaindex.ai/en/stable/",
-        "type": "article"
-      },
-      {
-        "title": "Introduction to LlamaIndex with Python (2024)",
-        "url": "https://www.youtube.com/watch?v=cCyYGYyCka4",
-        "type": "video"
-      }
-    ]
+    "description": "",
+    "links": []
   },
-  "eOqCBgBTKM8CmY3nsWjre": {
-    "title": "Open AI Assistant API",
-    "description": "The OpenAI Assistant API enables developers to create advanced conversational systems using models like GPT-4. It supports multi-turn conversations, allowing the AI to maintain context across exchanges, which is ideal for chatbots, virtual assistants, and interactive applications. Developers can customize interactions by defining roles, such as system, user, and assistant, to guide the assistant's behavior. With features like temperature control, token limits, and stop sequences, the API offers flexibility to ensure responses are relevant, safe, and tailored to specific use cases.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "OpenAI Assistants API – Course for Beginners",
-        "url": "https://www.youtube.com/watch?v=qHPonmSX4Ms",
-        "type": "course"
-      },
-      {
-        "title": "Assistants API",
-        "url": "https://platform.openai.com/docs/assistants/overview",
-        "type": "article"
-      }
-    ]
+  "[email protected]": {
+    "title": "Open AI Response API",
+    "description": "",
+    "links": []
   },
   "c0RPhpD00VIUgF4HJgN2T": {
     "title": "Replicate",
@@ -1551,26 +1496,10 @@
       }
     ]
   },
-  "AeHkNU-uJ_gBdo5-xdpEu": {
+  "ai-agents@4_ap0rD9Gl6Ep_4jMfPpG.md": {
     "title": "AI Agents",
-    "description": "In AI engineering, \"agents\" refer to autonomous systems or components that can perceive their environment, make decisions, and take actions to achieve specific goals. Agents often interact with external systems, users, or other agents to carry out complex tasks. They can vary in complexity, from simple rule-based bots to sophisticated AI-powered agents that leverage machine learning models, natural language processing, and reinforcement learning.\n\nVisit the following resources to learn more:",
-    "links": [
-      {
-        "title": "Building an AI Agent Tutorial - LangChain",
-        "url": "https://python.langchain.com/docs/tutorials/agents/",
-        "type": "article"
-      },
-      {
-        "title": "AI agents and their types",
-        "url": "https://play.ht/blog/ai-agents-use-cases/",
-        "type": "article"
-      },
-      {
-        "title": "The Complete Guide to Building AI Agents for Beginners",
-        "url": "https://youtu.be/MOyl58VF2ak?si=-QjRD_5y3iViprJX",
-        "type": "video"
-      }
-    ]
+    "description": "",
+    "links": []
   },
   "778HsQzTuJ_3c9OSn5DmH": {
     "title": "Agents Usecases",
@@ -1641,21 +1570,10 @@
       }
     ]
   },
-  "mbp2NoL-VZ5hZIIblNBXt": {
-    "title": "OpenAI Assistant API",
-    "description": "The OpenAI Assistant API enables developers to create advanced conversational systems using models like GPT-4. It supports multi-turn conversations, allowing the AI to maintain context across exchanges, which is ideal for chatbots, virtual assistants, and interactive applications. Developers can customize interactions by defining roles, such as system, user, and assistant, to guide the assistant's behavior. With features like temperature control, token limits, and stop sequences, the API offers flexibility to ensure responses are relevant, safe, and tailored to specific use cases.\n\nLearn more from the following resources:",
-    "links": [
-      {
-        "title": "OpenAI Assistants API – Course for Beginners",
-        "url": "https://www.youtube.com/watch?v=qHPonmSX4Ms",
-        "type": "course"
-      },
-      {
-        "title": "Assistants API",
-        "url": "https://platform.openai.com/docs/assistants/overview",
-        "type": "article"
-      }
-    ]
+  "[email protected]": {
+    "title": "OpenAI Response API",
+    "description": "",
+    "links": []
   },
   "W7cKPt_UxcUgwp8J6hS4p": {
     "title": "Multimodal AI",
@@ -1968,5 +1886,75 @@
         "type": "article"
       }
     ]
+  },
+  "[email protected]": {
+    "title": "Haystack",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "RAGFlow",
+    "description": "",
+    "links": []
+  },
+  "model-context-protocol-mcp@AeHkNU-uJ_gBdo5-xdpEu.md": {
+    "title": "Model Context Protocol (MCP)",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "MCP Host",
+    "description": "",
+    "links": []
+  },
+  "mcp-server@8Xkd88EjX3GE_9DWQhr7G.md": {
+    "title": "MCP Server",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "MCP Client",
+    "description": "",
+    "links": []
+  },
+  "data-layer@Z0920V57_ziDhXbQJMN9O.md": {
+    "title": "Data Layer",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "Transport Layer",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "Building an MCP Server",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "Building an MCP Client",
+    "description": "",
+    "links": []
+  },
+  "connect-to-local-server@H-G93SsEgsA_NGL_v4hPv.md": {
+    "title": "Connect to Local Server",
+    "description": "",
+    "links": []
+  },
+  "connect-to-remote-server@2t4uINxmzfx8FUF-_i_2B.md": {
+    "title": "Connect to Remote Server",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "Vertex AI",
+    "description": "",
+    "links": []
+  },
+  "[email protected]": {
+    "title": "Google ADK",
+    "description": "",
+    "links": []
   }
 }

public/roadmap-content/devops.json

@@ -2193,32 +2193,6 @@
       }
     ]
   },
-  "-pGF3soruWWxwE4LxE5Vk": {
-    "title": "Travis CI",
-    "description": "Travis CI is a cloud-based continuous integration (CI) service that automatically builds and tests code changes in GitHub repositories. It helps streamline the software development process by automatically running tests and building applications whenever code is pushed or a pull request is made. Travis CI supports a variety of programming languages and provides integration with other tools and services, offering features like build matrix configurations, deployment pipelines, and notifications. Its ease of setup and integration with GitHub makes it a popular choice for open-source and private projects looking to implement CI/CD practices.\n\nVisit the following resources to learn more:",
-    "links": [
-      {
-        "title": "Travis CI Documentation",
-        "url": "https://docs.travis-ci.com/",
-        "type": "article"
-      },
-      {
-        "title": "Travis CI Tutorial",
-        "url": "https://docs.travis-ci.com/user/tutorial/",
-        "type": "article"
-      },
-      {
-        "title": "Explore top posts about CI/CD",
-        "url": "https://app.daily.dev/tags/cicd?ref=roadmapsh",
-        "type": "article"
-      },
-      {
-        "title": "Travis CI Complete Tutorial for DevOps Engineers",
-        "url": "https://www.youtube.com/watch?v=xLWDOLhTH38",
-        "type": "video"
-      }
-    ]
-  },
   "1-JneOQeGhox-CKrdiquq": {
     "title": "Circle CI",
     "description": "CircleCI is a popular continuous integration and continuous delivery (CI/CD) platform that automates the build, test, and deployment processes of software projects. It supports a wide range of programming languages and integrates with various version control systems, primarily GitHub and Bitbucket. CircleCI uses a YAML configuration file to define pipelines, allowing developers to specify complex workflows, parallel job execution, and custom environments. It offers features like caching, artifact storage, and Docker layer caching to speed up builds. With its cloud-based and self-hosted options, CircleCI provides scalable solutions for projects of all sizes, helping teams improve code quality, accelerate release cycles, and streamline their development workflows.\n\nVisit the following resources to learn more:",
@@ -2240,26 +2214,10 @@
       }
     ]
   },
-  "TsXFx1wWikVBVoFUUDAMx": {
-    "title": "Drone",
-    "description": "Drone is an open-source continuous integration (CI) platform built on container technology. It automates building, testing, and deploying code using a simple, YAML-based pipeline configuration stored alongside the source code. Drone executes each step of the CI/CD process in isolated Docker containers, ensuring consistency and reproducibility. It supports multiple version control systems, offers parallel execution of pipeline steps, and provides plugins for integrating with various tools and services. Drone's lightweight, scalable architecture makes it suitable for projects of all sizes, from small teams to large enterprises. Its focus on simplicity and containerization aligns well with modern DevOps practices and microservices architectures.\n\nVisit the following resources to learn more:",
-    "links": [
-      {
-        "title": "Drone",
-        "url": "https://www.drone.io/",
-        "type": "article"
-      },
-      {
-        "title": "Drone Documentation",
-        "url": "https://docs.drone.io/",
-        "type": "article"
-      },
-      {
-        "title": "Drone CI Quickstart",
-        "url": "https://www.youtube.com/watch?v=Qf8EHRzAgHQ",
-        "type": "video"
-      }
-    ]
+  "[email protected]": {
+    "title": "Octopus Deploy",
+    "description": "",
+    "links": []
   },
   "L000AbzF3oLcn4B1eUIYX": {
     "title": "TeamCity",

public/roadmap-content/docker.json

@@ -378,22 +378,6 @@
       }
     ]
   },
-  "HlTxLqKNFMhghtKF6AcWu": {
-    "title": "Interactive Test Environments",
-    "description": "Docker allows you to create isolated, disposable environments that can be deleted once you're done with testing. This makes it much easier to work with third party software, test different dependencies or versions, and quickly experiment without the risk of damaging your local setup.\n\nVisit the following resources to learn more:",
-    "links": [
-      {
-        "title": "Launch a Dev Environment",
-        "url": "https://docs.docker.com/desktop/dev-environments/create-dev-env/",
-        "type": "article"
-      },
-      {
-        "title": "Test Environments - Medium",
-        "url": "https://manishsaini74.medium.com/containerized-testing-orchestrating-test-environments-with-docker-5201bfadfdf2",
-        "type": "article"
-      }
-    ]
-  },
   "YzpB7rgSR4ueQRLa0bRWa": {
     "title": "Command Line Utilities",
     "description": "Docker images can include command line utilities or standalone applications that we can run inside containers.\n\nVisit the following resources to learn more:",

public/roadmap-content/engineering-manager.json

@@ -568,11 +568,6 @@
     "description": "The role of an Engineering Manager extends to external collaboration as well. Here, they often serve the role of liaising with external teams, vendors, or partners, aligning goals and ensuring smooth communication flow. The key responsibilities include managing relationships, understanding the partner ecosystem, and negotiating win-win situations.\n\nEngineering Managers face challenges like cultural differences, communication hurdles, or time zone disparities. They address these by building reliability through regular updates, clear agendas, and understanding each other's work culture.\n\nTo succeed, Engineering Managers need good interpersonal skills, a keen eye for future opportunities, and the ability to adapt quickly. An understanding of business and sales, alongside engineering knowledge, can be advantageous too. This role needs balance - drive details when necessary and step back and delegate when appropriate.",
     "links": []
   },
-  "TQY4hjo56rDdlbzjs_-nl": {
-    "title": "Competitive Analysis",
-    "description": "An Engineering Manager uses competitive analysis to understand market trends and competitor strategies. This aids in decision-making and strategic planning. Their key responsibilities include identifying key competitors, analyzing their products, sales, and marketing strategies.\n\nChallenges may arise from having incomplete or inaccurate data. In these cases, Engineering Managers have to rely on their judgement and experience. Their analysis should be unbiased and as accurate as possible to influence the right design and development strategies.\n\nSuccessful competitive analysis requires strong analytical skills, keen attention to detail, and the ability to understand complex market dynamics. Managers must stay updated on market trend, technological advancements and be able to distinguish their company's unique selling proposition. This will allow them to plan steps to maintain competitiveness in the market.",
-    "links": []
-  },
   "QUxpEK8smXRBs2gMdDInB": {
     "title": "Legacy System Retirement",
     "description": "Every Engineering Manager knows the value and hurdles of legacy system retirement. They must plan and manage this complex task with a keen understanding of the system's purpose, its interdependencies, and potential risks of its retirement. Key responsibilities include assessing the impact on users, mitigating downtime, and ensuring business continuity.\n\nChallenges often arise from lack of documentation or knowledge about the legacy system. To overcome this, they could organize knowledge-sharing sessions with long-standing team members, assessing external help, or gradual transition methods.\n\nThe successful retirement of a legacy system requires a comprehensive approach, good interpersonal skills for team collaboration, and strong decision-making skills. An Engineering Manager has to balance the system’s business value against the cost and risk of maintaining it.",