{"id":28769,"date":"2026-04-22T10:02:31","date_gmt":"2026-04-22T10:02:31","guid":{"rendered":"https:\/\/hes.mephi.ru\/?page_id=28769"},"modified":"2026-04-22T10:02:31","modified_gmt":"2026-04-22T10:02:31","slug":"ai-and-llm-promptcontext-engineering","status":"publish","type":"page","link":"https:\/\/hes.mephi.ru\/?page_id=28769","title":{"rendered":"AI and LLM – PromptContext Engineering"},"content":{"rendered":"
\n
\n\t

\"\"<\/p>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div>

\n\t

\t\t\t\t\t\t\n\t\t\t\t\tDOWNLOAD THE FULL COURSE SYLLABUS<\/a><\/h3><\/div><\/div><\/div><\/div><\/div>
\n\t

\t\t\t\t\t\t\n\t\t\t\t\tBACK TO THE CURRICULUM<\/a><\/h3><\/div><\/div><\/div><\/div>
\n\t

\t\t\t\t\t\t\n\t\t\t\t\tBACK TO MASTER'S PROGRAM<\/a><\/h3><\/div><\/div><\/div><\/div>
\n\t

\t\t\t\t\t\t\n\t\t\t\t\tABOUT HES MEPHI<\/a><\/h3><\/div><\/div><\/div><\/div><\/div><\/div>
<\/div>
\n\t

Artificial Intelligence and Large Linguistic Models: Prompt and Context Engineering<\/h2><\/div><\/div><\/div>
\n
\n\t

This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.<\/span><\/span><\/h3>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div>
\n
\n\t \n

During the course, you\u2019ll dive into the world of modern artificial intelligence technologies and gain a comprehensive understanding of how cutting\u2011edge AI models work \u2014 including powerful Large Language Models (LLMs). You won\u2019t just study theory: you\u2019ll master practical skills in applying AI tools within real\u2011world digital systems.<\/p>\n\n

You\u2019ll learn to finely control the behaviour of intelligent models by mastering prompt engineering and context engineering techniques \u2014 from basic principles of query formulation to advanced strategies for managing model outputs and working with prompt chains. Special attention will be given to retrieval\u2011augmented generation (RAG) approaches and memory management techniques: you\u2019ll understand the role of system instructions and learn how to properly structure context to get the most accurate and useful results.<\/p>\n\n

The programme will cover the evolution of approaches in AI and introduce you to current trends and architectural solutions \u2014 particularly the inner workings of LLMs: transformer\u2011based architectures, pre\u2011training and fine\u2011tuning processes, and inference optimisation methods. You\u2019ll see how to apply LLMs in practice \u2014 for instance, to generate code, analyse system architectures, automate technical documentation, and support software testing.<\/p>\n\n

We\u2019ll also address important limitations and risks: we\u2019ll examine model hallucinations, factual inaccuracies, and bias issues, and study key safety protocols and data protection principles. By the end, you\u2019ll be able to competently assess the capabilities and weaknesses of AI technologies and make well\u2011founded decisions about how to apply them in engineering tasks.<\/p>\n\n

The learning experience is designed to reinforce theory with hands\u2011on practice. In lectures, we\u2019ll take an in\u2011depth look at architectural solutions; then, in workshops, you\u2019ll practise crafting effective prompts and designing interaction scenarios with models. In lab sessions, you\u2019ll work with up\u2011to\u2011date LLM platforms, and through mini\u2011projects you\u2019ll try integrating AI assistants into real engineering challenges. Analysing practical case studies will help you see how AI technologies are implemented in real life and solve pressing engineering problems.<\/p>\n\n

By the end of the course, you\u2019ll be fully prepared to confidently embed AI assistants into the development and operation of digital systems \u2014 and harness the full potential of modern AI technologies in your professional work.<\/p>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div>

\n\t

OBJECTIVES<\/h3><\/div><\/div><\/div>
\n
\n\t

Development of a systemic understanding of the operating principles of modern artificial intelligence models, including large linguistic models (LLM);<\/span><\/span><\/h3>\n

Development of skills in engineering application of AI tools in digital systems;<\/span><\/span><\/h3>\n

Mastering the methods of prompt engineering and context engineering as tools for managing the behavior of intelligent models;<\/span><\/span><\/h3>\n

Preparation for the integration of AI assistants into the development and operation of digital systems.<\/span><\/span><\/h3>\n<\/div>\n<\/div><\/div><\/div>
<\/div>
\n\t

KEY TASKS<\/h3><\/div><\/div><\/div>
\n
\n\t

Develop a comprehensive understanding of the operating principles of modern artificial intelligence models, including Large Language Models (LLMs);<\/span><\/span><\/h3>\n

Acquire practical engineering skills in applying AI tools within digital systems;<\/span><\/span><\/h3>\n

Gain proficiency in prompt engineering and context design for guiding AI model responses;<\/span><\/span><\/h3>\n

Prepare to integrate AI assistants into the development and operation of digital systems.<\/span><\/span><\/h3>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div>
\n
\n\t

Main topics of the course:<\/strong><\/span><\/h3>\n

Block 1. The Nature of the Tool<\/strong><\/span><\/h3>\n

1. What is a Large Language Model (LLM): evolution of AI from rule\u2011based systems to transformers.<\/p>\n

2. Principles of LLM operation: tokens, probabilities, sampling parameters (temperature, top\u2011p).<\/p>\n

3. Model hallucinations: causes and methods of reproduction.<\/p>\n

4. Transformer architecture: attention mechanism (without matrices), context window as an architectural constraint.<\/p>\n

5. Tokenization: impact on prompt engineering (numbers, code, non\u2011Latin alphabets).<\/p>\n

6. Solution space: pre\u2011training \u2192 inference \u2192 fine\u2011tuning \u2192 RAG (retrieval\u2011augmented generation).<\/p>\n

7. Overview of modern LLMs: GPT\u20114, Claude, Gemini, Llama, Mistral, GigaChat.<\/p>\n

8. Model optimization: distillation, quantization, weight pruning.<\/p>\n

9. Deployment options: cloud vs. on\u2011premises (economics, latency, privacy).<\/p>\n

10. Prompt as an engineering specification: structure (role, task, context, format, constraints).<\/p>\n

11. Output control strategies: zero\u2011shot, few\u2011shot, chain\u2011of\u2011thought.<\/p>\n

Block 2. Prompt Engineering as a Discipline<\/strong><\/span><\/h3>\n

1. Model output control strategies: with and without examples, step\u2011by\u2011step reasoning, self\u2011consistency.<\/p>\n

2. Structured output and function calling.<\/p>\n

3. System prompt as the model\u2019s \u201cconstitution\u201d: role delineation (system \u2014 user \u2014 assistant).<\/p>\n

4. Persona engineering and guardrails in prompts.<\/p>\n

5. Prompt injection attacks: demonstration and defense (instruction prioritization, input validation).<\/p>\n

6. LLM error typology: factual and reasoning hallucinations, overconfidence, sycophancy.<\/p>\n

7. Verification techniques: source querying, \u201cdevil\u2019s advocate\u201d technique.<\/p>\n

8. Comprehensive lab work: industrial case study analysis, prompt library peer review.<\/p>\n

Block 3. Context Engineering and API Integration<\/strong><\/span><\/h3>\n

1. Context as a managed resource: memory management strategies (sliding window, summarization).<\/p>\n

2. Lost\u2011in\u2011the\u2011middle effect and its impact on quality.<\/p>\n

3. Working with APIs: OpenAI, OpenRouter, GigaChat \u2014 request structure, streaming, rate limiting.<\/p>\n

4. Error handling and response caching: when and why.<\/p>\n

5. API cost optimization.<\/p>\n

6. FastAPI as a wrapper for LLM service: asynchronous processing, separation of prompt and application logic.<\/p>\n

7. Architectural patterns for AI applications.<\/p>\n

8. Chatbots and state management: stateless vs. stateful, session context persistence.<\/p>\n

9. Integration with Telegram and corporate platforms.<\/p>\n

Block 4. Semantic Search and Knowledge Base Augmentation <\/strong><\/span><\/h3>\n

1. Vector representations: meaning as a point in multidimensional space, cosine similarity.<\/p>\n

2. Semantic search vs. full\u2011text search: advantages for fuzzy queries.<\/p>\n

3. Vector databases: Qdrant, pgvector, Pinecone \u2014 comparison.<\/p>\n

4. RAG pipeline: chunking \u2192 vectorization \u2192 indexing \u2192 extraction \u2192 augmentation \u2192 generation.<\/p>\n

5. Chunking strategies: fixed size, semantic, hierarchical.<\/p>\n

6. Quality metrics: reliability, answer relevance, context precision and recall.<\/p>\n

7. Errors in knowledge\u2011augmented systems: poor extraction, context loss, source conflicts.<\/p>\n

8. First\u2011semester final lab: integration of all components, project pre\u2011defense.<\/p>\n

Block 5. Agents and External System Integration <\/strong><\/span><\/h3>\n

1. Agent concept: LLM + tools + cycle (Observe \u2192 Think \u2192 Act).<\/p>\n

2. Agent patterns: ReAct, plan\u2011and\u2011execute, reflexive agent.<\/p>\n

3. Agent reliability: protection against infinite loops, confidence thresholds, logging.<\/p>\n

4. Multi\u2011agent systems: orchestration (supervisor, pipeline, debate), responsibility separation.<\/p>\n

5. Agent integration with external systems: databases, web search, enterprise APIs.<\/p>\n

6. Agent activity audit: audit log implementation.<\/p>\n

Block 6. Quality, Validation, and Production Maturity <\/strong><\/span><\/h3>\n

1. AI system quality metrics: RAGAS, G\u2011Eval, LLM\u2011as\u2011judge.<\/p>\n

2. Manual evaluation: annotation guidelines, inter\u2011rater agreement.<\/p>\n

3. Evaluation datasets: creation and maintenance.<\/p>\n

4. Validation and testing: unit tests for prompts, integration tests, regression testing, A\/B testing.<\/p>\n

5. Risk management and security: risk classification (technical, operational, ethical), data leakage, content moderation.<\/p>\n

6. LLM in development processes: code review, test generation, documentation, architecture analysis.<\/p>\n

Block 7. Advanced Search Techniques and Multimodality<\/strong><\/span><\/h3>\n

1. Hybrid search: BM25 + semantic search, reranking models.<\/p>\n

2. HyDE (Hypothetical Document Embeddings): hypothetical answer generation and indexing.<\/p>\n

3. Corrective RAG and Self\u2011RAG: self\u2011correcting generation.<\/p>\n

4. Multimodal scenarios: multimodal LLMs (vision), audio models, prompt engineering specifics for image processing.<\/p>\n

Block 8. Further Training and Observability <\/strong><\/span><\/h3>\n

1. Fine\u2011tuning vs. alternatives: LoRA\/QLoRA, instruction tuning, RLHF (Reinforcement Learning from Human Feedback).<\/p>\n

2. AI system observability in production: logging, alerts, tracing (LangSmith, Langfuse).<\/p>\n

3. Quality drift: detecting system degradation.<\/p>\n

4. Feedback loops implementation.<\/p>\n

Block 9. Final Project <\/strong><\/span><\/h3>\n

1. Architectural audit and final design.<\/p>\n

2. Implementation of final modifications.<\/p>\n

3. Preparation for defense: presentation and system demonstration.<\/p>\n

4. Project defense: justification of architectural decisions, system operation demonstration.<\/p>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div>

\n
\n\t

Download the extended description >><\/a><\/p>\n<\/div>\n<\/div><\/div><\/div><\/div>

\n
\n\t

Return to the study plan overview<\/a><\/p>\n<\/div>\n<\/div><\/div><\/div><\/div>

\n
\n\t

 <\/p>\n

HES MEPhI<\/span><\/h3>\n

+7 (495) 788-56-99 \u0434\u043e\u0431. 7691, 9570<\/span>
\n+7 (929) 684-71-59<\/span>
\nhes@mephi.ru<\/a><\/span><\/strong><\/p>\n

Ask a question!<\/a><\/p>\n<\/div>\n<\/div><\/div><\/div>

\n
\n\t

 <\/p>\n

<\/i>\u00a0 VK \/ Vkontakte<\/span><\/a><\/h3>\n

\"\u0412\u0418\u0428\u00a0 Yandex.Dzen<\/span><\/a><\/h3>\n

\"\u0412\u0418\u0428 MAX<\/a><\/span><\/h3>\n

\"\u0412\u0418\u0428\u00a0 Telegram<\/span><\/a><\/h3>\n

<\/i>\u00a0 Youtube<\/span><\/a><\/h3>\n

\"\u0412\u0418\u0428\u00a0 Rutube<\/span><\/a><\/h3>\n

 <\/p>\n<\/div>\n<\/div><\/div><\/div>

\n
\n\t

 <\/p>\n

NRNU MEPhI\u00a0Admissions Committee:<\/h3>\n

admission.mephi.ru<\/a><\/span><\/strong><\/p>\n

115409, Moscow, Kashirskoe shosse, 31<\/span><\/p>\n<\/div>\n<\/div><\/div><\/div><\/div><\/div><\/div>","protected":false},"excerpt":{"rendered":"

DOWNLOAD THE FULL COURSE SYLLABUS BACK TO THE CURRICULUM BACK TO MASTER’S PROGRAM ABOUT HES MEPHI Artificial Intelligence and Large Linguistic Models: Prompt and Context Engineering This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"template-blank3.php","meta":[],"yoast_head":"\nAI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418<\/title>\n<meta name=\"description\" content=\"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/hes.mephi.ru\/?page_id=28769\" \/>\n<meta property=\"og:locale\" content=\"ru_RU\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418\" \/>\n<meta property=\"og:description\" content=\"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/hes.mephi.ru\/?page_id=28769\" \/>\n<meta property=\"og:site_name\" content=\"\u0412\u0418\u0428 \u041c\u0418\u0424\u0418\" \/>\n<meta property=\"og:image\" content=\"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u041f\u0440\u0438\u043c\u0435\u0440\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043b\u044f \u0447\u0442\u0435\u043d\u0438\u044f\" \/>\n\t<meta name=\"twitter:data1\" content=\"8 \u043c\u0438\u043d\u0443\u0442\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebSite\",\"@id\":\"https:\/\/hes.mephi.ru\/#website\",\"url\":\"https:\/\/hes.mephi.ru\/\",\"name\":\"\u0412\u0418\u0428 \u041c\u0418\u0424\u0418\",\"description\":\"\u0412\u044b\u0441\u0448\u0430\u044f \u0438\u043d\u0436\u0438\u043d\u0438\u0440\u0438\u043d\u0433\u043e\u0432\u0430\u044f \u0448\u043a\u043e\u043b\u0430 \u041d\u0418\u042f\u0423 \u041c\u0418\u0424\u0418\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/hes.mephi.ru\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"ru-RU\"},{\"@type\":\"ImageObject\",\"@id\":\"https:\/\/hes.mephi.ru\/?page_id=28769#primaryimage\",\"inLanguage\":\"ru-RU\",\"url\":\"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png\",\"contentUrl\":\"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/hes.mephi.ru\/?page_id=28769#webpage\",\"url\":\"https:\/\/hes.mephi.ru\/?page_id=28769\",\"name\":\"AI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418\",\"isPartOf\":{\"@id\":\"https:\/\/hes.mephi.ru\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/hes.mephi.ru\/?page_id=28769#primaryimage\"},\"datePublished\":\"2026-04-22T10:02:31+00:00\",\"dateModified\":\"2026-04-22T10:02:31+00:00\",\"description\":\"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.\",\"breadcrumb\":{\"@id\":\"https:\/\/hes.mephi.ru\/?page_id=28769#breadcrumb\"},\"inLanguage\":\"ru-RU\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/hes.mephi.ru\/?page_id=28769\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/hes.mephi.ru\/?page_id=28769#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u0413\u043b\u0430\u0432\u043d\u0430\u044f \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0430\",\"item\":\"https:\/\/hes.mephi.ru\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AI and LLM – PromptContext Engineering\"}]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418","description":"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/hes.mephi.ru\/?page_id=28769","og_locale":"ru_RU","og_type":"article","og_title":"AI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418","og_description":"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.","og_url":"https:\/\/hes.mephi.ru\/?page_id=28769","og_site_name":"\u0412\u0418\u0428 \u041c\u0418\u0424\u0418","og_image":[{"url":"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png"}],"twitter_card":"summary_large_image","twitter_misc":{"\u041f\u0440\u0438\u043c\u0435\u0440\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043b\u044f \u0447\u0442\u0435\u043d\u0438\u044f":"8 \u043c\u0438\u043d\u0443\u0442"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebSite","@id":"https:\/\/hes.mephi.ru\/#website","url":"https:\/\/hes.mephi.ru\/","name":"\u0412\u0418\u0428 \u041c\u0418\u0424\u0418","description":"\u0412\u044b\u0441\u0448\u0430\u044f \u0438\u043d\u0436\u0438\u043d\u0438\u0440\u0438\u043d\u0433\u043e\u0432\u0430\u044f \u0448\u043a\u043e\u043b\u0430 \u041d\u0418\u042f\u0423 \u041c\u0418\u0424\u0418","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/hes.mephi.ru\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"ru-RU"},{"@type":"ImageObject","@id":"https:\/\/hes.mephi.ru\/?page_id=28769#primaryimage","inLanguage":"ru-RU","url":"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png","contentUrl":"http:\/\/hes.mephi.ru\/wp-content\/uploads\/2026\/04\/Logo_Vish_eng-1.png"},{"@type":"WebPage","@id":"https:\/\/hes.mephi.ru\/?page_id=28769#webpage","url":"https:\/\/hes.mephi.ru\/?page_id=28769","name":"AI and LLM - PromptContext Engineering - \u0412\u0418\u0428 \u041c\u0418\u0424\u0418","isPartOf":{"@id":"https:\/\/hes.mephi.ru\/#website"},"primaryImageOfPage":{"@id":"https:\/\/hes.mephi.ru\/?page_id=28769#primaryimage"},"datePublished":"2026-04-22T10:02:31+00:00","dateModified":"2026-04-22T10:02:31+00:00","description":"This course lays the foundation for your further studies in AI engineering, machine learning, and digital systems. You will gain a methodological and technological basis for applying artificial intelligence in digital systems engineering and make the transition from theoretical understanding to real\u2011world engineering practice.","breadcrumb":{"@id":"https:\/\/hes.mephi.ru\/?page_id=28769#breadcrumb"},"inLanguage":"ru-RU","potentialAction":[{"@type":"ReadAction","target":["https:\/\/hes.mephi.ru\/?page_id=28769"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/hes.mephi.ru\/?page_id=28769#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u0413\u043b\u0430\u0432\u043d\u0430\u044f \u0441\u0442\u0440\u0430\u043d\u0438\u0446\u0430","item":"https:\/\/hes.mephi.ru\/"},{"@type":"ListItem","position":2,"name":"AI and LLM – PromptContext Engineering"}]}]}},"_links":{"self":[{"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/pages\/28769"}],"collection":[{"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=28769"}],"version-history":[{"count":22,"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/pages\/28769\/revisions"}],"predecessor-version":[{"id":29094,"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=\/wp\/v2\/pages\/28769\/revisions\/29094"}],"wp:attachment":[{"href":"https:\/\/hes.mephi.ru\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=28769"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}