{
  "identifier": "tag:aim-pro.eu,2026:oer/66ebea80ee12/record",
  "profile": "aimpro-oer-profile/1",
  "normaliser": "oerlib.metadata/2",
  "status": "ready",
  "normalised_at": "2026-10-09T10:08:35+00:00",
  "resource": {
    "id": "66ebea80ee12",
    "identifier": "tag:aim-pro.eu,2026:oer/66ebea80ee12",
    "uri": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/README.md",
    "title": "Retrieval Augmented Generation (RAG) and Vector Databases",
    "description": "",
    "creators": [
      "Microsoft (microsoft)"
    ],
    "keywords": [
      "ai",
      "azure",
      "chatgpt",
      "dall-e",
      "generative-ai",
      "generativeai",
      "gpt",
      "language-model",
      "llms",
      "microsoft-for-beginners",
      "openai",
      "prompt-engineering",
      "semantic-search",
      "transformers"
    ],
    "kind": "markdown",
    "content_language": "en",
    "declared_language": "en",
    "word_count": 2027,
    "content_hash": "67ff4c0cec62d594",
    "metadata_only": false
  },
  "licence": {
    "raw": "MIT",
    "spdx": "MIT",
    "uri": "https://spdx.org/licenses/MIT.html",
    "verdict": "OPEN",
    "note": "recognised open SPDX id",
    "ingestable": true,
    "commercial_ok": true,
    "derivable": true,
    "share_alike": false,
    "evidence": {
      "scope": "repository-level LICENSE detection; embedded or third-party material may carry separate terms",
      "method": "GitHub repository-search metadata (Licensee detection)",
      "schema": 1,
      "status": "captured",
      "location": "items[full_name=microsoft/generative-ai-for-beginners].license.spdx_id",
      "source_url": "https://api.github.com/search/repositories?q=AI+%22AI+concepts%22+in%3Aname%2Cdescription%2Creadme+fork%3Afalse+archived%3Afalse&per_page=100&page=1",
      "asserted_by": "Repository rights holder/maintainer; detected by GitHub Licensee",
      "captured_at": "2026-10-09T09:55:20+00:00",
      "source_system": "github",
      "observed_value": "MIT",
      "documentation_url": "https://docs.github.com/en/rest/licenses/licenses",
      "responsibility_url": "https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/licensing-a-repository",
      "documentation_label": "GitHub REST licence detection documentation",
      "responsibility_note": "GitHub matches the repository LICENSE file against known licences; it does not cover dependencies or licence mentions elsewhere."
    }
  },
  "descriptive": {
    "contributions": [
      {
        "name": "Microsoft (microsoft)",
        "role": "content provider",
        "affiliation": "",
        "identifier": "https://github.com/microsoft",
        "scope": "container"
      }
    ],
    "identifiers": [
      {
        "scheme": "repository-path",
        "value": "translations/en/15-rag-and-vector-databases/README.md",
        "scope": "resource"
      },
      {
        "scheme": "git-blob",
        "value": "711148c998fc5e3e9d2836ba9926ab0ef9dbca81",
        "scope": "resource"
      },
      {
        "scheme": "github-repository",
        "value": "microsoft/generative-ai-for-beginners",
        "scope": "container"
      }
    ],
    "dates": [
      {
        "meaning": "created",
        "value": "2023-06-19",
        "scope": "container"
      },
      {
        "meaning": "modified",
        "value": "2026-10-08",
        "scope": "container"
      },
      {
        "meaning": "modified",
        "value": "2026-07-16",
        "scope": "resource"
      }
    ],
    "subjects": [
      {
        "value": "ai",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "azure",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "chatgpt",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "dall-e",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "generative-ai",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "generativeai",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "gpt",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "language-model",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "llms",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "microsoft-for-beginners",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "openai",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "prompt-engineering",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "semantic-search",
        "scheme": "",
        "scope": "container"
      },
      {
        "value": "transformers",
        "scheme": "",
        "scope": "container"
      }
    ],
    "relations": [
      {
        "kind": "ispartof",
        "target": "https://github.com/microsoft/generative-ai-for-beginners",
        "label": "microsoft/generative-ai-for-beginners"
      }
    ],
    "educational": {
      "learning_resource_type": "",
      "intended_end_user_role": "",
      "context": "",
      "difficulty": "",
      "typical_learning_time": "",
      "description": ""
    },
    "container": {
      "kind": "repository",
      "uri": "https://github.com/microsoft/generative-ai-for-beginners",
      "title": "microsoft/generative-ai-for-beginners",
      "description": "21 Lessons, Get Started Building with Generative AI ",
      "identifier": "microsoft/generative-ai-for-beginners"
    },
    "declared_language": "en",
    "declared_type": "",
    "rights_holder": "",
    "access_rights": "",
    "publisher": "",
    "version": "",
    "citation": "",
    "notes": "",
    "lifecycle_status": "",
    "structure_role": "lesson",
    "snapshot": {
      "file": {},
      "resource": {
        "sha": "711148c998fc5e3e9d2836ba9926ab0ef9dbca81",
        "path": "translations/en/15-rag-and-vector-databases/README.md",
        "size": 15093,
        "branch": "main",
        "html_url": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/README.md"
      },
      "container": {
        "owner": {
          "id": 6154722,
          "url": "https://api.github.com/users/microsoft",
          "type": "Organization",
          "login": "microsoft",
          "node_id": "MDEyOk9yZ2FuaXphdGlvbjYxNTQ3MjI=",
          "html_url": "https://github.com/microsoft",
          "gists_url": "https://api.github.com/users/microsoft/gists{/gist_id}",
          "repos_url": "https://api.github.com/users/microsoft/repos",
          "avatar_url": "https://avatars.githubusercontent.com/u/6154722?v=4",
          "events_url": "https://api.github.com/users/microsoft/events{/privacy}",
          "site_admin": false,
          "gravatar_id": "",
          "starred_url": "https://api.github.com/users/microsoft/starred{/owner}{/repo}",
          "followers_url": "https://api.github.com/users/microsoft/followers",
          "following_url": "https://api.github.com/users/microsoft/following{/other_user}",
          "user_view_type": "public",
          "organizations_url": "https://api.github.com/users/microsoft/orgs",
          "subscriptions_url": "https://api.github.com/users/microsoft/subscriptions",
          "received_events_url": "https://api.github.com/users/microsoft/received_events"
        },
        "topics": [
          "ai",
          "azure",
          "chatgpt",
          "dall-e",
          "generative-ai",
          "generativeai",
          "gpt",
          "language-model",
          "llms",
          "microsoft-for-beginners",
          "openai",
          "prompt-engineering",
          "semantic-search",
          "transformers"
        ],
        "html_url": "https://github.com/microsoft/generative-ai-for-beginners",
        "language": "Jupyter Notebook",
        "full_name": "microsoft/generative-ai-for-beginners",
        "pushed_at": "2026-10-08T03:45:38Z",
        "created_at": "2023-06-19T16:28:59Z",
        "updated_at": "2026-10-09T09:52:26Z",
        "description": "21 Lessons, Get Started Building with Generative AI ",
        "default_branch": "main"
      }
    }
  },
  "representations": [
    {
      "role": "extracted",
      "media_type": "text/markdown",
      "size_bytes": 15321,
      "filename": "",
      "location": "",
      "source_format": "markdown",
      "converter": "passthrough"
    }
  ],
  "observed": {
    "language": {
      "method": "declared",
      "reason": "declared English",
      "accepted": true,
      "declared": "en",
      "detected": "en",
      "confidence": null,
      "review_required": false
    },
    "description_scope": "container"
  },
  "collection": {
    "source": "github",
    "source_label": "GitHub",
    "collected_at": "2026-10-09T09:57:02.931028+00:00",
    "query": "AI \"AI concepts\" in:name,description,readme fork:false archived:false",
    "note": "where this was collected from. Not a claim that the provider published or authored it"
  },
  "provenance": [
    {
      "field": "resource_id",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/resource_id"
    },
    {
      "field": "query",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/query"
    },
    {
      "field": "collected_from",
      "scope": "resource",
      "method": "engine",
      "evidence_ref": "engine#/source"
    },
    {
      "field": "title",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "description",
      "scope": "container",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/container/description"
    },
    {
      "field": "subjects",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "contributions",
      "scope": "container",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/container"
    },
    {
      "field": "dates",
      "scope": "container",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/container"
    },
    {
      "field": "dates",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/path"
    },
    {
      "field": "identifiers",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/sha"
    },
    {
      "field": "identifiers",
      "scope": "container",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/container/full_name"
    },
    {
      "field": "relations",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource/html_url"
    },
    {
      "field": "container",
      "scope": "container",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/container/full_name"
    },
    {
      "field": "content_language",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/language/declared"
    },
    {
      "field": "declared_language",
      "scope": "resource",
      "method": "source_metadata",
      "evidence_ref": "snapshot#/resource"
    },
    {
      "field": "licence",
      "scope": "resource",
      "method": "gate_observation",
      "evidence_ref": "gate#/licence/evidence"
    },
    {
      "field": "representations",
      "scope": "resource",
      "method": "conversion",
      "evidence_ref": "conversion#/markdown"
    },
    {
      "field": "structure_role",
      "scope": "resource",
      "method": "repository_path_convention",
      "evidence_ref": "container#/path_role/lesson"
    }
  ],
  "incidents": [
    {
      "code": "absent",
      "field": "description",
      "detail": "the only description available is the repository's own, which describes microsoft/generative-ai-for-beginners and not this resource. It is kept against the container and the resource's description is left empty"
    },
    {
      "code": "absent",
      "field": "creators",
      "detail": "nobody is named as an author of this resource — the contributions recorded are about the container or carry a non-authorial role"
    },
    {
      "code": "absent",
      "field": "dates",
      "detail": "no publication date was declared; a collection date is not one and is kept separately"
    },
    {
      "code": "absent",
      "field": "rights_holder",
      "detail": "no rights holder is named at source; the licence is recorded without one rather than attributed to the platform that served it"
    },
    {
      "code": "absent",
      "field": "publisher",
      "detail": "the source named no publisher of the work; where it was collected from is recorded as collection provenance instead, which is a different claim"
    },
    {
      "code": "absent",
      "field": "educational",
      "detail": "the source declared no educational metadata — no resource type, audience, context, difficulty or learning time. Nothing here estimates them"
    },
    {
      "code": "unmapped",
      "field": "structure_role",
      "detail": "this file sits in the container as 'lesson' by directory convention. That is a fact about the repository's layout, not a declaration that the resource is of that educational type, so no educational element is filled from it"
    }
  ],
  "inferred": [
    {
      "rule": "description.statement",
      "field": "description",
      "value": "In this lesson, we will delve further into the concepts of grounding your data in your LLM application, the mechanics of the process and the methods for storing data, including both embeddings and text.",
      "method": "inferred",
      "evidence": {
        "lines": [
          9,
          9
        ],
        "under": "Retrieval Augmented Generation (RAG) and Vector Databases"
      },
      "rule_version": "description/13"
    },
    {
      "rule": "learning_resource_type.prose",
      "field": "learning_resource_type",
      "value": "narrative text",
      "method": "inferred",
      "evidence": {
        "lines": [],
        "counts": {
          "pages": 0,
          "steps": 1,
          "questions": 0,
          "link_items": 0,
          "list_items": 31,
          "paragraphs": 31,
          "quiz_words": 0,
          "step_lines": [],
          "table_rows": 0,
          "text_words": 1787,
          "code_blocks": 5,
          "prose_words": 1210,
          "quiz_headings": [],
          "task_headings": [
            "Assignment"
          ],
          "numbered_steps": 0,
          "words_per_page": null,
          "action_headings": [
            "Search index",
            "Use Cases for using RAG (Retrieval Augmented Generation) and vector databases"
          ],
          "table_link_rows": 0
        }
      },
      "rule_version": "learning_resource_type/9"
    },
    {
      "rule": "objectives.statement",
      "field": "educational_description",
      "value": "In this lesson we will cover the following: An introduction to RAG, what it is and why it is used in AI (artificial intelligence); Understanding what vector databases are and creating one for our application; A practical example on how to integrate RAG into an application.",
      "method": "inferred",
      "evidence": {
        "of": 3,
        "items": 3,
        "lines": [
          15,
          21
        ]
      },
      "rule_version": "objectives/9"
    },
    {
      "rule": "purpose.repository",
      "field": "purpose",
      "value": "teaching",
      "method": "inferred",
      "evidence": {
        "words": [
          "lessons",
          "get started"
        ],
        "declared": "21 Lessons, Get Started Building with Generative AI"
      },
      "rule_version": "purpose/1"
    },
    {
      "field": "requires",
      "value": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/data/frameworks.md",
      "label": "Neural Network Frameworks",
      "resource_id": "d48230a15cc0",
      "method": "inferred",
      "rule": "components",
      "rule_version": "components/3",
      "evidence": {
        "links": [
          {
            "basis": "layout",
            "folder": "translations/en/15-rag-and-vector-databases",
            "convention": "same folder"
          }
        ]
      }
    },
    {
      "field": "requires",
      "value": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/data/own_framework.md",
      "label": "Introduction to Neural Networks. Multi-Layered Perceptron",
      "resource_id": "5be6670216a0",
      "method": "inferred",
      "rule": "components",
      "rule_version": "components/3",
      "evidence": {
        "links": [
          {
            "basis": "layout",
            "folder": "translations/en/15-rag-and-vector-databases",
            "convention": "same folder"
          }
        ]
      }
    },
    {
      "field": "requires",
      "value": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/data/perceptron.md",
      "label": "Introduction to Neural Networks: Perceptron",
      "resource_id": "3b874c020834",
      "method": "inferred",
      "rule": "components",
      "rule_version": "components/3",
      "evidence": {
        "links": [
          {
            "basis": "layout",
            "folder": "translations/en/15-rag-and-vector-databases",
            "convention": "same folder"
          }
        ]
      }
    },
    {
      "field": "referenced_by",
      "value": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/14-the-generative-ai-application-lifecycle/README.md",
      "label": "The Generative AI Application Lifecycle",
      "resource_id": "e2a82f48ce0e",
      "method": "inferred",
      "rule": "link",
      "rule_version": "links/1",
      "evidence": {
        "links": [
          {
            "how": "link",
            "line": 91,
            "basis": "reference",
            "literal": "https://github.com/microsoft/generative-ai-for-beginners/blob/main/translations/en/15-rag-and-vector-databases/README.md"
          }
        ],
        "kind": "link"
      }
    }
  ]
}