Text

Concept Extraction

Extract key concepts, definitions, and relationships from educational content across video, slides, and code

9K runs

Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

Input

Text Input string

Enter the text you want to process

# content_url string

Required

URL pointing to content file. Supported formats: MP4, PDF, ZIP (code), TXT. Default: undefined

# content_type string

Required

Type of content to process. Default: undefined

# domain string

Content domain for better extraction. Default: general

# extraction_mode string

Extraction mode to use. Default: pattern-based

# extract_relationships boolean

Extract concept prerequisite and related relationships. Default: true

# extract_definitions boolean

Extract concept definitions from context. Default: true

# extract_examples boolean

Extract code/text examples demonstrating concepts. Default: true

# assess_difficulty boolean

Classify concepts by difficulty level. Default: false

# cross_modal_linking boolean

Link concepts across video, slides, and code. Default: true

# generate_embeddings boolean

Generate semantic embeddings for concepts. Default: true

# min_confidence number

Minimum confidence threshold (0.0-1.0). Default: 0.7

Output

{
  "document_id": "doc_abc123",
  "collection_id": "col_xyz789",
  "source_object_id": "obj_def456",
  "concepts": [
    {
      "id": "concept_001",
      "name": "malloc",
      "category": "memory_management",
      "definition": "A C library function that allocates a specified number of bytes from the heap and returns a pointer to the allocated memory",
      "confidence": 0.94,
      "sources": [
        {
          "type": "transcript",
          "timestamp": 125.3,
          "text": "we use malloc to allocate memory dynamically...",
          "confidence": 0.91
        },
        {
          "type": "slide",
          "slide_number": 15,
          "title": "Dynamic Memory Allocation",
          "confidence": 0.88
        },
        {
          "type": "code",
          "file": "memory.c",
          "line": 45,
          "snippet": "int *ptr = malloc(sizeof(int) * 10);",
          "confidence": 0.96
        }
      ],
      "difficulty_level": "intermediate",
      "importance_score": 0.87,
      "frequency": 15,
      "examples": [
        "malloc(sizeof(int) * 10)",
        "ptr = malloc(100)"
      ],
      "prerequisites": [
        "pointers",
        "heap_memory"
      ],
      "related_concepts": [
        "free",
        "calloc",
        "realloc"
      ],
      "parent_concepts": [
        "memory_management"
      ],
      "child_concepts": [],
      "embedding": {
        "model": "bge-m3",
        "dimension": 1024,
        "vector": [
          0.023,
          -0.142
        ],
        "normalized": true
      }
    }
  ],
  "graph_stats": {
    "total_concepts": 47,
    "categories": {
      "memory_management": 8,
      "data_structure": 12,
      "algorithm": 5,
      "function": 15,
      "principle": 7
    },
    "difficulty_distribution": {
      "beginner": 15,
      "intermediate": 22,
      "advanced": 10
    },
    "average_confidence": 0.84,
    "total_relationships": 156
  },
  "content": {
    "type": "video",
    "filename": "cs50_lecture4_memory.mp4",
    "domain": "programming",
    "duration": 5430.5,
    "title": "CS50 2024 - Lecture 4 - Memory"
  }
}

Already have embeddings? Skip extraction — search your own vectors with MVS. First 1M vectors free.

Try MVS →