{
  "name": "intelligent-ingest",
  "description": "Chunk, deduplicate, and selectively ingest documents",
  "version": "1.0.0",
  "branding": {
    "icon": "brain",
    "color": "#0D9488"
  },
  "inputs": {
    "text": { "type": "string", "required": true, "description": "Document text to process" },
    "source": { "type": "string", "required": true, "description": "Source identifier" },
    "similarity_threshold": { "type": "number", "default": 0.92, "description": "Similarity threshold for deduplication" }
  },
  "defaults": { "db": "myapp", "collection": "knowledge" },
  "steps": [
    {
      "id": "split",
      "tool": "chunk",
      "name": "Chunk the document",
      "inputs": {
        "text": "{{ inputs.text }}",
        "strategy": "recursive",
        "size": 512,
        "source": "{{ inputs.source }}"
      }
    },
    {
      "id": "filter_short",
      "tool": "filter",
      "name": "Remove short chunks",
      "inputs": {
        "array": "{{ split.output.chunks }}",
        "condition": "item.charCount > 100"
      }
    },
    {
      "id": "check_each",
      "tool": "loop",
      "name": "Check novelty of each chunk",
      "inputs": {
        "items": "{{ filter_short.output.results }}",
        "as": "chunk",
        "step": {
          "tool": "search",
          "inputs": {
            "query": "{{ chunk.content }}",
            "limit": 1
          }
        }
      }
    },
    {
      "id": "embed_novel",
      "tool": "template",
      "name": "Summarize results",
      "inputs": {
        "text": "Processed {{ split.output.totalChunks }} chunks, {{ filter_short.output.resultCount }} passed filter, {{ check_each.output.iterations }} checked for novelty"
      }
    }
  ],
  "output": {
    "totalChunks": "{{ split.output.totalChunks }}",
    "filteredChunks": "{{ filter_short.output.resultCount }}",
    "summary": "{{ embed_novel.output.text }}"
  }
}