LLM과 Event Sourcing으로 조직 지식 그래프 유지하기

# from config/ontology.yml
node_kinds:
  - kind: person
    description: "team member, candidate, client contact, external person"
  - kind: decision
    description: "formal decision requiring group verdict — for casual suggestions use idea"
edge_relations:
  - relation: works_on
    signature: "person --works_on--> project"

node = Node.find_or_initialize_by(name: data[:name])
enforce_status!(data[:name], data[:status], node) # raises when the model's new/existing claim disagrees with the DB
was_new = node.new_record?
node.assign_attributes(short_description: ..., description: ..., attrs: node.attrs.merge(attrs))
changes = node.changes.except("updated_at", "created_at", "kind", "slug")
{
  op: was_new ? "create" : "update",
  node_id: node.persisted? ? node.id : nil,
  changes: changes
}

def self.hybrid_search(query, limit: 10)
  # fuzzy match on canonical names and aliases, powered by pg_trgm
  by_name = where("similarity(nodes.name, ?) > 0.3", query)
  by_alias = joins(:aliases).where("similarity(node_aliases.name, ?) > 0.3", query)
  trigram_results = union_by_best_similarity(by_name, by_alias)

  response = RubyLLM.embed(query, model: "bge-m3", provider: :ollama)
  semantic_results = nearest_neighbors(:embedding, response.vectors, distance: "cosine")
    .select { |n| n.neighbor_distance < SEMANTIC_THRESHOLD }

  merge_and_rank(trigram_results, semantic_results, limit)
end

chat = RubyLLM
  .chat(model: MODEL)
  .with_params(tools: [
    { type: "web_search_20250305", name: "web_search", max_uses: 10 },
    { type: "web_fetch_20250910", name: "web_fetch", max_uses: 10 }
  ])
  .with_schema(ResearchBriefSchema.build)