expand_knowledge.py

# ======================================================================
# AXIS: Knowledge Expansion Tool (V1.2)
# This script converts raw text into AXIS-compatible Semantic Lattices.
# ======================================================================

import json
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

MODEL_ID = "kofdai/AXIS-Sovereign-Logic-Engine"

def extract_to_lattice(text):
    print(f"🧐 [AXIS] 知識抽出中: {text[:30]}...")
    
    tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
    model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.bfloat16, device_map="auto")

    prompt = f"以下のテキストをAXIS立体十字形式（JSON）に変換せよ。論理矛盾があればconflictsに記載せよ。\n入力: {text}\nFormat: {{'nodes':[], 'edges':[], 'conflicts':[]}}"
    
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(**inputs, max_new_tokens=512)
    
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return result

if __name__ == "__main__":
    # 拡張したい知識の例
    raw_knowledge = [
        "意味は計算の結果ではなく、計算が走るための初期構造である。",
        "AXISの物理パージは、知能の純粋性を保つための儀式である。"
    ]
    
    knowledge_base = []
    for k in raw_knowledge:
        lattice_piece = extract_to_lattice(k)
        knowledge_base.append(lattice_piece)
    
    # local_massive_data.json として保存
    with open("local_massive_data.json", "w", encoding="utf-8") as f:
        json.dump(knowledge_base, f, ensure_ascii=False, indent=4)
    
    print("✅ [SUCCESS] 知識拡張完了。local_massive_data.json を生成しました。")