The contractor shall provide all materials per ASTM C150-20. Maximum load
shall not exceed 500 psf per ASCE 7-22. Notice to proceed within 14 calendar
days of contract execution. Retainage of 10% applies to all payments.
For general background, the project is located in Denver, CO...

[
  {
    "text": "The contractor shall provide all materials per ASTM C150-20.",
    "authority": "mandatory",
    "risk": "compliance",
    "type": "requirement",
    "irreducible": true,
    "attention": 8.0,
    "entities": ["ASTM C150-20"]
  },
  {
    "text": "Maximum load shall not exceed 500 psf per ASCE 7-22.",
    "authority": "prohibitive",
    "risk": "safety_critical",
    "type": "constraint",
    "irreducible": true,
    "attention": 10.0,
    "entities": ["ASCE 7-22"]
  }
]

pip install decompose-mcp

{
  "mcpServers": {
    "decompose": {
      "command": "uvx",
      "args": ["decompose-mcp", "--serve"]
    }
  }
}

{
  "mcpServers": {
    "decompose": {
      "command": "python3",
      "args": ["-m", "decompose", "--serve"]
    }
  }
}

# Pipe text
cat spec.txt | decompose --pretty

# Inline
decompose --text "The contractor shall provide all materials per ASTM C150-20."

# Compact output (smaller JSON)
cat document.md | decompose --compact

from decompose import decompose_text, filter_for_llm

result = decompose_text("The contractor shall provide all materials per ASTM C150-20.")

for unit in result["units"]:
    print(f"[{unit['authority']}] [{unit['risk']}] {unit['text'][:60]}...")

# Pre-filter for LLM context — keep only high-value units
filtered = filter_for_llm(result, max_tokens=4000)
print(f"{filtered['meta']['reduction_pct']}% token reduction")
llm_input = filtered["text"]  # Ready for your LLM

Without:  document → chunk → embed → retrieve → LLM → answer  (100% of tokens)
With:     document → decompose → filter/route → LLM → answer  (20-40% of tokens)

from decompose import decompose_text, filter_for_llm

result = decompose_text(open("contract.md").read())
filtered = filter_for_llm(result, max_tokens=4000)

# filtered["text"] = high-value units only, ready for LLM
# filtered["meta"]["reduction_pct"] = how much was dropped (typically 60-80%)

# Or use the units directly for embedding
for unit in filtered["units"]:
    embed_and_store(unit["text"], metadata={
        "authority": unit["authority"],
        "risk": unit["risk"],
        "attention": unit["attention"],
    })

from decompose import decompose_text

result = decompose_text(spec_text)

for unit in result["units"]:
    if unit["risk"] == "safety_critical":
        safety_chain.process(unit)       # Full analysis + human review
    elif unit["risk"] == "financial":
        audit_chain.process(unit)         # Flag for finance team
    elif unit["attention"] < 0.5:
        pass                              # Skip boilerplate
    else:
        general_chain.process(unit)       # Standard LLM analysis

from decompose import decompose_text

result = decompose_text(spec_text)
total = len(result["units"])
high = [u for u in result["units"] if u["attention"] >= 1.0]

print(f"{len(high)}/{total} units need LLM analysis")
print(f"{100 - len(high) * 100 // total}% token reduction")