aidc-proposal-parser
v0.1.0
Published
Open-source TypeScript parser for AI data center developer proposals. Extracts structured data (capacity, schedule, cost, equipment, location, tier, PUE) from PDF / DOCX / pasted text.
Maintainers
Readme
aidc-proposal-parser
Open-source parser for AI data center developer proposals. Built by Livio Building Systems Inc. for the AI infrastructure community.
What this is
A TypeScript library that takes an AI data center developer proposal (PDF / DOCX / paste) and returns structured data: claimed capacity, schedule, cost, equipment, location, redundancy tier, PUE.
It is the parser that powers grid.golivio.com/review at the upstream parsing layer. Open-sourced because:
- Every offtaker, broker, and capital partner needs this same parsing capability.
- Proprietary lock-in on parsing slows down the whole industry.
- The hard work — first-principles engineering review — is still at grid.golivio.com/review. The parser is the easy part. Make it free, make it good, and let the community improve it.
Installation
npm install aidc-proposal-parserUsage
import { parseProposal } from 'aidc-proposal-parser'
const result = await parseProposal('./developer-proposal.pdf')
console.log(result)
// {
// capacity: { itLoadMW: 25, totalLoadMW: 31.25, source: 'page-3' },
// schedule: { rfsMonths: 9, source: 'page-12' },
// cost: { totalUsdM: 145, perKwIt: 5800, source: 'page-18' },
// equipment: [
// { category: 'UPS', vendor: 'Vertiv', model: 'Liebert APM', leadTimeWeeks: '12', source: 'page-22' },
// ...
// ],
// location: { city: 'Houston', state: 'TX', country: 'US', source: 'page-1' },
// tier: { claim: 'Tier 3', topology: 'N+1', source: 'page-5' },
// pue: { claim: 1.15, mode: 'directional', source: 'page-8' },
// completeness: 0.78,
// missingFields: ['epoLocations', 'fireSuppressionType', 'gensetEmissionsTier']
// }Why a dedicated parser?
AI DC proposals are a specific document genre. Different from generic engineering proposals:
- Equipment names follow vendor catalogs (Vertiv, Schneider, Cummins, GE, Cerebras, Nvidia)
- Capacity is always quoted in two figures — IT load and total load — that must reconcile via PUE
- Schedule is dominated by long-lead procurement, not construction
- Site geography determines half the design choices (climate, regulatory, water rights)
A general-purpose PDF parser will get 30% of the structured data right. A purpose-built parser gets 85%+.
What it does NOT do
This is a parser, not an evaluator. It extracts structured claims; it does not judge whether those claims are deliverable.
For a first-principles engineering review of the parsed claims (capacity feasibility, schedule realism, cost benchmarking, NEC/NFPA compliance), use grid.golivio.com/review — free, no signup.
Contributing
We welcome contributions. The most valuable contributions are new proposal patterns — anonymized real proposals you've seen that the parser handles poorly. Open an issue using the new_proposal_pattern template.
License
MIT. See LICENSE.
Maintainers
- Livio Building Systems Inc. (livio.com)
- Community: see CONTRIBUTORS.md
