Jev directory
CommunityJev Benchmarks & Evaluations
typesafeAI evalsafe invoice processing dataset
An Apache-2.0 Hugging Face dataset of English invoice documents in parquet format, tagged as a mirror under the typesafeAI evalsafe naming. It pairs tabular fields such as line items, unit prices, and amounts with raw invoice text.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Hosted on Hugging Face as HYUKI5/typesafeAI__evalsafe-invoice-processing with 0 likes.
- Modalities are tabular and text; files are distributed in parquet format.
- Language is English and the stated size is 1K to 10K records.
- Licensed Apache-2.0, with tags including laya, laya-finetune, mirror, domain-business, domain-finance, and use-conditional.
- Sample records carry structured line items with quantity, unit, unit_price, and amount alongside a raw_text field.
Questions about this entry
Short answers drawn from the linked project or page.
It is a Hugging Face dataset of English invoice documents. Records pair structured tabular fields, such as line items with quantity, unit, unit_price, and amount, with a raw_text field holding the invoice text.
The dataset card lists the license as apache-2.0.
The files are distributed in parquet format, and the card lists Datasets, pandas, and Polars among the supported libraries.
The card states a size of 1K to 10K records, with English as the language and tabular and text as the modalities.
It is published on Hugging Face under the account HYUKI5, with the dataset name typesafeAI__evalsafe-invoice-processing and tags that include mirror and laya-finetune.
The provided card does not describe any Jev questions, states, or answer labels. It is tagged as a mirror dataset for invoice processing under the typesafeAI evalsafe naming.
Sample content shows supplier and billing details, invoice and due dates, payment terms, line items with unit prices and amounts, VAT lines, totals in GBP, and remittance details.
More Jev resources like this
An open Claude Cowork-style workspace whose eval testkit can call Jev as a typed verification judge on agent-produced artifacts.
Jev Benchmarks & Evaluations#community#typescript#agents
Community
different-ai/openworkTypeScript
different-ai/openworkTypeScriptAgentic search evaluation inside Zilliz DeepSearcher: a standalone harness replaces the ChainOfRAG reflection call with one Jev Noul per round to decide whether to stop within a seven-round budget, then compares stopping behavior, evidence recall and decision cost on 100 sampled 2WikiMultiHopQA queries.
Jev Benchmarks & Evaluations#community#rag#evaluation
Community
zilliztech/deep-searcherPython
zilliztech/deep-searcherPythonLangWatch Instant Evals ships a TypeSafe Jev classifier that batches Noul, Score, and Choice judgments on production traces in one POST per text.
Jev Benchmarks & Evaluations#community#typescript#evaluation
Community
langwatch/langwatchTypeScript
langwatch/langwatchTypeScriptA worked example of using Jev as an LLM judge: ten synthetic frozen refund-support traces are scored by three yes/no criteria and one ordered helpfulness rubric in a single Jev request and recorded as a Comet Opik experiment.
Jev Benchmarks & Evaluations#community#catalog-import#madewithjev
Community
patchy631/jev-as-judgePython
patchy631/jev-as-judgePythonA fast, typed Python framework from TrustifAI for evaluating LLMs, RAG pipelines and agents with decision models: Jev by default, Microsoft Decision-1 on OpenRouter or OpenAI's Decisions API through the same backend. It returns typed scores, thresholds and status, with optional human-label calibration.
Jev Benchmarks & Evaluations#community#github#python
Community
trustifai/typed_evalsPython
trustifai/typed_evalsPythonA BEIR reranking recipe that asks up to 30 parallel Noul relevance questions in one Jev state, with RESULTS.md against cross-encoders and hosted rerankers.
Jev Benchmarks & Evaluations#community#evaluation#python
Community
hev/rerankerPython
hev/rerankerPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.