Metadata-Version: 2.4
Name: iomeval
Version: 0.1.6
Summary: Streamline evaluation evidence mapping at scale with LLMs
Home-page: https://github.com/franckalbinet/iomeval
Author: Solveit
Author-email: nobody@fast.ai
License: Apache Software License 2.0
Keywords: nbdev jupyter notebook python
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastcore
Requires-Dist: pandas
Requires-Dist: lisette
Requires-Dist: pydantic
Requires-Dist: tiktoken
Requires-Dist: mistocr
Requires-Dist: python-dotenv
Provides-Extra: dev
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: license-file
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# IOMEval


<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->

[![CI](https://github.com/franckalbinet/iomeval/actions/workflows/test.yaml/badge.svg)](https://github.com/franckalbinet/iomeval/actions/workflows/test.yaml)
[![PyPI](https://img.shields.io/pypi/v/iomeval.png)](https://pypi.org/project/iomeval/)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](LICENSE)

`iomeval` streamlines the mapping of [IOM](https://www.iom.int)
evaluation reports against strategic frameworks like the [Strategic
Results Framework (SRF)](https://srf.iom.int/) and [Global Compact for
Migration
(GCM)](https://www.un.org/en/development/desa/population/migration/generalassembly/docs/globalcompact/A_RES_73_195.pdf).
It uses LLMs to process PDF reports, extract key sections, and tag/map
them to framework components, turning dispersed, untagged evaluation
documents into structured, searchable knowledge maps.

## Why This Matters

UN agencies produce extensive evaluation reports and other public
documents. For IOM, this body of knowledge is extensive and variegated,
but putting it to practical use becomes more challenging as volume
increases, particularly when documentation is stored across different
repositories with no single index available.

**The Challenge for IOM**

IOM’s evaluation production is highly decentralized, with reports stored
across multiple repositories (the [IOM Evaluation
Repository](https://evaluation.iom.int/evaluation-search-pdf), IOM
Library, IOM Protection Platform). Quality varies greatly: quality
control processes are not applied uniformly, and variation also reflects
the inherent subjectivity in evaluation approaches and interpretations.
Reports also vary significantly in structure: some follow common formats
with executive summaries, findings, and recommendations, while others
have different structures entirely. This inconsistency makes systematic
mapping challenging.

Critically, existing metadata doesn’t indicate which elements of IOM’s
strategic frameworks (the [Strategic Results Framework
(SRF)](https://srf.iom.int/) or the [Global Compact for Migration
(GCM)](https://www.un.org/en/development/desa/population/migration/generalassembly/docs/globalcompact/A_RES_73_195.pdf))
each report addresses. This is a major gap that limits the ability to
connect evaluation evidence with key strategic frameworks.

**Evidence Maps as a Solution**

Evidence Maps display the extent and nature of research and evaluation
available on a subject. Following the [2025 UNEG Eval
Week](https://www.unevaluation.org/events/uneg-evaluation-week-2025),
four primary use cases emerged: guiding future evidence generation,
informing policy decisions, knowledge management, and enhancing
collaboration. The maps created by `iomeval` serve primarily as
**knowledge management tools**—structured repositories that make
identifying relevant sources easier by organizing them against strategic
framework components.

**What This Enables**

By tagging reports against SRF outputs, enablers, cross-cutting
priorities, and GCM objectives, these maps help answer questions like:
Which framework elements are well-covered by existing evaluations? Where
are the knowledge gaps that should prioritize future evaluation work?
Which themes have enough evidence for a dedicated synthesis report?

## Key Features

- **Automated PDF Processing**: Download and OCR evaluation reports with
  proper heading hierarchy
- **Intelligent Section Extraction**: LLM-powered extraction of
  executive summaries, findings, conclusions, and recommendations
- **Strategic Framework Mapping**: Map report content to IOM’s SRF
  Enablers, Cross-Cutting Priorities, GCM Objectives, and SRF Outputs
- **Checkpoint/Resume**: Built-in state persistence - interrupt and
  resume long-running pipelines
- **Granular Control**: Use the full pipeline or individual components
  as needed

## Installation

Install from PyPI:

``` sh
pip install iomeval
```

Or install the latest development version from GitHub:

``` sh
pip install git+https://github.com/franckalbinet/iomeval.git
```

## Configuration

### Core Dependencies

iomeval relies on two key libraries:

- **[mistocr](https://fr.anckalbi.net/mistocr)**: Powers the
  PDF-to-markdown conversion with intelligent OCR and heading hierarchy
  detection
- **[lisette](https://lisette.answer.ai)**: A thin wrapper around
  [litellm](https://www.litellm.ai/) that provides access to all major
  LLM providers. By default, iomeval uses Anthropic models (Haiku for
  debugging, Sonnet for production)

### API Keys

`iomeval` automatically loads API keys on import. You have two options:

**Option 1: Environment variables** (recommended for production)

``` sh
export ANTHROPIC_API_KEY='your-key-here'
export MISTRAL_API_KEY='your-key-here'
```

**Option 2: .env file** (convenient for development)

Create a `.env` file in your project root:

    ANTHROPIC_API_KEY=your-key-here
    MISTRAL_API_KEY=your-key-here

Since lisette supports all major LLM providers via litellm, you can
configure other providers (OpenAI, Google, etc.) by setting their
respective API keys using either method.

## Quick Start

First, prepare your evaluations data. Export evaluations from [IOM’s
evaluation repository](https://evaluation.iom.int/evaluation-search-pdf)
as CSV, then convert to JSON:

``` python
from iomeval.readers import IOMRepoReader

reader = IOMRepoReader('evaluation-search-export.csv')
reader.to_json('evaluations.json')
```

Now process an evaluation report end-to-end:

``` python
from iomeval.readers import load_evals
from iomeval.pipeline import run_pipeline

evals = load_evals('evaluations.json')
url = "https://evaluation.iom.int/sites/g/files/tmzbdl151/files/docs/resources/Abridged%20Evaluation%20Report_%20Final_Olta%20NDOJA.pdf"

report = await run_pipeline(url, evals, 
                            pdf_dst='data/pdfs', 
                            md_dst='data/md', 
                            results_path='data/results', 
                            ocr_kwargs=dict(add_img_desc=False), 
                            model='claude-haiku-4-5')
report
```

The pipeline runs 7 steps:

**download → OCR → extract → map SRF Enablers → map SRF Cross-cutting
Priorities → map GCM Objectives → map SRF Outputs**

Progress is displayed as each step completes, and state is automatically
saved after each stage for checkpoint/resume capability.

> [!NOTE]
>
> The prompts used for extraction and framework mapping are available in
> the [prompts
> directory](https://github.com/franckalbinet/iomeval/tree/master/nbs/files/prompts).

## Detailed Workflow

For more control over individual pipeline stages, see the module
documentation:

- **Loading evaluation metadata**: See
  [readers](https://fr.anckalbi.net/iomeval/readers.html) for working
  with IOM evaluation data
- **Downloading and OCR**: See
  [downloaders](https://fr.anckalbi.net/iomeval/downloaders.html) and
  [core](https://fr.anckalbi.net/iomeval/core.html) for PDF processing
- **Section extraction**: See
  [extract](https://fr.anckalbi.net/iomeval/extract.html) for extracting
  executive summaries, findings, conclusions, and recommendations
- **Framework mapping**: See
  [mapper](https://fr.anckalbi.net/iomeval/mapper.html) for mapping to
  SRF enablers, cross-cutting priorities, GCM objectives, and SRF
  outputs
- **Pipeline control**: See
  [pipeline](https://fr.anckalbi.net/iomeval/pipeline.html) for granular
  control over the full pipeline and checkpoint/resume functionality

## Development

iomeval is built with [nbdev](https://nbdev.fast.ai/), which means the
entire library is developed in Jupyter notebooks. The notebooks serve as
both documentation and source code.

### Setup for development

``` sh
git clone https://github.com/franckalbinet/iomeval.git
cd iomeval
pip install -e '.[dev]'
```

### Key nbdev commands

``` sh
nbdev_test          # Run tests in notebooks
nbdev_export        # Export notebooks to Python modules
nbdev_preview       # Preview documentation site
nbdev_prepare       # Export, test, and clean notebooks (run before committing)
```

### Workflow

1.  Make changes in the `.ipynb` notebook files
2.  Run `nbdev_prepare` to export code and run tests
3.  Commit both notebooks and exported Python files
4.  Documentation is automatically generated from the notebooks

Learn more about nbdev’s literate programming approach in the [nbdev
documentation](https://nbdev.fast.ai/).

### Contributing

Contributions are welcome! Please: - Follow the existing notebook
structure - Run `nbdev_prepare` before submitting PRs
