# API Reference

This section provides comprehensive class, method, and function documentation for all modules in REANIMATOR-VLM.

---

## Data Models (`reanimator.models`)

| Class | Description |
| :--- | :--- |
| [`Document`](models.md#document) | Top-level container representing a processed document. |
| [`Table`](models.md#table) | Extracted table with DataFrame content, caption, and position. |
| [`Figure`](models.md#figure) | Extracted figure with caption, image path, and position. |
| [`Formula`](models.md#formula) | Extracted math formula or equation. |
| [`Topic`](models.md#topic) | Retrieval query topic object. |
| [`Judgement`](models.md#judgement) | Synthetic 4-level relevance judgment object. |

---

## Document Pipeline (`reanimator.pipeline`)

| Class | Description |
| :--- | :--- |
| [`ReanimatorVLM`](pipeline.md#reanimatorvlm) | Main document processing pipeline entry point. |
| [`PDFLocalizer`](pipeline.md#pdflocalizer) | Bounding box normalization & figure image cropper. |

---

## Project Collection Workspace (`reanimator.collection`)

| Class / Method | Description |
| :--- | :--- |
| [`ProjectCollection`](collection.md#projectcollection) | Workspace directory manager. |
| [`ProjectCollection.process`](collection.md#projectcollectionprocess) | Stream and save parsed documents directly to disk. |
| [`ProjectCollection.iter_documents`](collection.md#projectcollectioniter_documents) | Yield document instances lazily from disk. |
| [`ProjectCollection.run_relevance_assessment`](collection.md#projectcollectionrun_relevance_assessment) | Evaluate synthetic relevance and export TREC qrels. |

---

## Synthetic Relevance Assessment (`reanimator.relevance`)

| Class / Function | Description |
| :--- | :--- |
| [`RelevanceEvaluator`](relevance.md#relevanceevaluator) | Core UMBRELA-style relevance judging engine. |
| [`ModalityExtractor`](relevance.md#modalityextractor) | Extract target modalities (`full_document`, `text_only`, `tables`, `figures`, `formulas`, `chunks`). |
| [`TopicAdapter`](relevance.md#topicadapter) | Normalize query strings, lists, or TREC topic dicts. |
| [`export_qrels`](relevance.md#export_qrels) | Export judgments in standard TREC qrels format. |

---

## VLM Backends (`reanimator.backends`)

| Class | Description |
| :--- | :--- |
| [`OpenAIVisionBackend`](backends.md#openaivisionbackend) | OpenAI API & remote `dots.mocr` vLLM backend. |
| [`GeminiBackend`](backends.md#geminibackend) | Google Gemini 2.0 Flash / Pro vision backend. |
| [`CachedBackend`](backends.md#cachedbackend) | Disk-backed response caching wrapper. |

---

## Visualization (`reanimator.visualization`)

| Function | Description |
| :--- | :--- |
| [`draw_bounding_boxes`](visualization.md#draw_bounding_boxes) | Render color-coded bounding boxes and centered label pills onto page images. |