xretrieval 0.1.1

Retrieve and Evaluate with X(any) models

Explore the docs »
Quickstart · Feature Request · Report Bug · Discussions · About

Evaluate your multimodal retrieval system with any models and datasets.

Specific inputs:

• A dataset
• A model
• A mode (e.g. image-to-image)

Get evaluation metrics:

• A retrieval results dataframe
• A retrieval metrics dataframe

🌟 Key Features

• ✅ Supports a wide range of models and datasets.
• ✅ Installation in one line.
• ✅ Run benchmarks with one function call.

🚀 Quickstart

import xretrieval

metrics, results_df = xretrieval.run_benchmark(
    dataset="coco-val-2017",
    model_id="transformers/Salesforce/blip2-itm-vit-g",
    mode="text-to-text",
)

    Retrieval Metrics     
┏━━━━━━━━━━━━━━━┳━━━━━━━━┓
┃ Metric        ┃ Score  ┃
┡━━━━━━━━━━━━━━━╇━━━━━━━━┩
│ MRR           │ 0.3032 │
│ NormalizedDCG │ 0.3497 │
│ Precision     │ 0.2274 │
│ Recall        │ 0.4898 │
│ HitRate       │ 0.4898 │
│ MAP           │ 0.2753 │
└───────────────┴────────┘

📦 Installation

pip install xretrieval

🛠️ Usage

List datasets:

xretrieval.list_datasets()

                    Available Datasets                     
┏━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Dataset Name  ┃ Description                             ┃
┡━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ coco-val-2017 │ The COCO Validation Set with 5k images. │
└───────────────┴─────────────────────────────────────────┘

List models:

xretrieval.list_models()

                         Available Models                         
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Model ID                                         ┃ Model Input ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│ transformers/Salesforce/blip2-itm-vit-g          │ text-image  │
│ transformers/Salesforce/blip2-itm-vit-g-text     │ text        │
│ transformers/Salesforce/blip2-itm-vit-g-image    │ image       │
│ sentence-transformers/paraphrase-MiniLM-L3-v2    │ text        │
│ sentence-transformers/paraphrase-albert-small-v2 │ text        │
│ sentence-transformers/multi-qa-distilbert-cos-v1 │ text        │
│ sentence-transformers/all-MiniLM-L12-v2          │ text        │
│ sentence-transformers/all-distilroberta-v1       │ text        │
│ sentence-transformers/multi-qa-mpnet-base-dot-v1 │ text        │
│ sentence-transformers/all-mpnet-base-v2          │ text        │
│ sentence-transformers/multi-qa-MiniLM-L6-cos-v1  │ text        │
│ sentence-transformers/all-MiniLM-L6-v2           │ text        │
│ timm/resnet18.a1_in1k                            │ image       │
└──────────────────────────────────────────────────┴─────────────┘