mono-kit 0.1.4

ML toolkit for developers to build document, audio, and image similarity retrieval systems with pretrained and finetunable models—ready to use out of the box.

📚 Mono-Kit Library Documentation

mono-kit is a versatile machine learning library designed to help developers build advanced similarity retrieval systems such as Google Lens (image similarity retrieval), hum-to-search (audio similarity retrieval), and RAG-style retrieval systems. It supports document, audio, and image inputs, offering a suite of pretrained embedding models as well as finetunable custom built-in models. With mono-kit, you can perform similarity-based retrieval effortlessly—no need to implement complex pipelines. Everything you need comes ready to use, right out of the box.

Available Models

mono-kit comes with powerful, production-ready models tailored for each modality:

• Image

  • Default: ResNet-50
  • Custom: Finetunable customized ResNet-50 for domain-specific tasks

• Audio

  • Default: VGGish
  • Custom: Finetunable custom Siamese network with a custom loss function for enhanced similarity learning

• Document

  • Default: all-MiniLM-L6-v2 – a compact and efficient transformer model ideal for semantic document embeddings

---

📦 Installation

Install the library via pip:

pip install mono-kit

🔧 Initialization

mono-kit uses ChromaDB by default for embedding storage and retrieval.

Start by initializing a chromadb client:

import chromadb

client = chromadb.PersistentClient(path="path_to_save")

✅ You can use any chromadb client (e.g., EphemeralClient, HttpClient, etc.), not just PersistentClient.

⚠️ Collection Name Constraint: Each of mono_document, mono_audio, and mono_image must use unique collection names. You can reuse a collection name across default and custom models.

---

📝 Text Search: mono_document

1. Initialize Document Handler

mono_docs = mono_document(client, "unique_text_collection")

2. Text Splitting and Mounting

text = """Your long text block here..."""
docs = mono_docs.text_splitter(text, (150, 200), 20, False)

for id, doc in enumerate(docs):
    mono_docs.mount_document(doc, str(id))

• (150, 200): Min/max character chunk size
• 20: Overlap in characters
• False: If True, will retain sentence boundaries (optional feature)

3. Semantic Search

result = mono_docs.find_similar_documents("search query here", k=3)
print(result)

---

🔊 Audio Search: mono_audio

1. Initialize Audio Handler

mono_aud = mono_audio(client, "unique_audio_collection")

2. Mount Audio Files

mono_aud.mount_audio("path/to/audio1.mp3")
mono_aud.mount_audio("path/to/audio2.mp3")

3. Batch Mounting

mono_aud.mount_audio_batch("path/to/audio_directory")

4. Find Similar Audio

result = mono_aud.find_similar_audio("path/to/query.mp3", k=3)
print(result)

---

✅ With Custom Audio Model

1. Train Custom Audio Model

x = "path/to/reference_audio"
y = "path/to/target_audio"
mono_aud.create_audio_model(directory_x=x, directory_y=y)

2. Mount and Search with Custom Model

model_path = "custom_trained_audio_embedding_model/audio_model.keras"

mono_aud.mount_audio("audio.mp3", model_path=model_path)
mono_aud.mount_audio_batch("audio_directory", model_path=model_path)

result = mono_aud.find_similar_audio("query.mp3", k=2, model_path=model_path)
print(result)

---

🖼️ Image Search: mobo_image

1. Initialize Image Handler

mono_img = mono_image(client, "unique_image_collection")

2. Mount Images

mono_img.mount_image("path/to/image.jpg")

3. Batch Mounting

mono_img.mount_image_batch("path/to/image_directory")

4. Find Similar Images

result = mono_img.find_similar_image("path/to/query_image.jpg", k=3)
print(result)

---

✅ With Custom Image Model

1. Train Custom Image Model

x = "path/to/reference_images"
y = "path/to/target_images"
mono_img.create_image_model(directory_x=x, directory_y=y)

2. Mount and Search with Custom Model

model = "/path/to/custom_trained_image_embedding_model/image_model.keras"

mono_img.mount_image_batch("image_directory", model_path=model)

result = mono_img.find_similar_image("query.jpg", k=3, model_path=model)
print(result)

---

✅ Summary of Key Functions

Operation	Document	Audio	Image
Mount file	mount_document	mount_audio	mount_image
Mount batch	—	mount_audio_batch	mount_image_batch
Similarity search	find_similar_documents	find_similar_audio	find_similar_image
Train custom model	—	create_audio_model	create_image_model
Use custom model	—	via model_path	via model_path

---