Welcome to RAGatouille

Easily use and train state of the art retrieval methods in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

<p align="center"><img width=500 alt="The RAGatouille logo, it's a cheerful rat on his laptop (branded with a slightly eaten piece of cheese) and a pile of books he's looking for information in." src="RAGatouille.png"/></p>

---

The main motivation of RAGatouille is simple: bridging the gap between state-of-the-art research and alchemical RAG pipeline practices. RAG is complex, and there are many moving parts. To get the best performance, you need to optimise for many components: among them, a very important one is the models you use for retrieval.

Dense retrieval, i.e. using embeddings such as OpenAI's text-ada-002, is a good baseline, but there's a lot of research showing dense embeddings might not be the best fit for your usecase.

The Information Retrieval research field has recently been booming, and models like ColBERT have been shown to generalise better to new or complex domains than dense embeddings, are ridiculously data-efficient and are even better suited to efficiently being trained on non-English languages with low amount of data! Unfortunately, most of those new approaches aren't very well known, and are much harder to use than dense embeddings.

This is where RAGatouille comes in: RAGatouille's purpose is to bridge this gap: make it easy to use state-of-the-art methods in your RAG pipeline, without having to worry about the details or the years of literature! At the moment, RAGatouille focuses on making ColBERT simple to use. If you want to check out what's coming next, you can check out our broad roadmap!

If you want to read more about the motivations, philosophy, and why the late-interaction approach used by ColBERT works so well, check out the introduction in the docs.

Want to give it a try? Nothing easier, just run pip install ragatouille and you're good to go!

⚠️ Running notes/requirements: ⚠️

• If running inside a script, you must run it inside if __name__ == "__main__"
• Windows is not supported. RAGatouille doesn't appear to work outside WSL and has issues with WSL1. Some users have had success running RAGatouille in WSL2.

Get Started

RAGatouille makes it as simple as can be to use ColBERT! We want the library to work on two levels:

• Strong, but parameterizable defaults: you should be able to get started with just a few lines of code and still leverage the full power of ColBERT, and you should be able to tweak any relevant parameter if you need to!
• Powerful yet simple re-usable components under-the-hood: any part of the library should be usable stand-alone. You can use our DataProcessor or our negative miners outside of RAGPretrainedModel and RagTrainer, and you can even write your own negative miner and use it in the pipeline if you want to!

<!-- (more on [components](https://ben.clavie.eu/ragatouille/components)). -->

In this section, we'll quickly walk you through the three core aspects of RAGatouille:

• 🚀 Training and Fine-Tuning ColBERT models
• 🗄️ Embedding and Indexing Documents
• 🔎 Retrieving documents

➡️ If you want just want to see fully functional code examples, head over to the examples⬅️

🚀 Training and fine-tuning

If you're just prototyping, you don't need to train your own model! While finetuning can be useful, one of the strength of ColBERT is that the pretrained models are particularly good at generalisation, and ColBERTv2 has repeatedly been shown to be extremely strong at zero-shot retrieval in new domains!

Data Processing

RAGatouille's RAGTrainer has a built-in TrainingDataProcessor, which can take most forms of retrieval training data, and automatically convert it to training triplets, with data enhancements. The pipeline works as follows:

• Accepts pairs, labelled pairs and various forms of triplets as inputs (strings or list of strings) -- transparently!
• Automatically remove all duplicates and maps all positives/negatives to their respective query.
• By default, mine hard negatives: this means generating negatives that are hard to distinguish from positives, and that are therefore more useful for training.

This is all handled by RAGTrainer.prepare_training_data(), and is as easy as doing passing your data to it:

from ragatouille import RAGTrainer

my_data = [
    ("What is the meaning of life ?", "The meaning of life is 42"),
    ("What is Neural Search?", "Neural Search is a terms referring to a family of ..."),
    ...
]  # Unlabelled pairs here
trainer = RAGTrainer()
trainer.prepare_training_data(raw_data=my_data)

ColBERT prefers to store processed training data on-file, which also makes easier to properly version training data via wandb or dvc. By default, it will write to ./data/, but you can override this by passing a data_out_path argument to prepare_training_data().

Just like all things in RAGatouille, prepare_training_data uses strong defaults, but is also fully parameterizable.

<!-- Check out the [Data Processing](https://ben.clavie.eu/ragatouille/data-processing) section of the docs! -->

Running the Training/Fine-Tuning

Training and Fine-Tuning follow the exact same process. When you instantiate RAGTrainer, you must pass it a pretrained_model_name. If this pretrained model is a ColBERT instance, the trainer will be in fine-tuning mode, if it's another kind of transformer, it will be in training mode to begin training a new ColBERT initialised from the model's weights!

from ragatouille import RAGTrainer
from ragatouille.utils import get_wikipedia_page

pairs = [
    ("What is the meaning of life ?", "The meaning of life is 42"),
    ("What is Neural Search?", "Neural Search is a terms referring to a family of ..."),
    # You need many more pairs to train! Check the examples for more details!
    ...
]

my_full_corpus = [get_wikipedia_page("Hayao_Miyazaki"), get_wikipedia_page("Studio_Ghibli")]


trainer = RAGTrainer(model_name = "MyFineTunedColBERT",
        pretrained_model_name = "colbert-ir/colbertv2.0") # In this example, we run fine-tuning

# This step handles all the data processing, check the examples for more details!
trainer.prepare_training_data(raw_data=pairs,
                                data_out_path="./data/",
                                all_documents=my_full_corpus)

trainer.train(batch_size=32) # Train with the default hyperparams

When you run train(), it'll by default inherit its parent ColBERT hyperparameters if fine-tuning, or use the default training parameters if training a new ColBERT. Feel free to modify them as you see fit (check the example and API reference for more details!)

🗄️ Indexing

To create an index, you'll need to load a trained model, this can be one of your own or a pretrained one from the hub! Creating an index with the default configuration is just a few lines of code:

from ragatouille import RAGPretrainedModel
from ragatouille.utils import get_wikipedia_page

RAG = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")
my_documents = [get_wikipedia_page("Hayao_Miyazaki"), get_wikipedia_page("Studio_Ghibli")]
index_path = RAG.index(index_name="my_index", collection=my_documents)

You can also optionally add document IDs or document metadata when creating the index:

document_ids = ["miyazaki", "ghibli"]
document_metadatas = [
    {"entity": "person", "source": "wikipedia"},
    {"entity": "organisation", "source": "wikipedia"},
]
index_path = RAG.index(
    index_name="my_index_with_ids_and_metadata",
    collection=my_documents,
    document_ids=document_ids,
    document_metadatas=document_metadatas,
)

Once this is done running, your index will be saved on-disk and ready to be queried! RAGatouille and ColBERT handle everything here:

• Splitting your documents
• Tokenizing your documents
• Identifying the individual terms
• Embedding the documents and generating the bags-of-embeddings
• Compressing the vectors and storing them on disk

Curious about how this works? Check out the Late-Interaction & ColBERT concept explainer

<!-- or find out more about [indexing](https://ben.clavie.eu/ragatouille/indexing)! -->

🔎 Retrieving Documents

Once an index is created, querying it is just as simple as creating it! You can either load the model you need directly from an index's configuration:

from ragatouille import RAGPretrainedModel

query = "ColBERT my dear ColBERT, who is the fairest document of them all?"
RAG = RAGPretrainedModel.from_index("path_to_your_index")
results = RAG.search(query)

This is the preferred way of doing things, since every index saves the full configuration of the mod