Some modules not found in advanced RAG notebook when running in Colab

[sergiopaniego]

In the Advanced RAG on Hugging Face documentation using LangChain example, when running it on Colab, it generates some errors due to missing dependencies.

These dependencies are:

• datasets
• langchain-community
• ragatouille

All of them are used through the notebook but not installed previously.

The errors are thrown in:

• datasets:

from tqdm.notebook import tqdm
import pandas as pd
from typing import Optional, List, Tuple
from datasets import Dataset
import matplotlib.pyplot as plt

pd.set_option(
    "display.max_colwidth", None
)  # This will be helpful when visualizing retriever outputs

• langchain-community :

from langchain.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores.utils import DistanceStrategy

embedding_model = HuggingFaceEmbeddings(
    model_name=EMBEDDING_MODEL_NAME,
    multi_process=True,
    model_kwargs={"device": "cuda"},
    encode_kwargs={"normalize_embeddings": True},  # Set `True` for cosine similarity
)

KNOWLEDGE_VECTOR_DATABASE = FAISS.from_documents(
    docs_processed, embedding_model, distance_strategy=DistanceStrategy.COSINE
)

• ragatouille

from ragatouille import RAGPretrainedModel

RERANKER = RAGPretrainedModel.from_pretrained("colbert-ir/colbertv2.0")