Add pip install datasets to RAG example

[sanjeed5]

datasets is used in the code later and would throw an error

in the below code:

import datasets
from langchain.docstore.document import Document
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.retrievers import BM25Retriever

knowledge_base = datasets.load_dataset("m-ric/huggingface_doc", split="train")
knowledge_base = knowledge_base.filter(lambda row: row["source"].startswith("huggingface/transformers"))

source_docs = [
    Document(page_content=doc["text"], metadata={"source": doc["source"].split("/")[1]})
    for doc in knowledge_base
]

text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=500,
    chunk_overlap=50,
    add_start_index=True,
    strip_whitespace=True,
    separators=["\n\n", "\n", ".", " ", ""],
)
docs_processed = text_splitter.split_documents(source_docs)

[albertvillanova]

Thanks!

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.