Ragas with Llama-Index not working correctly due to misdefined scope

[georgije-conv]

[x] I have checked the documentation and related resources and couldn't resolve my bug.

Describe the bug
When trying to generate a test set using generate_with_llamaindex_docs, the code fails with a NameError indicating that 'LCDocument' is not defined. This appears to be an internal import issue in the Ragas library where the Langchain Document class is not properly imported in the scope where it's being used.

Ragas version: 0.2.6
Python version: 3.10.11

Code to Reproduce

from llama_index.core import SimpleDirectoryReader
from ragas.testset import TestsetGenerator
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding

# Load documents
documents = SimpleDirectoryReader("./nyc_wikipedia").load_data()

# Initialize generator components
generator_llm = OpenAI(model="gpt-4")
embeddings = OpenAIEmbedding(model="text-embedding-3-large")

# Create generator
generator = TestsetGenerator.from_llama_index(
    llm=generator_llm,
    embedding_model=embeddings,
)

# Generate testset
testset = generator.generate_with_llamaindex_docs(
    documents,
    testset_size=5,
)

Error trace

NameError                                 Traceback (most recent call last)
Cell In[4], line 2
      1 # generate testset
----> 2 testset = generator.generate_with_llamaindex_docs(
      3     documents,
      4     testset_size=5,
      5 )

File [...]/ragas/testset/synthesizers/generate.py:241, in TestsetGenerator.generate_with_llamaindex_docs(self, documents, testset_size, transforms, transforms_llm, transforms_embedding_model, query_distribution, run_config, callbacks, with_debugging_logs, raise_exceptions)
    240     transforms = default_transforms(
--> 241         documents=[LCDocument(page_content=doc.text) for doc in documents],
    242         llm=llm_for_transforms,
    243         embedding_model=embedding_model_for_transforms,
    244     )

NameError: name 'LCDocument' is not defined

Expected behavior
I expected it to generate a test set like described in the guide.