Details: stuff as many text (concatenated/packed from the retrieved chunks) that can fit within the context window (considering the maximum prompt size between text_qa_template and refine_template). If the text is too long to fit in one prompt, it is split in as many parts as needed (using a TokenTextSplitter and thus allowing some overlap between text chunks).

query_engine = index.as_query_engine(
    vector_store_query_mode="hybrid", similarity_top_k=2
)
response = query_engine.query(
    "What did the author do growing up?",
)

----> 4 dataset_generator.generate_questions_from_nodes()

File ~/Desktop/gen-ai-bot-builder/fastapi/genai_env_4/lib/python3.9/site-packages/nest_asyncio.py:99, in _patch_loop.<locals>.run_until_complete(self, future)
     96 if not f.done():
     97     raise RuntimeError(
     98         'Event loop stopped before Future completed.')
---> 99 return f.result()

File /Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/asyncio/futures.py:201, in Future.result(self)
    199 self.__log_traceback = False
    200 if self._exception is not None:
--> 201     raise self._exception
    202 return self._result

File /Library/Developer/CommandLineTools/Library/Frameworks/Python3.framework/Versions/3.9/lib/python3.9/asyncio/tasks.py:256, in Task.__step(***failed resolving arguments***)
    252 try:
    253     if exc is None:
    254         # We use the `send` method directly, because coroutines
    255         # don't have `__iter__` and `__next__` methods.
--> 256         result = coro.send(None)
    257     else:
    258         result = coro.throw(exc)

File ~/Desktop/gen-ai-bot-builder/fastapi/genai_env_4/lib/python3.9/site-packages/llama_index/llama_dataset/generator.py:218, in RagDatasetGenerator.agenerate_questions_from_nodes(self)
    216 """Generates questions for each document."""
    217 dataset = await self._agenerate_dataset(self.nodes, labelled=False)
--> 218 return dataset.questions

AttributeError: 'LabelledRagDataset' object has no attribute 'questions'

RagDatasetGenerator.from_documents(documents)

from llama_index.embeddings import AzureOpenAIEmbedding

# You need to deploy your own embedding model as well as your own chat completion model
embed_model = AzureOpenAIEmbedding(
    model="text-embedding-ada-002",
    deployment_name="text-embedding-ada-002-2",
    api_key='...',
    azure_endpoint='...',
    api_version="2",
)
embed_model.get_text_embedding(
    "It is raining cats and dogs here!"
)

When I try to run it, the following error occurs.
NotFoundError: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}

from llama_index.core.indices.vector_store.base import VectorStoreIndex
from llama_index.legacy.vector_stores.qdrant import QdrantVectorStore
import qdrant_client
from llama_index.core import Settings
from llama_index.legacy.embeddings.ollama_embedding import OllamaEmbedding
from llama_index.legacy.embeddings import LangchainEmbedding
from langchain.embeddings import OllamaEmbeddings

# Initialize Ollama embedding model
embed_model = OllamaEmbedding(model_name="nomic-embed-text", base_url="http://localhost:11434")

# Set the global embedding model
Settings.embed_model = embed_model

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
Cell In[48], line 13
     10 embed_model = OllamaEmbedding(model_name="nomic-embed-text", base_url="http://localhost:11434")
     12 # Set the global embedding model
---> 13 Settings.embed_model = embed_model

File ~/Library/Caches/pypoetry/virtualenvs/ollama-env-Rz8XYqBf-py3.12/lib/python3.12/site-packages/llama_index/core/settings.py:74, in _Settings.embed_model(self, embed_model)
     71 @embed_model.setter
     72 def embed_model(self, embed_model: EmbedType) -> None:
     73     """Set the embedding model."""
---> 74     self._embed_model = resolve_embed_model(embed_model)

File ~/Library/Caches/pypoetry/virtualenvs/ollama-env-Rz8XYqBf-py3.12/lib/python3.12/site-packages/llama_index/core/embeddings/utils.py:136, in resolve_embed_model(embed_model, callback_manager)
    133     print("Embeddings have been explicitly disabled. Using MockEmbedding.")
    134     embed_model = MockEmbedding(embed_dim=1)
--> 136 assert isinstance(embed_model, BaseEmbedding)
    138 embed_model.callback_manager = callback_manager or Settings.callback_manager
    140 return embed_model

AssertionError: 

    # Weaviate
    weaviate_client = weaviate.Client("http://localhost:8080")  # Connect with default parameters

    # First, flush the existing vector store to ensure a clean state
    flush_weaviate_vector_store(weaviate_client)
    
    vector_store = WeaviateVectorStore(
        weaviate_client=weaviate_client, index_name="LlamaIndex"
    )

import weaviate
from llama_index.vector_stores import WeaviateVectorStore

weaviate_client = weaviate.Client("http://localhost:8080")  # Connect with default parameters
    
    vector_store = WeaviateVectorStore(
        weaviate_client=weaviate_client, index_name="LlamaIndex"
    )