TypeError: Cannot use scipy.linalg.eigh for sparse A with k >= N. Use scipy.linalg.eigh(A.toarray()) or reduce k. -> _bertopic.py", line 3742, in _reduce_dimensionality

Nobody has claimed this yet.

### Have you searched existing issues? 🔎

- [X] I have searched and found no existing issues

### Desribe the bug

## Description
When generating topics for the attached file the following trace back was produced:

```
/home/mediumroast/.local/lib/python3.11/site-packages/umap/spectral.py:521: RuntimeWarning: k >= N for N * N square matrix. Attempting to use scipy.linalg.eigh instead.
eigenvalues, eigenvectors = scipy.sparse.linalg.eigsh(
Traceback (most recent call last):
File "/home/mediumroast/.local/lib/python3.11/site-packages/bertopic/_bertopic.py", line 3742, in _reduce_dimensionality
self.umap_model.fit(embeddings, y=y)
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 2784, in fit
self.embedding_, aux_data = self._fit_embed_data(
^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 2830, in _fit_embed_data
return simplicial_set_embedding(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 1107, in simplicial_set_embedding
embedding = spectral_layout(
^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/spectral.py", line 304, in spectral_layout
return _spectral_layout(
^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/spectral.py", line 521, in _spectral_layout
eigenvalues, eigenvectors = scipy.sparse.linalg.eigsh(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/scipy/sparse/linalg/_eigen/arpack/arpack.py", line 1608, in eigsh
raise TypeError("Cannot use scipy.linalg.eigh for sparse A with "
TypeError: Cannot use scipy.linalg.eigh for sparse A with k >= N. Use scipy.linalg.eigh(A.toarray()) or reduce k.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/mediumroast/mr_caffeine/./caffeine_svc.py", line 131, in
asyncio.run(main())
File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/./caffeine_svc.py", line 103, in main
await asyncio.gather(*tasks)
File "/home/mediumroast/mr_caffeine/./caffeine_svc.py", line 31, in run_pipeline
await processing_pipeline.run_pipeline(tenant, env)
File "/home/mediumroast/mr_caffeine/lib/pipeline.py", line 286, in run_pipeline
_intermediate_results = await _interactions_pipe(prepared_interactions[2]['partial_data'], tenant, my_env, u)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/pipeline.py", line 102, in _interactions_pipe
processed_interactions = await interaction_processor.run_subpipeline(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/interactions.py", line 123, in run_subpipeline
topics, reprocess = await self._generate_topics(interaction)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/interactions.py", line 67, in _generate_topics
topics_result, reprocess = await topic_modeler.model_document()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/model.py", line 441, in model_document
return await self._bertopic_model()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/model.py", line 419, in _bertopic_model
topics = self._get_topics(document)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/mr_caffeine/lib/model.py", line 371, in _get_topics
topics, probs = model.fit_transform(document)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/bertopic/_bertopic.py", line 449, in fit_transform
umap_embeddings = self._reduce_dimensionality(embeddings, y)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/bertopic/_bertopic.py", line 3744, in _reduce_dimensionality
self.umap_model.fit(embeddings)
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 2784, in fit
self.embedding_, aux_data = self._fit_embed_data(
^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 2830, in _fit_embed_data
return simplicial_set_embedding(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/umap_.py", line 1107, in simplicial_set_embedding
embedding = spectral_layout(
^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/spectral.py", line 304, in spectral_layout
return _spectral_layout(
^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/umap/spectral.py", line 521, in _spectral_layout
eigenvalues, eigenvectors = scipy.sparse.linalg.eigsh(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mediumroast/.local/lib/python3.11/site-packages/scipy/sparse/linalg/_eigen/arpack/arpack.py", line 1608, in eigsh
raise TypeError("Cannot use scipy.linalg.eigh for sparse A with "
TypeError: Cannot use scipy.linalg.eigh for sparse A with k >= N. Use scipy.linalg.eigh(A.toarray()) or reduce k.
```

## Attachment
A PDF representation of a web page with text extracted and cleaned Unstructured.io tooling wrapped in LangChain.
[How to use Jira Product Discovery - Official guide.pdf](https://github.com/user-attachments/files/17802870/How.to.use.Jira.Product.Discovery.-.Official.guide.pdf)

### Reproduction

```python
from bertopic import BERTopic
from bertopic.representation import MaximalMarginalRelevance
from sklearn.feature_extraction.text import CountVectorizer
from langchain_community.document_loaders import UnstructuredFileLoader
from unstructured.cleaners.core import (
clean, clean_bullets, clean_dashes, clean_ligatures,
clean_non_ascii_chars, clean_extra_whitespace,
replace_mime_encodings, replace_unicode_quotes
)

def get_topics(document):
start_time = time.time()
# Instantiate the BERTopic model
model = BERTopic(
vectorizer_model=CountVectorizer(stop_words="english"),
verbose=False,
n_gram_range=(3,5),
representation_model=MaximalMarginalRelevance(),
min_topic_size=2,
nr_topics=10,
)

# Train the model
topics, probs = model.fit_transform(document)

# Get the topics
results = model.get_topics()
topics_with_name = model.get_topic_info() # This is returning a Pandas Dataframe
duration = time.time() - start_time
print(f"Modeled topics for [{self.OBJECT_TYPE}] with id [{str(self.ID)}] in [{duration}] seconds.")
return topics_with_name.to_dict() # Force df to dict

def get_clean_text_langchain(path_to_file):
file_loader = UnstructuredFileLoader(
file_path=path_to_file
mode='elements',
post_processors=[
clean,
clean_extra_whitespace,
clean_bullets,
clean_dashes,
clean_ligatures,
clean_non_ascii_chars,
replace_mime_encodings,
replace_unicode_quotes
]
)
# Load the document
file_elements = interaction_loader.load()
# Obtain the important text from the partition
selected_elements = [e for e in file_elements if e.metadata['category']=="NarrativeText"]
# Combine the text
full_clean = " ".join([e.page_content for e in selected_elements])

# Finished extracting text returning to the calling service
self.logger.info(f"Successfully cleaned and captured text from [{str(extracted)}] interactions, returning to caller.")
return full_clean

# extracted using langchain and ustructured
cleaned_text = get_clean_text_langchain('/path/to/file')
topics = get_topics(cleaned_text)
```

### BERTopic Version

0.16.4

Start by running the provided BERTopic 0.16.4 reproduction with the attached document and inspect the _reduce_dimensionality path in the BERTopic traceback, along with UMAP's spectral.py and SciPy's eigsh error. Compare behavior for this small input and verify that topic generation completes without the reported k >= N failure.

Written by the indexing model from the issue text.