Fix excessive tokens used with data format

[ahuang11]

Serializing a dataframe to YAML caused excessive token bloat:

Data Overview: - input_tokens: 80
  frequency: 1
- input_tokens: 231
  frequency: 1
- input_tokens: 1207
  frequency: 1
- input_tokens: 1324
  frequency: 1
- input_tokens: 1353
  frequency: 1
- input_tokens: 1452
  frequency: 1
- input_tokens: 1539
  frequency: 1
- input_tokens: 1687
  frequency: 1
- input_tokens: 1745
  frequency: 1
- input_tokens: 1895
  frequency: 1
- input_tokens: 1993
  frequency: 1
- input_tokens: 2066
  frequency: 1
- input_tokens: 2115
  frequency: 1
- input_tokens: 2155
  frequency: 1
- input_tokens: 2302
  frequency: 1
- input_tokens: 2316
  frequency: 1
- input_tokens: 2541
  frequency: 1
- input_tokens: 2553
  frequency: 1
- input_tokens: 3342
  frequency: 1
- input_tokens: 3534
  frequency: 1
- input_tokens: 5086
  frequency: 1

Then, sometimes I get:

    return yaml.dump(df.to_dict('index'), default_flow_style=False, allow_unicode=True, sort_keys=False)
                     ^^^^^^^^^^^^^^^^^^^
  File "/Users/ahuang/miniconda3/envs/lumen/lib/python3.12/site-packages/pandas/util/_decorators.py", line 333, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/ahuang/miniconda3/envs/lumen/lib/python3.12/site-packages/pandas/core/frame.py", line 2183, in to_dict
    return to_dict(self, orient, into=into, index=index)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/ahuang/miniconda3/envs/lumen/lib/python3.12/site-packages/pandas/core/methods/to_dict.py", line 242, in to_dict
    raise ValueError("DataFrame index must be unique for orient='index'.")
ValueError: DataFrame index must be unique for orient='index'.

I think to_markdown might be best option.

[codecov]

Codecov Report

❌ Patch coverage is 0% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 47.91%. Comparing base (77e4af2) to head (55307db).
⚠️ Report is 3 commits behind head on main.

Files with missing lines	Patch %	Lines
lumen/ai/utils.py	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1463      +/-   ##
==========================================
+ Coverage   47.90%   47.91%   +0.01%     
==========================================
  Files         122      122              
  Lines       20799    20791       -8     
==========================================
  Hits         9963     9963              
+ Misses      10836    10828       -8     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[philippjfr]

I don't see tabulate used anywhere.