Fix FastLLM bug, defaults

[NolanTrem]

Important

Remove fast_llm default and set None defaults for UnstructuredIngestionConfig attributes.

• Behavior:
  • Remove fast_llm default value from CompletionConfig in llm.py.
  • Set default values to None for attributes in UnstructuredIngestionConfig in base.py, including coordinates, encoding, extract_image_block_types, and others.
• Misc:
  • No changes to logic or functionality, only default value adjustments.

^{This description was created by for 9ca5de5. It will automatically update as commits are pushed.}

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to 9ca5de5 in 33 seconds

More details

• Looked at 70 lines of code in 2 files
• Skipped 0 files when reviewing.
• Skipped posting 6 drafted comments based on config settings.

1. py/core/base/providers/llm.py:25

• Draft comment:
  fast_llm default removed. Ensure no dependent code still references it.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50%
  The comment is asking the author to ensure that no dependent code references the removed default, which is a form of asking the author to double-check something. This violates the rule against asking the author to ensure behavior is intended or to double-check things.

2. py/core/providers/ingestion/unstructured/base.py:49

• Draft comment:
  Defaults added for optional fields improve clarity. Verify they align with usage expectations.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50%
  This comment is asking the PR author to verify something, which is against the rules. It does not provide a specific suggestion or point out a specific issue with the code.

3. py/core/providers/ingestion/unstructured/base.py:61

• Draft comment:
  Defaults added for additional optional fields. Confirm that downstream code correctly handles 'None' values.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50%
  The comment is asking the PR author to confirm that downstream code handles 'None' values correctly. This falls under the rule of not asking the author to ensure behavior is intended or to double-check things. Therefore, this comment should be removed.

4. py/core/base/providers/llm.py:25

• Draft comment:
  Removed the 'fast_llm' attribute from the config. Ensure that any dependent code or documentation referencing it is updated.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50%
  The comment is asking the PR author to ensure that dependent code or documentation is updated, which violates the rule against asking the author to ensure things are tested or reviewed. It doesn't provide a specific suggestion or point out a specific issue with the code.

5. py/core/providers/ingestion/unstructured/base.py:49

• Draft comment:
  Default values (None) have been added for multiple optional config fields. Confirm that downstream consumers correctly handle explicit None instead of missing keys.
• Reason this comment was not posted:
  Comment did not seem useful. Confidence is useful = 0% <= threshold 50%
  The comment is asking the PR author to confirm that downstream consumers handle explicit None values correctly. This falls under the rule of not asking the author to confirm their intention or to ensure behavior is intended. Therefore, this comment should be removed.

6. py/core/providers/ingestion/unstructured/base.py:385

• Draft comment:
  Typo: In the TODO comment, 'inadvertedly' should be corrected to 'inadvertently' for clarity.
• Reason this comment was not posted:
  Comment was not on a location in the diff, so it can't be submitted as a review comment.

Workflow ID: wflow_4DzINswLEWn6mteL

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.