Skip to content

Conversation

@jagadeeswaran-zipstack
Copy link
Contributor

Summary

• Add 'excel' as a supported processing mode in the JSON schema for LLMWhisperer v2 adapter

Test plan

  • Verify that the new excel mode appears in the adapter settings
  • Test that the excel mode functions correctly with LLMWhisperer v2

🤖 Generated with Claude Code

Added 'excel' as a supported processing mode in the JSON schema for LLMWhisperer v2 adapter.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 8, 2025

Summary by CodeRabbit

  • New Features

    • Introduced an “Excel” mode for LLM Whisperer v2, optimized for .xlsx/.xls inputs. Improves extraction of structured tables and cell values from spreadsheets. Selectable wherever processing mode is configured alongside existing options.
  • Chores

    • Updated SDK version to v0.78.1.

Walkthrough

Adds "excel" to the mode enum in the LLMWhisperer v2 JSON schema and updates the module __version__ from "v0.78.0" to "v0.78.1"; no other behavioral or schema fields changed.

Changes

Cohort / File(s) Summary of Changes
Schema update
src/unstract/sdk/adapters/x2text/llm_whisperer_v2/src/static/json_schema.json
Extended the mode enum to include "excel" (previous enum: "native_text","low_cost","high_quality","form","table"). Default remains "form".
Version bump
src/unstract/sdk/__init__.py
Updated module __version__ from "v0.78.0" to "v0.78.1". Functionality unchanged.

Sequence Diagram(s)

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks (2 passed, 1 warning)

❌ Failed Checks (1 warning)
Check Name Status Explanation Resolution
Description Check ⚠️ Warning The pull request description does not adhere to the repository’s required template, as it only provides a Summary and Test plan while omitting essential sections such as What, Why, How, Relevant Docs, Related Issues or PRs, Dependencies Versions / Env Variables, Notes on Testing, Screenshots, and the Checklist. Update the description to include all required template sections—What, Why, How, Relevant Docs, Related Issues or PRs, Dependencies Versions / Env Variables, Notes on Testing, Screenshots, and the Checklist—to ensure full context and compliance with repository standards.
✅ Passed Checks (2 passed)
Check Name Status Explanation
Title Check ✅ Passed The title clearly summarizes the primary change—adding an “excel” mode to the LLMWhisperer v2 adapter settings—while referencing the relevant ticket and feature label, making it concise and immediately understandable to reviewers.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The description does not follow the repository’s required template and is missing key sections such as “What,” “Why,” “How,” and other mandatory headings, instead using “Summary” and “Test plan,” so it lacks the structured information the template demands. Please update the PR description to use the exact template headings (e.g., “What,” “Why,” “How,” etc.), fill in any missing sections such as Relevant Docs, Dependencies Versions, and the Checklist, and ensure the content under each heading clearly addresses the template requirements.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The title precisely describes the main change by indicating the addition of an “excel” mode to the LLMWhisperer v2 adapter settings and follows conventional formatting with the ticket number and feature tag.
Docstring Coverage ✅ Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
✨ Finishing touches
  • 📝 Generate docstrings
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch UN-2039-add-excel-mode-llmwhisperer-v2

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

Cache: Disabled due to Reviews > Disable Cache setting

Knowledge base: Disabled due to Reviews -> Disable Knowledge Base setting

📥 Commits

Reviewing files that changed from the base of the PR and between 65d8cc7 and 6dc7b15.

📒 Files selected for processing (1)
  • src/unstract/sdk/__init__.py (1 hunks)
🔇 Additional comments (1)
src/unstract/sdk/__init__.py (1)

1-1: Version bump looks appropriate for the feature addition.

The patch version increment (v0.78.0 → v0.78.1) is suitable for the backward-compatible addition of the "excel" mode to the schema. The testing concern for the new mode has already been flagged in the previous review.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@jagadeeswaran-zipstack jagadeeswaran-zipstack changed the title UN-2039: Add excel mode to LLMWhisperer v2 adapter settings UN-2039 [FEAT] Add excel mode to LLMWhisperer v2 adapter settings Sep 8, 2025
Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 0

🧹 Nitpick comments (2)
src/unstract/sdk/adapters/x2text/llm_whisperer_v2/src/static/json_schema.json (2)

40-41: Confirm default remains “form”

If Excel files are a common input, consider switching default contextually (e.g., by mime type) or documenting that users must select "excel".


102-107: Fix minor grammar in webhook description

“which will should be called” → “that should be called”.

Apply this diff:

-      "description": "The webhook's name which will should be called after the conversion is complete. The name should have been registered earlier using the webhooks management endpoint"
+      "description": "The webhook's name that should be called after the conversion is complete. The name should have been registered earlier using the webhooks management endpoint."
📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

Cache: Disabled due to Reviews > Disable Cache setting

Knowledge Base: Disabled due to Reviews > Disable Knowledge Base setting

📥 Commits

Reviewing files that changed from the base of the PR and between 4afc1f2 and f37c496.

📒 Files selected for processing (1)
  • src/unstract/sdk/adapters/x2text/llm_whisperer_v2/src/static/json_schema.json (1 hunks)
🔇 Additional comments (1)
src/unstract/sdk/adapters/x2text/llm_whisperer_v2/src/static/json_schema.json (1)

32-39: Excel mode added — manually verify handling in adapter, validations, mappings, and docs

Ensure every code path that references native_text, low_cost, high_quality, form, or table also includes “excel” (adapter/client logic, server-side validations, switch/mapping statements) and update documentation/UI accordingly. For example, you can run:

grep -RlE 'native_text|low_cost|high_quality|form|table' . | xargs grep -L 'excel'

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

🧹 Nitpick comments (1)
src/unstract/sdk/__init__.py (1)

1-1: Optional: consider PEP 440 version format if used for packaging.

If packaging tools read __version__, PEP 440 prefers 0.77.4 (no leading v). If your build metadata is elsewhere (e.g., pyproject), ignore.

-__version__ = "v0.77.4"
+__version__ = "0.77.4"
📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

Cache: Disabled due to Reviews > Disable Cache setting

Knowledge base: Disabled due to Reviews -> Disable Knowledge Base setting

📥 Commits

Reviewing files that changed from the base of the PR and between f37c496 and 65d8cc7.

📒 Files selected for processing (1)
  • src/unstract/sdk/__init__.py (1 hunks)

Signed-off-by: jagadeeswaran-zipstack <jagadeeswaran@zipstack.com>
Signed-off-by: jagadeeswaran-zipstack <jagadeeswaran@zipstack.com>
Signed-off-by: jagadeeswaran-zipstack <jagadeeswaran@zipstack.com>
@harini-venkataraman harini-venkataraman merged commit b85c150 into main Oct 29, 2025
2 checks passed
@harini-venkataraman harini-venkataraman deleted the UN-2039-add-excel-mode-llmwhisperer-v2 branch October 29, 2025 11:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants