fix(extraction): llm extraction strategy not overriding response

[scris]

Summary

In extract() of LLMExtractionStrategy, response is not overridden. Thus if some error is met in later part of this try, in except we'll get error triggering response.choices[0].message.content: 'str' object has no attribute 'choices', as response is now overridden into a string.

https://github.com/unclecode/crawl4ai/blob/main/crawl4ai/extraction_strategy.py#L658-L689

This error occurs occasionally when crawl4ai is used against a list of models include gemini-2.5-pro and gemini-2.5-flash.

List of files changed and why

In extract() of LLMExtractionStrategy, change response = response.choices[0].message.content to content = ..., so response is not overriden.

How Has This Been Tested?

Extract for 200 different webpages after fixing this on my computer.

Checklist:

• [x] My code follows the style guidelines of this project
• [x] I have performed a self-review of my own code
• [x] I have commented my code, particularly in hard-to-understand areas
• [ ] I have made corresponding changes to the documentation
• [ ] I have added/updated unit tests that prove my fix is effective or that my feature works
• [x] New and existing unit tests pass locally with my changes

Summary by CodeRabbit

• Refactor
  • Improved internal variable naming for clearer distinction between LLM response objects and their content. No changes to user-facing features or functionality.

[coderabbitai[bot]]

Walkthrough

The variable used to store the LLM response content in the LLMExtractionStrategy.extract method was renamed from response to content to prevent overwriting the original response object. All subsequent references were updated to use content for clarity and to avoid confusion.

Changes

File(s)	Change Summary
crawl4ai/extraction_strategy.py	Renamed the variable holding LLM response content from response to content in the extract method, updating all related references.

Poem

A hop and a skip, a name set right,
No more confusion in code's bright light.
response and content now clearly apart,
Less tangled logic, a fresh bunny start!
🐇✨

[!NOTE]

⚡️ AI Code Reviews for VS Code, Cursor, Windsurf

CodeRabbit now has a plugin for VS Code, Cursor and Windsurf. This brings AI code reviews directly in the code editor. Each commit is reviewed immediately, finding bugs before the PR is raised. Seamless context handoff to your AI code agent ensures that you can easily incorporate review feedback. Learn more here.

[!WARNING]

Review ran into problems

🔥 Problems

Git: Failed to clone repository. Please run the @coderabbitai full review command to re-trigger a full review. If the issue persists, set path_filters to include or exclude specific files.

---

📜 Recent review details

Configuration used: CodeRabbit UI Review profile: CHILL Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 897e0173618d20fea5d8952ccdbcdad0febc0fee and 149c7447ad64ddcc46396afd7058d003975c8e0f.

📒 Files selected for processing (1)

• crawl4ai/extraction_strategy.py (2 hunks)

🔇 Additional comments (3)

crawl4ai/extraction_strategy.py (3)

659-659: Preserve full LLM response object
Assigning response.choices[0].message.content to a new content variable avoids overwriting the original response, ensuring downstream exception handlers still have access to the full response object.

---

663-663: Consistent JSON parsing from content
Switching to json.loads(content) keeps parsing focused on the extracted text and prevents inadvertent use of the raw response object for JSON decoding.

---

676-676: Use content in XML extraction step
Updating the XML extraction call to extract_xml_data(..., content) ensures the preserved text is used, eliminating reliance on the original response field and aligning with the new content naming.

✨ Finishing Touches

• [ ] 📝 Generate Docstrings

---

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

• X
• Mastodon
• Reddit
• LinkedIn

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Explain this complex logic.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
  • @coderabbitai explain this code block.
  • @coderabbitai modularize this function.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read src/utils.ts and explain its main purpose.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
  • @coderabbitai help me debug CodeRabbit configuration file.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

• @coderabbitai pause to pause the reviews on a PR.
• @coderabbitai resume to resume the paused reviews.
• @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
• @coderabbitai full review to do a full review from scratch and review all the files again.
• @coderabbitai summary to regenerate the summary of the PR.
• @coderabbitai generate docstrings to generate docstrings for this PR.
• @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
• @coderabbitai resolve resolve all the CodeRabbit review comments.
• @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
• @coderabbitai help to get help.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[lance6716]

Hi @unclecode @aravindkarnam I meet a problem of error 'str' object has no attribute 'choices' and I think this PR will fix it. Can you take a look? Thanks.