Skip to content

Improve chat API documentation clarity based on customer feedback #3280

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

tpayet
Copy link
Member

@tpayet tpayet commented Jun 24, 2025

Summary

This PR improves the chat completions documentation based on feedback from customer support interactions. The changes make the documentation more welcoming and easier to understand for users setting up conversational search.

Changes

API Reference Updates (/reference/api/chats.mdx)

  • Added a tip linking to index conversation settings for content optimization
  • Clarified that PATCH /chats/{workspace}/settings automatically creates workspaces if they don't exist
  • Added a new "Privacy and data storage" section explicitly stating that Meilisearch doesn't store conversation data

Getting Started Guide Updates (/guides/ai/getting_started_with_chat.mdx)

  • Added friendly "Understanding workspaces" section explaining the concept with examples
  • Added "Managing conversations" section with code examples showing how to handle stateless conversations
  • Made the overall tone more encouraging and approachable

Related Issue

Based on customer support feedback about chat completions feature documentation.

Test plan

  • All markdown linting passes (npm run marklint)
  • Prose linting checked (npm run proselint)
  • Preview documentation changes in Mintlify
  • Verify links work correctly
  • Check that examples are clear and accurate

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Documentation
    • Added sections explaining workspaces and managing conversation history, including JavaScript and Python code examples, to the AI chat getting started guide.
    • Enhanced the /chats API documentation with tips on conversation settings, clarification on workspace creation, and a new section on privacy and data storage.
    • Improved formatting and readability in the tool calling section of the API docs.
    • Added a Python code sample for updating typo tolerance settings in the typo tolerance guide.

tpayet and others added 2 commits June 24, 2025 13:55
Based on customer support feedback, this commit enhances the chat completions documentation with:

- Added link to index conversation settings for better content optimization
- Clarified that PATCH /chats/{workspace}/settings automatically creates workspaces
- Added explicit privacy section stating no conversation data is stored
- Improved workspace explanation in getting started guide
- Added conversation management example showing stateless nature
- Made documentation more welcoming and easier to understand

These changes address common customer questions and make the complex chat feature more approachable.

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

Co-Authored-By: Claude <[email protected]>
Copy link

coderabbitai bot commented Jun 24, 2025

Walkthrough

Documentation was updated to enhance guidance on AI chat workspaces, conversation management, and privacy. New sections explain workspace concepts, provide code examples for handling conversation history in JavaScript and Python, and clarify that conversation context is not stored server-side. A Python code sample was added for typo tolerance settings.

Changes

Files/Groups Change Summary
guides/ai/getting_started_with_chat.mdx Added sections on workspaces and managing conversations, with JavaScript/Python code examples and clarifications.
reference/api/chats.mdx Added privacy and data storage section, workspace auto-creation note, tip on conversation settings per index, and formatting improvements in tool calling examples.
snippets/samples/code_samples_typo_tolerance_guide_5.mdx Added Python code snippet for updating typo tolerance settings on numbers for the "movies" index.

Poem

In the warren of docs, new wisdom appears,
On workspaces and chats, the guidance is clear.
Python joins the party with typo control,
Privacy is honored, stateless the goal.
With snippets and notes, the path is in view—
A rabbit’s delight: fresh knowledge for you!
🐇✨


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
🪧 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.

Copy link

@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: 2

🧹 Nitpick comments (1)
guides/ai/getting_started_with_chat.mdx (1)

282-344: Minor: consider tightening JS sample to avoid unhandled promise at top level

The snippet uses await at the top level; some bundlers still require it to be wrapped in an async function or top-level await support. Not critical, but you may want to wrap the snippet in an IIFE for portability.

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between be63fbc and 32df4c3.

📒 Files selected for processing (3)
  • guides/ai/getting_started_with_chat.mdx (3 hunks)
  • reference/api/chats.mdx (7 hunks)
  • snippets/samples/code_samples_typo_tolerance_guide_5.mdx (1 hunks)
🧰 Additional context used
🪛 LanguageTool
reference/api/chats.mdx

[uncategorized] ~574-~574: Loose punctuation mark.
Context: ...the scenes. Arguments: - call_id: Unique identifier to track the search o...

(UNLIKELY_OPENING_PUNCTUATION)


[uncategorized] ~597-~597: Loose punctuation mark.
Context: ...s and results. Arguments: - role: Message author role ("user" or "assista...

(UNLIKELY_OPENING_PUNCTUATION)


[uncategorized] ~621-~621: Loose punctuation mark.
Context: ...rification. Arguments: - call_id: Matches the call_id from `_meiliSearc...

(UNLIKELY_OPENING_PUNCTUATION)

🔇 Additional comments (2)
snippets/samples/code_samples_typo_tolerance_guide_5.mdx (1)

18-22: Python snippet looks correct – no action needed

The call signature, dict syntax, and key casing (disableOnNumbers) match the REST payload and the Python SDK expectations.

reference/api/chats.mdx (1)

11-13: Verify target anchor of the “conversation settings” link

The link points to /reference/api/settings#conversation.
Double-check that the actual heading ID on the settings page is indeed conversation; otherwise users will land at the top of the page instead of the intended section.

- Removed duplicate "Understanding workspaces" section in getting_started_with_chat.mdx
- Replaced non-standard Capsule component with built-in Note component in chats.mdx

These changes address PR feedback to prevent duplicate anchors and ensure compatibility with the documentation build system.

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

Co-Authored-By: Claude <[email protected]>
Copy link

@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 (4)
reference/api/chats.mdx (2)

402-414: Great addition, but consider tightening the wording

The bullets already state that no data is stored. The opening sentence repeats the same idea nearly verbatim.
A single concise sentence followed by the bullet list would read better and reduce redundancy.


573-577: Minor formatting glitch after “Arguments” heading

There is a double space before the line break, triggering the LanguageTool UNLIKELY_OPENING_PUNCTUATION warning.
Removing the extra space silences the linter without affecting rendering.

guides/ai/getting_started_with_chat.mdx (2)

275-299: Provide full-context snippet or add a note

client is referenced but never declared in this code block, and await is used at top level.
Either:

  1. Prepend the snippet with the two-line client instantiation (as shown earlier), or
  2. Add a short sentence like “Assume client is defined as in the previous section and that your environment supports top-level await.”

This prevents cut-and-paste frustrations.


301-325: Python snippet: show client creation for completeness

Same context issue as the JS example. A one-liner creating client (or a brief comment referring back) will make the example self-contained.

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 32df4c3 and 8c94335.

📒 Files selected for processing (2)
  • guides/ai/getting_started_with_chat.mdx (2 hunks)
  • reference/api/chats.mdx (7 hunks)
🧰 Additional context used
🪛 LanguageTool
reference/api/chats.mdx

[uncategorized] ~574-~574: Loose punctuation mark.
Context: ...the scenes. Arguments: - call_id: Unique identifier to track the search o...

(UNLIKELY_OPENING_PUNCTUATION)


[uncategorized] ~597-~597: Loose punctuation mark.
Context: ...s and results. Arguments: - role: Message author role ("user" or "assista...

(UNLIKELY_OPENING_PUNCTUATION)


[uncategorized] ~621-~621: Loose punctuation mark.
Context: ...rification. Arguments: - call_id: Matches the call_id from `_meiliSearc...

(UNLIKELY_OPENING_PUNCTUATION)

⏰ Context from checks skipped due to timeout of 90000ms (1)
  • GitHub Check: Mintlify Deployment
🔇 Additional comments (3)
reference/api/chats.mdx (2)

11-13: Verify anchor correctness for new “conversation settings” link

/reference/api/settings#conversation looks plausible, but the settings page usually namespaces subsections as #conversation-settings.
Please double-check the generated anchor in the target file to avoid a broken link.


47-49: Nice UX clarification

Calling out the auto-creation of workspaces removes a common stumbling block.
No further action required.

guides/ai/getting_started_with_chat.mdx (1)

24-33: Duplicate section issue resolved – nice cleanup

Comment on lines 597 to 598
- `role`: Message author role ("user" or "assistant")
- `content`: Message content (for tool results)
Copy link

Choose a reason for hiding this comment

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

⚠️ Potential issue

Incorrect value in role description

The description says either role or assistant – the first option should be user.

- "description": "The role of the messages author, either `role` or `assistant`"
+ "description": "The role of the message author, either `user` or `assistant`"

Committable suggestion skipped: line range outside the PR's diff.

🧰 Tools
🪛 LanguageTool

[uncategorized] ~597-~597: Loose punctuation mark.
Context: ...s and results. Arguments: - role: Message author role ("user" or "assista...

(UNLIKELY_OPENING_PUNCTUATION)

🤖 Prompt for AI Agents
In reference/api/chats.mdx at lines 597 to 598, the description of the `role`
field incorrectly states the possible values as "role" or "assistant". Update
the description to correctly specify that `role` can be either "user" or
"assistant" to accurately reflect the message author roles.

@tpayet tpayet marked this pull request as draft June 26, 2025 07:51
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.

1 participant