Skip to content
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

Make /v1 endpoint optional in order to support Ollama models #2181

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

vvok12
Copy link

@vvok12 vvok12 commented Jan 26, 2025

Earlier commit removes the ability to specify /v1 which breaks Ollama integration.

This PR fixes regression by making /v1 ending optional

Summary by CodeRabbit

  • Bug Fixes
    • Updated OpenAI settings URL validation to support optional /v1 endpoint segment
    • Improved base URL validation for more flexible configuration

Copy link

coderabbitai bot commented Jan 26, 2025

📝 Walkthrough

Walkthrough

The pull request introduces a modification to the URL validation regex pattern in the OpenAI settings component. The change allows the base URL to optionally include /v1 at the end, expanding the acceptable URL formats for OpenAI configuration. This subtle adjustment provides more flexibility in how users can specify their OpenAI endpoint URLs while maintaining the core validation structure.

Changes

File Change Summary
apps/client/src/pages/dashboard/settings/_sections/openai.tsx Updated regex pattern for baseURL validation to optionally accept /v1 at the end of the URL

Poem

🐰 A regex tweak, so subtle and neat,
Allowing /v1 to make the URL complete
A rabbit's touch, with validation so light
OpenAI configs now shine just right!
Flexibility dancing, one character strong 🌟


Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

❤️ 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.
    • Generate unit testing code for this file.
    • 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 generate unit testing code for this file.
    • @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 generate unit testing code.
    • @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.

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. (Beta)
  • @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: 0

🧹 Nitpick comments (1)
apps/client/src/pages/dashboard/settings/_sections/openai.tsx (1)

30-30: LGTM! The regex change successfully restores Ollama compatibility.

The updated regex pattern now correctly allows URLs with an optional /v1 endpoint, fixing the regression for Ollama model support.

However, consider making the pattern more flexible:

-    .regex(/^https?:\/\/[^/]+\/?(v1)?$/, "That doesn't look like a valid URL")
+    .regex(/^https?:\/\/[^/]+(:\d+)?\/?(v1)?$/, "That doesn't look like a valid URL")

This improvement adds support for port numbers, which is essential for local Ollama instances (e.g., localhost:11434).

📜 Review details

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

📥 Commits

Reviewing files that changed from the base of the PR and between 1fa8aae and 4e114a2.

📒 Files selected for processing (1)
  • apps/client/src/pages/dashboard/settings/_sections/openai.tsx (1 hunks)
🔇 Additional comments (2)
apps/client/src/pages/dashboard/settings/_sections/openai.tsx (2)

Line range hint 91-102: LGTM! Clear and accurate documentation.

The component provides excellent documentation with:

  • Clear instructions for both OpenAI and Ollama setup
  • Accurate example URL format
  • Proper security and privacy notices

30-30: Verify URL handling across the codebase.

Let's ensure consistent URL handling throughout the codebase:

✅ Verification successful

URL validation is correctly isolated to OpenAI settings

The OpenAI URL validation is specific to the settings section and doesn't need replication elsewhere, as all API interactions are properly centralized in dedicated service files.

🏁 Scripts executed

The following scripts were executed for the analysis:

Script:

#!/bin/bash
# Description: Search for URL validation patterns and API endpoint handling

echo "Searching for URL validation patterns..."
rg -l 'https?:\/\/[^/]+' --type ts --type tsx

echo -e "\nSearching for OpenAI/Ollama API calls..."
rg -l 'baseURL.*openai|openai.*baseURL' --type ts --type tsx

echo -e "\nSearching for v1 endpoint usage..."
rg -l '\/v1\/' --type ts --type tsx

Length of output: 612


Script:

#!/bin/bash
# Description: Search for URL validation patterns and API endpoint handling with corrected regex

# Add tsx as a recognized file type
rg --type-add 'tsx:*.tsx' --type-add 'ts:*.ts'

echo "Searching for URL validation patterns..."
rg -l 'https?://[^/]+' --type ts --type tsx

echo -e "\nSearching for OpenAI/Ollama API calls..."
rg -l 'baseURL.*openai|openai.*baseURL' --type ts --type tsx

echo -e "\nSearching for v1 endpoint usage..."
rg -l '/v1/' --type ts --type tsx

# Also search for specific validation patterns
echo -e "\nSearching for URL validation code..."
rg -l 'regex.*url|validate.*url|isValidUrl' --type ts --type tsx

Length of output: 1129


Script:

#!/bin/bash
# Description: Search for URL validation and API endpoints with simplified approach

echo "Searching for URL validation patterns..."
fd -e ts -e tsx | xargs rg -l 'https?://[^/]+'

echo -e "\nSearching for OpenAI API related code..."
fd -e ts -e tsx | xargs rg -l 'openai'

echo -e "\nSearching for v1 endpoint usage..."
fd -e ts -e tsx | xargs rg -l '/v1'

echo -e "\nSearching for URL validation code..."
fd -e ts -e tsx | xargs rg -l 'regex.*url|validate.*url|isValidUrl'

Length of output: 2927

@AmruthPillai
Copy link
Owner

@vvok12 Can we update the PR to just check if the URL starts with https or http? So the url path or other routes just shouldn't matter. This might be useful when v1 changes to v2 someday and we can make use of the app even then.

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.

2 participants