Fix response handler for ollama

[zolezzi1775]

Check for content in ollama response

ollama returns a "content" dict, checking for content dict before falling back to response.

[gemini-code-assist]

Summary of Changes

Hello @zolezzi1775, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request refines the handling of streaming responses from the Ollama language model within the WebSocket chat functionality. The primary goal is to ensure accurate and clean extraction of chat content by prioritizing the 'content' field within 'message' objects and filtering out extraneous metadata, thereby improving the reliability and quality of the real-time chat output.

Highlights

• Ollama Response Parsing: The logic for handling streaming responses from Ollama has been updated to correctly extract the chat content. It now first checks for a 'message' object within the response chunk and attempts to retrieve its 'content' field, providing a more robust parsing mechanism for Ollama's specific response structure.
• Fallback Content Extraction: If the 'content' field is not found within the 'message' object, the system now gracefully falls back to checking for 'response' or 'text' attributes directly on the chunk, ensuring that content is still extracted even if the primary method fails or the response format varies slightly.
• Metadata Filtering: New filtering has been implemented to prevent metadata lines, such as those starting with 'model=' or 'created_at=', from being sent as part of the chat output. This ensures that only relevant conversational text is displayed to the user.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the response handler for Ollama to correctly parse content from the new response structure, which may contain a message dictionary. The change is a good improvement. I've suggested a refinement to make the implementation more robust by safely handling different types of message objects and correctly processing empty strings in the stream, preventing potential runtime errors and incorrect behavior.