-
-
Notifications
You must be signed in to change notification settings - Fork 5
Added models to the public server #36
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
base: dev
Are you sure you want to change the base?
Conversation
WalkthroughThe README.md file was updated to correct the example JSON configuration by adding a missing comma and introducing a new "model" key with suggested values. No changes were made to code, functionality, or public interfaces. Changes
Poem
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed 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)
Other keywords and placeholders
CodeRabbit Configuration File (
|
There was a problem hiding this 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)
README.md (1)
24-24
: Minor wording tweak for clarity
The prompt string reads a bit awkwardly (“You are helping assistant”). Consider:- "system_prompt": "You are helping assistant who gives very short and factual answers in maximum twenty words and you don't use emojis", + "system_prompt": "You are a helpful assistant who gives very short, factual answers (max 20 words) and never uses emojis.",Purely editorial; feel free to ignore if the original wording is intentional.
@@ -21,7 +21,8 @@ To create your own persona using a OpenAI compatible server create a .json in `~ | |||
"ovos-solver-openai-plugin": { | |||
"api_url": "https://llama.smartgic.io/v1", | |||
"key": "sk-xxxx", | |||
"system_prompt": "You are helping assistant who gives very short and factual answers in maximum twenty words and you don't use emojis" | |||
"system_prompt": "You are helping assistant who gives very short and factual answers in maximum twenty words and you don't use emojis", | |||
"model": "llama3.1:8b" // or qwen2.5:7b |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
//
comment breaks JSON validity – example cannot be copy-pasted
Standard JSON does not allow comments, so the snippet will fail to load if someone copies it verbatim. Move the alternative model hint outside the fenced block or use a textual note below.
- "model": "llama3.1:8b" // or qwen2.5:7b
+ "model": "llama3.1:8b"
Then add a sentence right after the code block:
You can replace
"llama3.1:8b"
with"qwen2.5:7b"
or any other model your server exposes.
📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
"model": "llama3.1:8b" // or qwen2.5:7b | |
"model": "llama3.1:8b" |
🤖 Prompt for AI Agents
In README.md at line 25, the JSON snippet includes a comment using // which
breaks JSON validity and prevents direct copy-pasting. Remove the inline comment
from the JSON snippet to keep it valid, then add a textual note immediately
after the code block explaining that the "model" value can be replaced with
"qwen2.5:7b" or any other supported model.
Summary by CodeRabbit
"model"
key and corrected a missing comma for valid syntax.