-
-
Notifications
You must be signed in to change notification settings - Fork 644
refactor(ai): standardize prompt building #2198
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
YousefED
wants to merge
11
commits into
main
Choose a base branch
from
refactor/ai-prompts
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
@blocknote/ariakit
@blocknote/code-block
@blocknote/core
@blocknote/mantine
@blocknote/react
@blocknote/server-util
@blocknote/shadcn
@blocknote/xl-ai
@blocknote/xl-docx-exporter
@blocknote/xl-email-exporter
@blocknote/xl-multi-column
@blocknote/xl-odt-exporter
@blocknote/xl-pdf-exporter
commit: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
This PR redesigns how BlockNote AI builds prompts and talks to the LLM.
Instead of mutating the
messagesarray on the client, the editor now attaches metadata (serialized document state) to user messages, and the server turns that into the final LLM prompt usinginjectDocumentStateMessagesandaiDocumentFormats.html.systemPrompt.Core Change
UIMessage[]before sending, assembling document state and instructions in the browser.AIRequestsendMessageWithAIRequestattachesdocumentStateto message metadata and forwards JSON-schema tool definitions.injectDocumentStateMessages(messages)to inject the serialized document into the conversation,system: aiDocumentFormats.html.systemPrompt(or a custom equivalent) when callingstreamText.Effectively, prompt composition has moved from the client into a explicit, server-side step based on message metadata.
Other Changes
sendMessageWithAIRequestand updatedAIExtension.invokeAIto use it, so tool streaming and document metadata are wired upchatProviderso you can hook up your own instance of the AI SDK Chat (for example, when integrating chat windows outside of BlockNote)@blocknote/xl-ai/serverentrypoint that should be safe to import in Next.js. Closes #ai nextBreaking Changes
injectDocumentStateMessages(messages)beforeconvertToModelMessages(...), andsystemprompt (usuallyaiDocumentFormats.html.systemPrompt).Checklist