Skip to content

fix(component,ai,gemini): correct text-based documents logic #1103

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Sep 18, 2025
Merged

fix(component,ai,gemini): correct text-based documents logic #1103

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 5 additions & 6 deletions pkg/component/ai/gemini/v0/task_chat.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -541,14 +541,13 @@ func buildReqParts(in TaskChatInput) ([]genai.Part, error) {
}
} else if isTextBasedDocument(contentType) {
// Text-based documents (TXT, Markdown, HTML, XML, etc.)
// These are processed as pure text content - visual formatting is lost
// The model won't see HTML tags, Markdown formatting, etc.
textContent, err := doc.Text()
// Pass as base64 like PDFs for consistent handling
docBase64, err := doc.Base64()
if err != nil {
return nil, fmt.Errorf("failed to extract text from document: %w", err)
return nil, err
}
if textContent.String() != "" {
parts = append(parts, genai.Part{Text: textContent.String()})
if p := newURIOrDataPart(docBase64.String(), detectMIMEFromPath(docBase64.String(), contentType)); p != nil {
parts = append(parts, *p)
}
} else if isConvertibleToPDF(contentType) {
// Office documents (DOC, DOCX, PPT, PPTX, XLS, XLSX)
Expand Down
Loading