Skip to content

fix(embedding): reduce MAX_CHARS to prevent context length errors #23

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
0xranx merged 1 commit into from
Jan 29, 2026
Merged

fix(embedding): reduce MAX_CHARS to prevent context length errors #23

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
7 changes: 4 additions & 3 deletions crates/opencontext-core/src/search/embedding.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,9 +127,10 @@ impl EmbeddingClient {
let input_count = texts.len();

// Truncate texts that are too long (most embedding APIs have ~8K token limit)
// Using char count as approximation: ~4 chars per token for English, ~1-2 for Chinese
// Set conservative limit to avoid API silently dropping texts
const MAX_CHARS: usize = 8000;
// Using char count as approximation: ~4 chars per token for English, ~1-2 for CJK/Cyrillic
// nomic-embed-text and similar models have 8192 token limit
// Conservative limit: 2000 chars (safe for all languages including Cyrillic/CJK)
const MAX_CHARS: usize = 2000;
let texts: Vec<String> = texts
.into_iter()
.map(|t| {
Expand Down