improve native embedder handling of large files #584
Merged
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
server/utils/EmbeddingEngines/native/index.jsIn the #writeToTempfile(filePath, data) {
let fd = 0;
try {
fd = fs.openSync(filePath, "a", 0o666);
let _ = fs.writeSync(fd, data, null, "utf8");
} catch (e) {
console.error(`Error writing to tempfile: ${e}`);
} finally {
if (fd) fs.closeSync(fd);
}
}
async embedChunks(textChunks = []) {
console.log(`\x1b[34m[INFO] Starting embedding process...\x1b[0m`);
...
console.log(`\x1b[34m[INFO] Embedding process completed.\x1b[0m`);
}The async #writeToTempfile(filePath, data) {
try {
await fs.promises.appendFile(filePath, data, { encoding: 'utf8' });
} catch (e) {
console.error(`Error writing to tempfile: ${e}`);
}
} |
cabwds
pushed a commit
to cabwds/anything-llm
that referenced
this pull request
Jul 3, 2025
* improve native embedder handling of large files * perf changes * ignore storage tmp
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Outdated suggestions cannot be applied.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.
Pull Request Type
What is in this change?
Improve
nativeembedder to handle large files (>100K words) without memory accrual resulting in OOM on some devices that are resource-constrained.Additional Information
There could be improvement in other models as well as the native model relies on a local
tmpwrite log for storing the response and other models still keep the embedding array in memory as the iterate.Note: this doesn't improve the speed at which native embeddings are done, it just keeps very large file embeds from crashing the entire instance.
Developer Validations
yarn lintfrom the root of the repo & committed changes