MythEclipse/GMW
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(automod): force float encoding for embeddings — Nvidia models reject base64
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 1m35s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 2m24s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 2m51s

Browse Source 
OpenAI SDK v6 defaults to encoding_format=base64; llama-nemotron-embed
(Nvidia-backed) returns 400 'do not support base64'. Semantic cache was
silently disabled in prod. encoding_format: 'float' fixes it.
This commit is contained in:
Developer
2026-07-31 20:14:18 +07:00
parent 67e432564d
commit 7ab9a7fd2d
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
services/discord-gateway/src/modules/ai-moderation/embeddingClient.ts
+3
View File
@@ -61,6 +61,9 @@ export async function embedTexts(texts: string[]): Promise<number[][] | null> {
const response = await client.embeddings.create({ const response = await client.embeddings.create({
model: config.AI_LLM_EMBEDDING_MODEL as string, model: config.AI_LLM_EMBEDDING_MODEL as string,
input: texts, input: texts,
// OpenAI SDK v6 defaults to base64; Nvidia-backed embedding models
// (e.g. llama-nemotron-embed) reject it with 400. Always float.
encoding_format: "float",
}); });
return response.data.map((item) => item.embedding); return response.data.map((item) => item.embedding);
} catch (error) { } catch (error) {