🐛 Bug Report: nomic-embed-text silently truncates input at 512 tokens, and the reported token count is untruncated
Personne n'a encore pris cette issue.
Évaluation
- Difficulté
- 4/5
- Temps estimé
- 3-5 jours
- Accessibilité débutants
- 45/100
- Type d'issue
- Bug
- Clarté
- Plutôt claire
- Activité
- Active
- Stack technique
- docker, rust
- Domaine
- backend, machine-learning
Piste de recherche
Start with src/embedding.rs, where init_model sets the model options, and the tokenizer loading and compute_sub_batch paths described in the report. Check tests/embed_e2e.rs for coverage of vector differences and token counts. The report identifies model context lengths but leaves the default cap and memory tradeoff open; done means embedding respects the chosen cap, reports the count actually embedded, and tests cover both behaviors.
Rédigé par le modèle d'indexation à partir du texte de l'issue.
Description
👟 Reproduction steps
- Run
appwrite/embedding:0.3.1(the image pinned in appwrite/appwrite'sdocker-compose.yml) withEMBEDDING_MODELS=nomic-embed-text,all-minilm. - Embed two texts that share a prefix longer than 512 tokens and differ only in the tail, then compare the vectors.
- Embed one long text (
"word " * 20000) and readtokensin the response.
Script
import json, math, urllib.request
def embed(model, texts):
req = urllib.request.Request("http://localhost:3000/embed",
json.dumps({"model": model, "texts": texts}).encode(),
{"content-type": "application/json"})
return json.load(urllib.request.urlopen(req))
def cos(a, b):
return sum(x*y for x, y in zip(a, b)) / math.sqrt(sum(x*x for x in a) * sum(y*y for y in b))
prefix = "fox " * 600 # > 512 tokens
a = embed("nomic-embed-text", [prefix + "cats cats cats cats"])
b = embed("nomic-embed-text", [prefix + "quantum quantum quantum quantum"])
print(cos(a["embeddings"][0], b["embeddings"][0])) # 1.0, the tails were never seen
print(embed("nomic-embed-text", ["word " * 20000])["tokens"]) # 20002
👍 Expected behavior
nomic-embed-text(the default model) embeds up to its real context length (Nomic Embed Text v1.5 supports 8192), or up to a documented, configurable cap.tokensreports the number of tokens the model actually embedded.
👎 Actual Behavior
The model only sees the first 512 tokens and silently ignores the rest. Binary search over the prefix length finds where the tail stops affecting the vector:
| Model | Tail is ignored once the prefix reaches | Cosine of the two vectors |
|---|---|---|
| nomic-embed-text | 512 tokens | 1.000000 |
| all-minilm | 256 tokens (its real limit) | 1.000000 |
At the same time tokens counts the full, untruncated input:
| Model | tokens reported |
Tokens actually embedded |
|---|---|---|
| nomic-embed-text | 20002 | 512 |
| all-minilm | 256 | 256 |
Impact:
- Semantic search over anything longer than ~400 English words matches only on the opening. Two long documents with the same intro get identical vectors, with no error or warning.
- Appwrite's embedding token usage overstates real work by up to ~40x on long inputs.
Root cause:
- Truncation at 512.
init_modelinsrc/embedding.rsbuildsInitOptions::new(model)withoutwith_max_length, so fastembed falls back toDEFAULT_MAX_LENGTH = 512(fastembed-rs/src/text_embedding/mod.rs), and its tokenizer loader applieswith_truncation(max_length). - Untruncated count. Tokens are counted with a separate tokenizer from
load_tokenizer, which readstokenizer.jsondirectly withTokenizer::from_fileand never applies that truncation. nomic'stokenizer.jsoncarries none, so every input token is counted. (minilm's does, which is why its count is right.)
compute_sub_batch also assumes "~1000-2000 token code chunks", which suggests more than 512 tokens was the intent.
💡 Proposed fix
I'd like to take this:
- Explicit context length per model. Pass
.with_max_length(n)ininit_model, wherenis the model's real context (nomic 8192, gemma 2048, bge-small 512, minilm 256), capped by a newEMBEDDING_MAX_TOKENSenv var so self-hosters can trade context for memory. - Count what was embedded. Apply the same
TruncationParams { max_length: n }to the counting tokenizer inload_tokenizer, sotokensis what the model saw. Optionally add atruncatedcount to the response so Appwrite can tell users when input was cut. - Size memory by the real length. Scale
mb_per_textincompute_sub_batchwith the configuredmax_length(attention grows with seq²) instead of the fixed 100/40 MB, so a higher cap can't OOM the container. - Tests. In
tests/embed_e2e.rs: two texts differing only after 600 tokens must produce different nomic vectors;tokensmust never exceedtexts.len() * max_length. - Docs. State each model's limit in
create-text-embeddings.mdin appwrite/appwrite.
Open question: what should the default cap be? 8192 gives nomic its full context but costs much more memory per text. A middle value (for example 2048, in line with the compute_sub_batch comment) covers most real documents. Steps 2 to 4 hold either way.
Related Appwrite endpoint issues: https://github.com/appwrite/appwrite/issues/15532
🎲 Appwrite version
Different version (specify in environment)
💻 Operating system
MacOS
🧱 Your Environment
appwrite/embedding:0.3.1 in Docker on macOS (CPU, ONNX), as pinned by appwrite/appwrite main at c7949c2887 (12 Nov 2026). The relevant code is unchanged on this repo's main (0.3.3): no commit since 0.3.1 touches max_length or the counting tokenizer.
👀 Have you spent some time to check if this issue has been raised before?
- I checked and didn't find similar issue
🏢 Have you read the Code of Conduct?
- I have read the Code of Conduct
- Langage dominant
- Rust
- Étoiles
- 0
- Forks
- 3
- Merge moyen
- 10 h 33 min
- PR mergées (30 j)
- 4
Préparer son environnement
- Fournit un Dockerfile ou un fichier Docker Compose
- Aucun modèle de pull request
- Lire le guide de contribution
Par où commencer
- Lisez l'issue en entier, puis le guide de contribution du projet.
- Signalez en commentaire que vous la prenez — cela évite que deux personnes fassent le même travail.
- Forkez le dépôt et travaillez sur une branche.
- Ouvrez une pull request qui référence le numéro de l'issue.
Autres issues de appwrite/embedding
-
Dependency DashboardOuverte
Difficulté 4/5 3-5 jours Accessibilité débutants 15/100
Toutes les issues de appwrite/embedding
Issues similaires
-
bug ui
Difficulté 2/5 1-3 heures Accessibilité débutants 84/100
userFRM/egui-charts#3363 ·
Les mainteneurs répondent en général sous 1 jour
-
ada documentation mobile report
Difficulté 1/5 Moins d'une heure Accessibilité débutants 86/100
physicsdolphin/nv-uefi-unlocker#254 · 2 réactions ·
Les mainteneurs répondent en général sous 1 jour
-
bug
Difficulté 2/5 1-3 heures Accessibilité débutants 82/100
kindraywind/rustnarok-client#1382 ·
Les mainteneurs répondent en général sous 1 jour
-
area:accessibility bug good first issue help wanted priority:p3-low size:small
Difficulté 2/5 1-3 heures Accessibilité débutants 78/100
NecturaLabs/Canopy#209 ·
-
CLI config custom-model enhancement
Difficulté 2/5 1-3 heures Accessibilité débutants 68/100
Les mainteneurs répondent en général sous 1 jour