ajianaz/codomate/embeddinggemma-qdrant

Claude Code and agent skill by ajianaz/codomate

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

EmbeddingGemma ONNX — CPU-only local embedding (onnxruntime+tokenizers, NO optimum/transformers). Model setup, embed function, Qdrant connection. Use embeddinggemma-knowledge or embeddinggemma-novel for specific use cases.

Install

npx vskill@latest install ajianaz/codomate/embeddinggemma-qdrant

SKILL.md

EmbeddingGemma ONNX — Base Skill

Base skill for local embedding pipeline. Use the specific skill for your use case:

  • embeddinggemma-knowledge — hermes-knowledge collection (newsletter, riset, digest, blog)
  • embeddinggemma-novel — novel chapters collection

Architecture

Text → EmbeddingGemma ONNX (768d) → embed_utils.py (rate control) → Qdrant (cosine similarity)
PropertyValue
Modelonnx-community/embeddinggemma-300m-ONNX (308M params, Q4)
EngineONNX Runtime CPU (188 MB)
Dimensions768 (Matryoshka — truncatable to 512/256/128)
Model path${EMBEDDINGGEMMA_MODEL_DIR}/onnx/model_q4.onnx
Rate control${EMBED_UTILS_PATH}
Vector DBQdrant http://${QDRANT_URL} (HTTP only, check_compatibility=False)
Perf~2s cold load, ~18ms/single, ~0.03s/batch

Quick Start

python
import sys; sys.path.insert(0, "${SCRIPTS_DIR}")
import embeddinggemma
vec = embeddinggemma.embed_one("Hello world", dimensions=768)
vectors = embeddinggemma.embed_texts(["Hello", "World"], dimensions=512)

Packages: onnxruntime + tokenizers only. NO optimum/transformers/torch.

Rate Limits (MANDATORY)

Server: 4 cores, Qdrant on same machine. ALWAYS use `embed_utils.py`:

python
from embed_utils import embed_with_control, embed_one_with_control, acquire_embed_lock, release_embed_lock
# Single
vec = embed_one_with_control("text", dimensions=768)
# Batch with lock
fd = acquire_embed_lock()
try:
vectors = embed_with_control(texts, dimensions=768)
finally:
release_embed_lock(fd)
RuleLimit
Max batch10 (embed_utils.BATCH_SIZE)
Concurrent jobsNEVER (file lock required)
Load checkEvery batch via check_load()
Target load~2.0 (server auto-restarts >2.5)

Collections

CollectionDimensionsPurpose
hermes-knowledge768Skills, entities, agent memory
outline-docs768Outline docs
hermes-sessions512Session recall (real-time)
midjourney512Image references

⛔ Match dimension to collection — mismatch → 400 crash.

Critical Gotchas

  • Server crash = embedding too fast. Always use embed_utils.py, never inline load checks.
  • No concurrent jobs — combine check_load() + acquire_embed_lock().
  • Qdrant URL must use ${QDRANT_URL} — localhost:6333 doesn't work from inside Docker.
  • Point IDs must be UUID strings (use str(uuid.uuid4())). Hex truncation like uuid.uuid4().hex[:16] → 400 error.
  • Qdrant client `https=False` required when connecting to local Qdrant from within Docker. Without it, SSL handshake fails: record layer failure. Also suppress warning: UserWarning: Api key is used with an insecure connection.
  • `embeddinggemma` is a local module at ${EMBEDDINGGEMMA_MODULE}, not a pip package.
  • Mean pooling: NEVER use keepdims=True — produces wrong shape (batch,1,768).

References

  • Setup & Configuration — Model storage, packages, Qdrant config, collections, stress test
  • Code Examples — Loading, embed functions, Qdrant client/REST, embed_utils, migration
  • Pitfalls — All gotchas and critical warnings

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ajianaz/codomate/embeddinggemma-qdrant/badge)](https://verified-skill.com/skills/ajianaz/codomate/embeddinggemma-qdrant)

Something wrong with this skill or its page? Tell us.