Deploy and consume the Multimodal Embedding Serving microservice — bring it up with setup.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists)…
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .claude/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .agents/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .cursor/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .gemini/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .github/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "multimodal-embedding-serving-user" agent skill from https://github.com/open-edge-platform/edge-ai-libraries/tree/main/microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user into .opencode/skills/multimodal-embedding-serving-user/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "multimodal-embedding-serving-user", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
multimodal-embedding-serving-user
GitHub stars
168
Token cost
~1.7k tokens
SKILL.md length
556 words
Files
6
Skills in repo
29
Repo updated
First seen
Licence
Apache-2.0
At a glance
Deploy and consume the Multimodal Embedding Serving microservice — bring it up with setup.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists)…
Works in 5 steps: Context routing — repo clone or… → Bring-up (identical in both contexts) → Capability check (mandatory before… → …
An app needs embeddings for similarity search
SKILL.md covers When to Use, Example Prompts, Docs & deploy files — with or… and 1. Context routing — repo…, plus 5 more sections
Calls curl, docker and bash
What it does
Multimodal Embedding Serving User is an agent skill from open-edge-platform/edge-ai-libraries. Deploy and consume the Multimodal Embedding Serving microservice — bring it up with setup.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists) using the prebuilt intel/multimodal-embedding-serving image, embed text/images/videos over REST on port 9777, choose among 19 models (CLIP/SigLIP/MobileCLIP/CN-CLIP/Blip2/ QwenText), or integrate in-process via the Python SDK wheel. Use when an app needs embeddings for similarity search or retrieval. Not for modifying…
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files (for example `benchmark/benchmark.md`, `evals/evals.json` and `example-prompts/image-duplicate-detector.md`).
It sits in AI & LLM Engineering, covering Embeddings and Microservices. It works with Python, Docker and GitHub. The repository describes itself as: Libraries, microservices, tools, and other reference software, supporting development of performance-optimized Edge AI applications. The licence is Apache-2.0.
When your agent uses it
An app needs embeddings for similarity search
Tasks that involve Embeddings
Tasks that involve Microservices
Example prompts
“/multimodal-embedding-serving-user”
Requirements
Python 3
Docker
Workflow steps
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 960d2e4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
curl
docker
bash
poetry
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use curl and docker, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Multimodal Embedding Serving User loads about 1.7k tokens when it runs. Until then it costs about 154 tokens; SKILL.md has 556 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~154
When it runs· the whole SKILL.md, loaded when a task matches
~1.7k
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/multimodal-embedding-serving-user/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
multimodal-embedding-serving-user
description
Deploy and consume the Multimodal Embedding Serving microservice — bring it up with setup.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists) using the prebuilt intel/multimodal-embedding-serving image, embed text/images/videos over REST on port 9777, choose among 19 models (CLIP/SigLIP/MobileCLIP/CN-CLIP/Blip2/ QwenText), or integrate in-process via the Python SDK wheel. Use when an app needs embeddings for similarity search or retrieval. Not for modifying the service's source — that is multimodal-embedding-serving-dev.
Multimodal Embedding Serving — User
Run and call the embedding service. Run commands yourself and relay
output. REST base URL: http://localhost:9777 (host port hardcoded by
setup.sh; container 8000).
When to Use
Deploy the embedding service (Docker Compose or standalone) and confirm health
Embed text, images, or videos over REST on port 9777
Choose or switch among the CLIP/SigLIP/MobileCLIP/CN-CLIP/Blip2/QwenText models
Integrate embeddings in-process via the Python SDK wheel
Diagnose 400/422 errors or model-capability mismatches
Example Prompts
Sample Problem-solving scenarios this skill handles end-to-end:
Flag duplicate / near-duplicate images in a folder for cleanup, QC, and dataset deduplication
Docs & deploy files — with or without a clone
All paths below are relative to microservices/multimodal-embedding-serving/
in the
edge-ai-libraries
repo. No clone? Fetch any of them from GitHub raw:
1. Context routing — repo clone or standalone? REST or SDK?
In-process Python integration wanted (no separate server): the service
doubles as an SDK — build the wheel with poetry build (needs the repo) and
use get_model_handler(...) + EmbeddingModel; see
docs/user-guide/sdk-usage.md. Rule of thumb: default to REST; pick the SDK
when a Python process embeds heavily and an HTTP hop per item would
dominate. Note: MobileCLIP/Blip2 extras exist only in the Docker image, and
the wheel is not on PyPI.
Pick a model — default CLIP/clip-vit-b-32 (512-dim, text+image+video).
Trade-offs: docs/user-guide/supported-models.md.
setup.sh must be sourced and hard-fails without
EMBEDDING_MODEL_NAME. REGISTRY_URL=intel selects the prebuilt image;
--no-build prevents a source build. Run in the background — first start
downloads the model:bash
Intel GPU: also export EMBEDDING_DEVICE=GPU (setup.sh then auto-enables
OpenVINO + THROUGHPUT mode).
Wait for readiness:bash
until curl -sf http://localhost:9777/health; do sleep 5; done
3. Capability check (mandatory before non-text inputs)
bash
curl -s http://localhost:9777/model/capabilities
QwenText models are text-only — image/video requests return 400. GET /model/current shows the exact loaded model id to use in requests.
4. Embed
Text (single string or list of strings):
bash
curl -s http://localhost:9777/embeddings -H 'Content-Type: application/json' -d '{
"model": "CLIP/clip-vit-b-32",
"input": {"type": "text", "text": "a red truck at a loading dock"},
"encoding_format": "float"
}'
Response: {"embedding": [...]} — a flat vector for text/image; a list of
per-frame vectors for video inputs.
model must equal the loaded model (else 400).
Image: {"type":"image_url","image_url":"https://…"} (plain string, not a
nested object) or image_base64. Video: video_url/video_base64/
video_frames with segment_config (num_frames default 64,
extraction_fps, frame_indexes) — full shapes and examples:
docs/user-guide/api-reference.md.
5. Stop / clean
docker compose -f docker/compose.yaml down
Volumes ov-models (model caches) and data-prep persist; removing them
forces re-downloads — confirm with the user first.
Troubleshooting
Symptom
Likely cause → action
source setup.sh prints ERROR and stops
EMBEDDING_MODEL_NAME not exported → export it first
No response on 9777
still starting/downloading → docker logs -f multimodal-embedding-serving
400 "model mismatch"
request model ≠ loaded model → GET /model/current
400 unsupported modality on image/video
text-only model (QwenText) → switch model or send text
First non-text request slow
lazy OpenVINO conversion/compile → expected once
422 on /embeddings
malformed input union → check shapes in docs/user-guide/api-reference.md
Port 9777 busy
stop the conflicting service (EMBEDDING_SERVER_PORT is hardcoded by setup.sh)
SKILL.md and 5 other files in microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user of open-edge-platform/edge-ai-libraries.
Multimodal Embedding Serving User next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Multimodal Embedding Serving User compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Multimodal Embedding Serving User this skillopen-edge-platform/edge-ai-libraries
Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained .skill bundle (BM25 index + bundled searcher + query protocol).
A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.
Build a new time-series analytics use case on top of the deployed Time Series Analytics microservice — bring it up with Docker Compose (from a repo clone, or by fetching the compose files from…
A skill your agent uses whenever a developer needs to deploy VSS to Kubernetes, helm install VSS, configure values.yaml for VSS, or run VSS on k8s with GPU/vLLM for the…
Deploy and consume the Multimodal Embedding Serving microservice — bring it up with setup.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists)…. Multimodal Embedding Serving User is an agent skill from open-edge-platform/edge-ai-libraries.sh + docker compose (from a repo clone, or by fetching those same files from GitHub when no clone exists) using the prebuilt intel/multimodal-embedding-serving image, embed text/images/videos over REST on port 9777, choose among 19 models (CLIP/SigLIP/MobileCLIP/CN-CLIP/Blip2/ QwenText), or integrate in-process via the Python SDK wheel.
When should I use Multimodal Embedding Serving User?
Multimodal Embedding Serving User fits situations like: an app needs embeddings for similarity search; tasks that involve Embeddings; tasks that involve Microservices.
How do I install Multimodal Embedding Serving User in Claude Code?
Run `npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a claude-code`. Or copy the skill folder (microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user in open-edge-platform/edge-ai-libraries) into .claude/skills/multimodal-embedding-serving-user in your project. Claude Code loads it when a task matches its description.
How do I install Multimodal Embedding Serving User in Codex?
Run `npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a codex`. Or copy the skill folder (microservices/multimodal-embedding-serving/.github/skills/multimodal-embedding-serving-user in open-edge-platform/edge-ai-libraries) into .agents/skills/multimodal-embedding-serving-user in your project. Codex loads it when a task matches its description.
Can I use Multimodal Embedding Serving User in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/edge-ai-libraries --skill multimodal-embedding-serving-user -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/multimodal-embedding-serving-user, .gemini/skills/multimodal-embedding-serving-user, .github/skills/multimodal-embedding-serving-user and .opencode/skills/multimodal-embedding-serving-user in your project.
What does Multimodal Embedding Serving User need to run?
Going by SKILL.md and its folder, Multimodal Embedding Serving User needs the command-line tools its instructions call (curl, docker, bash and poetry). Our summary lists: Python 3; Docker.
Does Multimodal Embedding Serving User access the network?
SKILL.md contains no URLs. Its commands use curl and docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Multimodal Embedding Serving User safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Multimodal Embedding Serving User use?
Multimodal Embedding Serving User is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Multimodal Embedding Serving User use?
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Multimodal Embedding Serving User?
Skills that share tags, products or a category with Multimodal Embedding Serving User: Copilot SDK (github/awesome-copilot, 40k stars), Creating Kb (oaustegard/claude-skills, 150 stars), Molmim Nim (NVIDIA/skills, 3.5k stars) and Vss Deploy Detection Tracking 2D (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Multimodal Embedding Serving User?
open-edge-platform (a GitHub organization) maintains it in open-edge-platform/edge-ai-libraries, which has 168 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 7, 2026.
