skills.rest
Alex1980Alex
Alex1980AlexCOMMUNITY
Explore all skills by this author →
GitHub

embedding-models

Configure embedding models with ONNX backend and query/passage prefixes.

1|Updated Sep 20, 2025
Search Tags:#embeddings#retrieval#embedding#model-selection#onnx#prefix#dimension-mismatch
One-click install
npx skills add https://github.com/Alex1980Alex/1C-Enterprise_Framework --skill embedding-models
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: embedding-models
Source: https://github.com/Alex1980Alex/1C-Enterprise_Framework/tree/main/.claude/skills/embedding-models
Command: npx skills add https://github.com/Alex1980Alex/1C-Enterprise_Framework --skill embedding-models

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Embedding models selection, tuning, and debugging to ensure reliable vector representations for downstream retrieval and similarity tasks, including handling dimension mismatches, ONNX backend setup, and query/passage prefixes.

Core Features & Use Cases

  • Model cataloging and comparison for multilingual and Russian-focused contexts.
  • Prefix handling for query: and passage: prompts to ensure consistent embedding generation.
  • Backend configuration guidance (e.g., ONNX) and diagnostics to resolve dimension mismatches.
  • Diagnostic workflow to evaluate model quality, speed, and compatibility across several embedding providers.

Quick Start

Configure EMBEDDING__MODEL to your chosen embedding model and run a quick validation pass to verify dimensions and query/passage prefixes.

Frequently Asked Questions about embedding-models

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix embedding dimension mismatches when switching retrieval models?▼

Resolve embedding dimension mismatches by validating model compatibility through a diagnostic workflow that evaluates vector dimensions and aligns configurations across different embedding providers.

Why does my embedding model need query and passage prefixes for retrieval?▼

Query and passage prefixes ensure consistent embedding generation by distinguishing search queries from stored passages, which maintains accurate vector similarity calculations during retrieval.

How do I configure ONNX backend for embedding models?▼

Configure ONNX backend for embedding models by applying backend setup guidance and diagnostics to optimize inference speed and resolve deployment issues during vector generation.

Can I compare multilingual embedding models for Russian language retrieval?▼

Compare multilingual embedding models for Russian language retrieval using the model cataloging and comparison features to evaluate quality, speed, and compatibility across embedding providers.

What is the best way to evaluate embedding model quality for downstream similarity tasks?▼

Evaluate embedding model quality for similarity tasks by running a config-driven workflow that compares embeddings, validates dimensions, and checks query and passage prefix rules.

Do I need to validate embedding dimensions before deploying a new retrieval model?▼

Validate embedding dimensions before deploying a new retrieval model to prevent dimension mismatches and ensure the ONNX backend and prefix handling rules are correctly configured.

Related Skills

Explore More Data & Analytics Skills→
Alex1980AlexAlex1980Alex

framework-config

Document and validate PDF Vector Framework environment variables across profiles.

Community
Intermediate
ccfccf

embedding-strategies

Select and optimize embedding models for semantic search and RAG applications.

Community
Intermediate
AndyAnh174AndyAnh174

vector-database-engineer

Designs vector search systems with database selection, embedding configuration, and hybrid search integration.

Community
Advanced
openclaw-easyopenclaw-easy
14

sherpa-onnx-tts

Convert input text to speech locally using sherpa-onnx and ONNX models.

Community
Intermediate