Embedding Strategies

Embedding Strategies

Guide to selecting and optimizing embedding models for vector search applications.

When to Use

• The request matches the skill description: Guide to selecting and optimizing embedding models for vector search applications.
• The task needs the implementation patterns, examples, validation checks, or edge cases listed in the topic map.
• The work would benefit from the complete guidance preserved in references/full-guidance.md.

Core Workflow

1. Confirm the request matches this skill's trigger, scope, and risk profile.
2. Use the topic map to identify the relevant pattern, checklist, or example before writing detailed guidance or code.
3. Load references/full-guidance.md when implementation details, examples, anti-patterns, validation checks, or edge cases are needed.
4. Apply only the relevant guidance instead of loading or repeating the entire reference by default.
5. Verify the result against any validation checks, limitations, security notes, or platform constraints in the reference.

Topic Map

• Do not use this skill when
• Instructions
• Use this skill when
• Core Concepts
• Embedding Model Comparison
• Embedding Pipeline
• Templates
• Template 1: OpenAI Embeddings
• Template 2: Local Embeddings with Sentence Transformers
• Template 3: Chunking Strategies
• Template 4: Domain-Specific Embedding Pipeline
• Template 5: Embedding Quality Evaluation
• Best Practices
• Do's
• Don'ts
• Resources

Reference Map

• references/full-guidance.md preserves the complete original guidance, including examples and detailed edge cases.

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Progressive Loading

Keep this SKILL.md as the compact routing and workflow entrypoint. Load the reference file only when the user task requires the deeper implementation material.