Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ancoleman/embedding-optimization
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning.
Passed 16 of 22 test cases with the skill, and 10 of 22 without it.
and 8 more in the full report
7 fixed9 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are setting up a RAG pipeline for our company's software documentation and need guidance on text segmentation and model setup. Can you provide a recommendation specifying the chunking strategy, recommended character count and overlap length, plus the best model fit for balanced cost and retrieval quality?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends recursive or heading-aware chunking for software documentation | Passed | Passed |
| Recommends a chunk size of 800 characters for software documentation | Missed | Passed |
| Recommends an overlap size of 100 characters for software documentation | Missed | Passed |
| Recommends text-embedding-3-small or BGE-base-en-v1.5 for balanced cost and retrieval quality | Passed | Passed |
The instructions your model reads when the skill loads.
Optimize embedding generation for cost, performance, and quality in RAG and semantic search systems.
Trigger this skill when:
Choose the optimal embedding model based on requirements:
Quick Recommendations:
all-MiniLM-L6-v2 (local, 384 dims, zero API costs)text-embedding-3-small (API, 1,536 dims, balanced quality/cost)text-embedding-3-large (API, 3,072 dims, premium)multilingual-e5-base (local, 768 dims) or Cohere embed-multilingual-v3.0For detailed decision frameworks including cost comparisons, quality benchmarks, and data privacy considerations, see references/model-selection-guide.md.
Model Comparison Summary:
| Model | Type | Dimensions | Cost per 1M tokens | Best For |
|---|---|---|---|---|
| all-MiniLM-L6-v2 | Local | 384 | $0 (compute only) | High volume, tight budgets |
| BGE-base-en-v1.5 | Local | 768 | $0 (compute only) | Quality + cost balance |
| text-embedding-3-small | API | 1,536 | $0.02 | General purpose production |
| text-embedding-3-large | API | 3,072 | $0.13 | Premium quality requirements |
| embed-multilingual-v3.0 | API | 1,024 | $0.10 | 100+ language support |
Select chunking strategy based on content type and use case:
test cases passed, vs 10 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.