File contents Semantic Search
Pure vector similarity search using embeddings on a single collection.
Usage
uv run scripts/semantic_search.py --query "USER_QUERY" --collection "CollectionName" [--limit 10] [--distance 0.5] [--target-vector "vector_name"] [--json]
Parameters
Parameter
Flag
Required
Default
Description
--query-qYes
—
Search query text
--collection-cYes
—
Collection name
--limit-lNo
10Maximum number of results
--distance-dNo
—
Maximum distance threshold (filters out less similar results)
--target-vector-tNo
—
Target vector name for named vector collections
--json—
No
falseOutput in JSON format
Output
Default : Markdown table with object properties and distance scoresJSON : Array of objects with properties and distance metadata
Examples
Basic semantic search:
uv run scripts/semantic_search.py --query "environmental impact of urbanization" --collection "Research"
With distance threshold:
uv run scripts/semantic_search.py --query "machine learning" --collection "Papers" --distance 0.3 --limit 5
With named vector:
uv run scripts/semantic_search.py --query "abstract art" --collection "Artworks" --target-vector "description_vector"
1 --- 2 name: 2513-semantic-search-3e5098c0 3 description: Semantic Search 4 --- 5 # Semantic Search 6 7 Pure vector similarity search using embeddings on a single collection. 8 9 ## Usage 10 11 ```bash 12 uv run scripts/semantic_search.py --query "USER_QUERY" --collection "CollectionName" [--limit 10] [--distance 0.5] [--target-vector "vector_name"] [--json] 13 ``` 14 15 ## Parameters 16 17 | Parameter | Flag | Required | Default | Description | 18 |-----------|------|----------|---------|-------------| 19 | `--query` | `-q` | Yes | — | Search query text | 20 | `--collection` | `-c` | Yes | — | Collection name | 21 | `--limit` | `-l` | No | `10` | Maximum number of results | 22 | `--distance` | `-d` | No | — | Maximum distance threshold (filters out less similar results) | 23 | `--target-vector` | `-t` | No | — | Target vector name for named vector collections | 24 | `--json` | — | No | `false` | Output in JSON format | 25 26 ## Output 27 28 - **Default**: Markdown table with object properties and distance scores 29 - **JSON**: Array of objects with properties and distance metadata 30 31 ## Examples 32 33 Basic semantic search: 34 35 ```bash 36 uv run scripts/semantic_search.py --query "environmental impact of urbanization" --collection "Research" 37 ``` 38 39 With distance threshold: 40 41 ```bash 42 uv run scripts/semantic_search.py --query "machine learning" --collection "Papers" --distance 0.3 --limit 5 43 ``` 44 45 With named vector: 46 47 ```bash 48 uv run scripts/semantic_search.py --query "abstract art" --collection "Artworks" --target-vector "description_vector" 49 ``` 50
commit 1d74860309
Frequently asked questions How do I install the 2513 Semantic Search 3e5098c0 skill? Run npx skillmds@latest add tools-only/2513-semantic-search-3e5098c0 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the 2513 Semantic Search 3e5098c0 skill do? Semantic Search It is listed under Research & Search on SkillMD.
Is 2513 Semantic Search 3e5098c0 safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with 2513 Semantic Search 3e5098c0? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is 2513 Semantic Search 3e5098c0 free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published 2513 Semantic Search 3e5098c0? tools-only (@tools-only) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tools-only