ChromaDB Embeddings

SkillAI & models

Store and query vector embeddings using ChromaDB at {{CHROMADB_HOST}}:{{CHROMADB_PORT}}.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the ChromaDB Embeddings skill

What this skill tells your AI

The instructions your AI receives, as published by bidewio/better-openclaw in skills/chromadb-embeddings/SKILL.md and read by ahel’s review.

ChromaDB is available at http://{{CHROMADB_HOST}}:{{CHROMADB_PORT}} within the Docker network.

Create a Collection

curl -X POST "http://{{CHROMADB_HOST}}:{{CHROMADB_PORT}}/api/v1/collections" \
  -H "Content-Type: application/json" \
  -d '{"name": "my_collection", "metadata": {"hnsw:space": "cosine"}}'

Add Documents

curl -X POST "http://{{CHROMADB_HOST}}:{{CHROMADB_PORT}}/api/v1/collections/{collection_id}/add" \
  -H "Content-Type: application/json" \
  -d '{"ids": ["doc1"], "documents": ["Hello world"], "metadatas": [{"source": "test"}]}'

Query Similar Documents

curl -X POST "http://{{CHROMADB_HOST}}:{{CHROMADB_PORT}}/api/v1/collections/{collection_id}/query" \
  -H "Content-Type: application/json" \
  -d '{"query_texts": ["greeting"], "n_results": 5}'

Tips for AI Agents

ChromaDB can auto-generate embeddings if configured with an embedding function.
Use metadata filters to narrow search results.
Prefer cosine distance for normalized embeddings.

Signals

GitHub stars: 58
Forks: 6
Last commit: Aug 2026

Advanced

Item type: skill
Key: chromadb-embeddings
Source: github.com/bidewio/better-openclaw

github.com/bidewio/better-openclaw