Index embeddings and metadata for on-disk vector search.
npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill chroma-sheawinkler
Please help me install this Agent Skill. Skill: chroma Source: https://github.com/sheawinkler/hermes-agent-ultra/tree/main/optional-skills/mlops/chroma Command: npx skills add https://github.com/sheawinkler/hermes-agent-ultra --skill chroma-sheawinkler
Index embeddings and metadata for fast, on-disk vector search.
Create a local chroma database and index your documents to enable fast semantic search.
High-intent search queries and answers about installing and using this skill.
Semantic search is built by indexing embeddings and metadata for fast, on-disk vector search. This skill provides a self-hosted vector database backend with a simple API to store and retrieve document data.
Yes, RAG-enabled pipelines are supported across notebooks, local development, and production backends. The database indexes embeddings and metadata to facilitate document retrieval workflows.
Metadata filtering is supported to ensure precise results. The database stores both embeddings and metadata, allowing combined vector and full-text search operations.
The best way to integrate is using the database's simple API designed for common ML tooling. It enables indexing embeddings to build document retrieval workflows seamlessly.
Yes, an open-source vector database backend is required to perform fast, on-disk vector search. This skill provides that backend to index your embeddings and metadata.
HarriesStore and search embeddings with metadata in a self-hosted database.
afel6Store and query embeddings with metadata filtering for semantic search.
overviewlabsManage a fully managed, auto-scaling vector database for production AI applications.
Monjyu1101Store and query embeddings locally with metadata filtering.
