Create and manage a local embedding store with vector and full-text search.
npx skills add https://github.com/adm-humanerd/drewgent --skill chroma-adm-humanerd
Please help me install this Agent Skill. Skill: chroma Source: https://github.com/adm-humanerd/drewgent/tree/main/optional-skills/mlops/chroma Command: npx skills add https://github.com/adm-humanerd/drewgent --skill chroma-adm-humanerd
Embedding storage and retrieval for AI applications is often fragmented across services, making it hard to prototype locally or scale privately. This skill provides a single, self-hosted embedding database with metadata support to enable fast search, retrieval, and memory across projects. It is ideal for local development and open-source workflows, with a simple API for building RAG, semantic search, and document retrieval.
Install chroma, create a collection named my_docs, add documents with embeddings, and run a query to retrieve the most similar results.
High-intent search queries and answers about installing and using this skill.
Store embeddings locally by creating a collection, adding documents with their embeddings and metadata, and querying the store to retrieve the most similar results. This self-hosted embedding database provides a simple 4-function API for managing vector data across notebooks and production environments.
Yes, you can filter semantic search results by metadata in this self-hosted vector database. It supports both vector and full-text search with metadata filtering, allowing you to narrow down retrieved documents based on specific attributes attached during storage.
Build a document retrieval system without external dependencies by using a self-hosted embedding database. It provides a simple 4-function API to store embeddings, perform vector and full-text search, and filter results by metadata, making it ideal for private and local development workflows.
Yes, a self-hosted embedding store works for both local notebooks and production apps. It is designed to scale from local prototyping to production environments, providing a consistent 4-function API for storing embeddings and querying data across different project stages.
Set up a local vector database by installing the tool, creating a named collection, adding documents with embeddings and metadata, and running queries to retrieve similar results. This self-hosted embedding store enables semantic search and RAG workflows without external service dependencies.
lewisperez999Generate text embeddings with OpenAI and search by cosine similarity in Upstash Vector or pg-vector.
SlevoDevEnable semantic search over documents using AgentDB's vector store.
jxtngxOrchestrate document ingestion, chunking, embedding, and semantic search for RAG pipelines.
agentuityUpsert vectors with metadata and embeddings into a cloud vector store.
