skills.rest
richfrem
richfremCOMMUNITY
Explore all skills by this author →
GitHub

vector-db-ingest

Index repository files into ChromaDB using ingest.py with full or incremental modes.

5|3|Updated Feb 21, 2026
Search Tags:#indexing#manifests#semantic-search#ingest#vector-store#chromadb
One-click install
npx skills add https://github.com/richfrem/agent-plugins-skills --skill vector-db-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-db-ingest
Source: https://github.com/richfrem/agent-plugins-skills/tree/main/plugins/vector-db/skills/vector-db-ingest
Command: npx skills add https://github.com/richfrem/agent-plugins-skills --skill vector-db-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires chromadb, langchain, and includes scripts (resource) components.

What problem does it solve?

Ingests repository files into the ChromaDB vector store to enable semantic search by building or updating the vector index from a manifest or directory scan using ingest.py.

Core Features & Use Cases

  • Build and update the vector index by ingesting repository files via a manifest or directory scan.
  • Ingest a single file or a folder using the --file or --folder options for targeted updates.
  • After ingestion, verify retrievability with semantic search using query.py.

Quick Start

Ingest the latest repository files into the vector store using the ingest script.

Frequently Asked Questions about vector-db-ingest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I index repository files into a ChromaDB vector store?▼

To index repository files into a ChromaDB vector store, run the ingest script to build or update the vector index using a manifest or directory scan. You can ingest single files or folders for targeted updates.

What is the difference between full and incremental ingest for semantic search?▼

Full ingest builds the initial vector index by populating the ChromaDB store from a manifest, while incremental ingest updates the index with only the latest repository changes. Both options rely on the ingest.py script.

Do I need langchain and chromadb installed to build a vector index?▼

Yes, you need both chromadb and langchain packages installed to build the vector index. The ingestion and semantic search verification process relies on these dependencies to index and query repository files.

How can I verify if my ingested files are retrievable in the vector store?▼

After ingestion, you can verify retrievability by running semantic search queries using the query.py script. This confirms that your indexed repository files are successfully stored and searchable in the ChromaDB vector store.

Can I target specific files or folders for ingestion into the vector index?▼

Yes, you can target specific files or folders for ingestion using the --file or --folder options. This allows you to perform focused incremental updates rather than scanning the entire repository directory.

How do I select the correct manifest and batch when ingesting into ChromaDB?▼

Use the --profile option when running the ingestion script to select the correct manifest and batch. This ensures the vector index is built or updated using the intended configuration for your repository files.

Related Skills

Explore More Software Engineering Skills→
richfremrichfrem
5

vector-db-audit

Compares filesystem manifest to ChromaDB index to identify missing files.

Community
Intermediate
richfremrichfrem
5

vector-db-search

Perform semantic search against ChromaDB to retrieve contextually relevant code and documentation.

Community
Intermediate
joonlabjoonlab
8

langchain-rag

Implement a retrieval-augmented generation pipeline with LangChain for indexing and querying external knowledge sources.

Community
Advanced
DexploarerDexploarer
7

Railway Qdrant Manager

Deploy Qdrant vector databases on Railway with collection management and vector operations.

Community
Advanced