skills.rest
Maximilien-ai
Maximilien-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

weave-ingest

Ingests PDFs, text files and images into vector databases via weave-cli pipelines with optional backup and chunking recommendations.

Updated Mar 25, 2026
Search Tags:#schema#rag#backup#pipeline#ingest#vector-databases#collection-management
One-click install
npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-ingest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: weave-ingest
Source: https://github.com/Maximilien-ai/weave-cli-skills/tree/main/skills/weave-ingest
Command: npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ingest data into vector databases — create collections, manage schemas, run batch ingestion pipelines, and back up data.

Core Features & Use Cases

  • Creating collections with schemas
  • Ingesting PDFs, text files, images into vector databases
  • Running batch ingestion pipelines with parallel workers
  • Getting AI-powered schema and chunking recommendations
  • Backing up and restoring collection data

Quick Start

Ingest your first batch of documents into a new collection using weave pipeline ingestion.

Frequently Asked Questions about weave-ingest

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

FAQPage Schema
How do I ingest PDFs, text files, and images into vector databases for RAG retrieval?▼

You can ingest PDFs, text files, and images into vector databases for RAG retrieval by running batch ingestion pipelines with parallel workers. This process creates collections with defined schemas to enable accurate retrieval.

What is the best way to manage schemas and collections when ingesting documents for RAG?▼

The best way to manage schemas and collections during document ingestion is to use a pipeline approach that applies AI-powered schema and chunking recommendations, ensuring your vector database is structured for optimal RAG retrieval.

Do I need weave-cli to run batch ingestion pipelines for vector databases?▼

Yes, you need weave-cli to run batch ingestion pipelines for vector databases. The CLI facilitates per-document ingestion, parallel workers, and optional backup operations across your PDF, text, and image files.

Can I get AI-powered chunking recommendations before ingesting data into a vector database?▼

Yes, you can get AI-powered chunking recommendations before ingesting data into a vector database. The ingestion pipeline provides AI suggestions for both schema design and chunking strategies to optimize RAG retrieval.

How do I back up and restore collection data in a vector database?▼

You back up and restore collection data in a vector database by executing backup operations through weave-cli. This safeguards your ingested documents, schemas, and pipeline collections before making structural changes.

Related Skills

Explore More Data & Analytics Skills→
it-bensit-bens
9

tandoor-recipe-conversion

Convert recipes from images, PDFs, text, or URLs into Tandoor-compatible JSON.

Official
Advanced
I-OnlabsI-Onlabs
3

AgentDB Vector Search

Perform semantic search across document collections using AgentDB vector embeddings.

Community
Advanced
Godhand-ArnavGodhand-Arnav

rag-architect

Design and implement end-to-end RAG pipelines for context-aware LLM responses.

Community
Advanced
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate