Skill Detail

Chat with private document collections through Kotaemon

Run a self-hosted Kotaemon document QA workflow so agents can index private files, ask grounded questions, and return cited answers.

Data Extraction & TransformationMulti-Framework
Data Extraction & Transformation Multi-Framework Security Reviewed
⭐ 25.4k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill chat-with-private-document-collections-through-kotaemon Copy
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Docker or Python environment, Kotaemon, document collection to index, configured LLM provider or local model such as Ollama
Install & setup
Follow the Kotaemon user guide or run the documented Docker image from ghcr.io/cinnamon/kotaemon, configure the desired LLM and retrieval settings, then create collections and upload documents before running cited QA sessions.
Author
Cinnamon
Publisher
Organization
Last updated
Jun 9, 2026
Quick brief

Use Kotaemon when an agent or operator needs a repeatable private document QA workflow rather than a one-off chat. The workflow is to deploy Kotaemon, load private or team documents into collections, configure the retrieval and model path, ask focused questions, and review cited answers plus source previews before using the result downstream. This is useful when the output must stay tied to a bounded corpus and the operator needs citations that can be checked before a summary, decision memo, support answer, or research note is reused. Keep the scope to document-grounded QA, collection management, retrieval configuration, and citation review over a bounded collection; do not treat this as a generic RAG platform or full product listing. The workflow should remain reviewable against the upstream Kotaemon docs and repository, with Docker or Python setup, model credentials, and document access handled explicitly.

How it works

What this skill actually does

Inputs and prerequisites: Docker or Python environment, Kotaemon, document collection to index, configured LLM provider or local model such as Ollama.

Setup notes: Follow the Kotaemon user guide or run the documented Docker image from ghcr.io/cinnamon/kotaemon, configure the desired LLM and retrieval settings, then create collections and upload documents before running cited QA sessions.

Source and verification boundary: use https://cinnamon.github.io/kotaemon/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.