GraphCanon updated 1d · GitHub synced 1d
Decision brief
Cinnamon's kotaemon is an open-source Retrieval-Augmented Generation-based chat tool that facilitates document interaction through a user-friendly chat interface.
Good fit when
- When you need to customize the file types you can process beyond PDFs, HTML, MHTML, and XLSX by opting for the `full` Docker version which includes additional packages from 'unstructured'.
- For scenarios requiring Dockerized deployment and support for two computing platforms (`linux/amd64`, `linux/arm64`), potentially leveraging Ollama for local/private RAG configurations.
Avoid when
- If you only need to process a limited set of file types (PDF, HTML, MHTML, XLSX) and prefer the smaller Docker image size, as the `lite` version lacks additional package dependencies.
- In environments with strict constraints on external dependencies where installing Docker or Python packages is not feasible.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (34d since push)
- As of 1d
- Provenance
- Not a fork · Organization account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install kotaemon PyPIHow it fits your stack(9)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Cinnamon/kotaemon is an open-source Retrieval-Augmented Generation (RAG)-based chatbot application designed to facilitate interaction with documents through a chat interface, using Python as the primary language and supporting Dockerized deployment in both `lite` and `full` versions for different file type support.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 18, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 18, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 18, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 18, 2026)
1. [Python](https://www.python.org/downloads/) >= 3.10Source link
Tags
README
Installation
If you are not a developer and just want to use the app, please check out our easy-to-follow User Guide. Download the
.zipfile from the latest release to get all the newest features and bug fixes.
System requirements
- Python >= 3.10
- Docker: optional, if you install with Docker
- Unstructured if you want to process files other than
.pdf,.html,.mhtml, and.xlsxdocuments. Installation steps differ depending on your operating system. Please visit the link and follow the specific instructions provided there.
With Docker (recommended)
-
We support both
lite&fullversion of Docker images. Withfullversion, the extra packages ofunstructuredwill be installed, which can support additional file types (.doc,.docx, ...) but the cost is larger docker image size. For most users, theliteimage should work well in most cases.-
To use the
fullversion.docker run \ -e GRADIO_SERVER_NAME=0.0.0.0 \ -e GRADIO_SERVER_PORT=7860 \ -v ./ktem_app_data:/app/ktem_app_data \ -p 7860:7860 -it --rm \ ghcr.io/cinnamon/kotaemon:main-full -
To use the
fullversion with bundled Ollama for local / private RAG.# change image name to docker run <...> ghcr.io/cinnamon/kotaemon:main-ollama -
To use the
liteversion.
# change image name to docker run <...> ghcr.io/cinnamon/kotaemon:main-lite -
-
We currently support and test two platforms:
linux/amd64andlinux/arm64(for newer Mac). You can specify the platform by passing--platformin thedocker runcommand. For example:# To run docker with platform linux/arm64 docker run \ -e GRADIO_SERVER_NAME=0.0.0.0 \ -e GRADIO_SERVER_PORT=7860 \ -v ./ktem_app_data:/app/ktem_app_data \ -p 7860:7860 -it --rm \ --platform linux/arm64 \ ghcr.io/cinnamon/kotaemon:main-lite -
Once everything is set up correctly, you can go to
http://localhost:7860/to access the WebUI. -
We use GHCR to store docker images, all images can be found here.
Without Docker
-
Clone the repository:
git clone https://github.com/Cinnamon/kotaemon cd kotaemon -
Setup the environment:
-
Option 1: Using uv (recommended)
uv sync --python 3.10 source .venv/bin/activate -
Option 2: Using conda
conda create -n kotaemon python=3.10 conda activate kotaemon pip install -e "libs/kotaemon[all]" pip install -e "libs/ktem"
-
Create a
.envfile in the root of this project. Use.env.exampleas a template.The
.envfile is there to serve use cases where users want to pre-config the models before starting up the app (e.g. deploy the app on HF hub). The file will only be used to populate the db once upon the first run, it will no longer be used in consequent runs. -
(Optional) To enable in-browser
PDF_JSviewer, download PDF_JS_DIST then extract it tolibs/ktem/ktem/assets/prebuilt.
-
Start the web server:
python app.py- The app will be automatically launched in your browser.
- Default username and password are both
admin. Y
For agents
This page has a .md twin and JSON over the API.