This assumes you have Onyx deployed and at least one knowledge source indexed. If you have not set that up yet, do the self-hosting walkthrough first.

Why use Onyx inside Slack?

Adoption. A separate tool gets forgotten; chat gets used every day. When the bot answers “what is our refund policy?” with a link to the exact Confluence page, people trust it faster than a search box they have to remember to open.

How do you install the Onyx Slack bot?

1. In Onyx admin, go to connectors and choose Slack.
2. Authorize the app for your workspace (you need Slack admin rights).
3. Choose which channels the bot can join.
4. Invite the bot to a channel with /invite @Onyx.
5. Ask a question in that channel or DM the bot directly.

The first answers may take longer while the model warms up.

How do you control who sees what?

Permissions are the hard part. Onyx respects document-level permissions for connected sources, so a user without access to a Drive folder should not get its contents back in Slack. Make sure each source connector is set to sync permissions, not just content. Test with a low-privilege account before rolling out company-wide.

How do you get better answers?

• Ask specific questions (“What is the 2026 expense limit for travel?”) rather than vague ones.
• Name the source when you know it (“according to the HR handbook…”).
• Keep sync schedules current — stale indexes give stale answers.
• Use document filters to narrow the search when results are broad.

What are the trade-offs?

The bot can be too eager and answer from the wrong context if channels mix topics. Some teams restrict it to a single #ask-ai channel to keep signals clean. Also expect a learning curve — answers are only as good as the sources you connected and the freshness of the sync.

Key Takeaways

• Onyx answers questions in Slack with citations from connected apps.
• Setup needs workspace admin rights and takes about 15 minutes.
• Enable permission syncing so answers respect document access.
• Specific questions and fresh syncs improve answer quality.
• Consider limiting the bot to one channel to avoid noisy context.

Last updated October 2026. Details at Onyx.

Self-hosting keeps your documents on your own infrastructure, which is the main reason teams pick it over a hosted chatbot. The cost is setup work and server resources — plan for at least 4 vCPU and 16 GB RAM for a small deployment.

What is Onyx?

Onyx is an enterprise search assistant that indexes content from connected apps and lets you ask natural-language questions. Answers come with links back to the source. It supports GPT-class and open models through API keys, and the whole stack ships as containers.

How do you install Onyx with Docker?

1. Install Docker and Docker Compose on a Linux host (Ubuntu 22.04 or similar).
2. Clone the Onyx repository and open the deployment/docker_compose folder.
3. Copy the sample .env and set a strong Postgres password plus your model API keys.
4. Run docker compose up -d and wait for the containers to become healthy.
5. Open http://your-server-ip:8080, create the first admin account.

First boot takes several minutes while migrations run. The web UI is on port 80/8080 depending on your config.

How do you connect your data sources?

In the admin panel, add connectors one at a time. Onyx will walk you through OAuth for Google Drive and Slack, or an API token for Confluence and Jira. Start with one or two sources so the first index build stays quick. Each connector has a sync schedule you can set to hourly or daily.

Which LLM should you use?

Onyx works with OpenAI, Anthropic, Azure OpenAI, and local models via Ollama or vLLM. For a private deployment, a local 7B–13B model keeps everything on-prem but answers with less polish. A hosted model gives better reasoning at the cost of sending snippets to a third party. Pick based on your data policy, not benchmarks alone.

What does it cost to run?

Software is free under an open license. Your real costs are the server and any LLM API usage. A modest VM runs the stack; indexing large drives needs more RAM and disk. Cloud plans remove the ops burden and add SSO, but you lose full data control.

Key Takeaways

• Onyx is an open-source AI search assistant you can self-host with Docker Compose.
• Minimum practical spec: about 4 vCPU, 16 GB RAM for a small team.
• Connects to Slack, Google Drive, Confluence, Jira and more with per-source sync schedules.
• Works with OpenAI, Anthropic or local models via Ollama/vLLM.
• Choose self-host for data control, cloud for less ops work.

Last updated October 2026. Compare options on the Onyx page.