Skip to content

airweave-ai/cli

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Airweave CLI

pypi npm

A command-line interface for Airweave. Search across your connected sources from any terminal. Built for developers and AI agents.

Installation

pip install airweave-cli

This installs the airweave binary.

Quick Start

# Set your API key
export AIRWEAVE_API_KEY="your-api-key"

# Search a collection
airweave search "quarterly revenue figures" --collection finance-data

# List collections
airweave collections list

Authentication

The CLI resolves credentials in this order:

  1. AIRWEAVE_API_KEY environment variable
  2. ~/.airweave/config.json (saved via airweave auth login)

For interactive setup:

airweave auth login

This prompts for your API key, validates it, and saves it locally.

Self-hosted

Point the CLI at your own Airweave instance:

export AIRWEAVE_BASE_URL="https://airweave.internal.corp.com"

Or set it during airweave auth login.

Commands

Search

airweave search "<query>" --collection <id> --top-k 5 --format json
Flag Short Default Description
--collection -c $AIRWEAVE_COLLECTION Collection readable ID
--top-k -k 10 Number of results
--format -f json Output format: json or text

JSON output (default) writes pure JSON to stdout — nothing else. Pipe it:

airweave search "query" -c my-collection | jq '.results[0].md_content'

Auth

airweave auth login     # interactive setup
airweave auth status    # show current auth state
airweave auth logout    # clear saved credentials

Collections

airweave collections list                           # list all
airweave collections create --name "My Data"        # create
airweave collections get my-data-x7k9m              # get details

Sources

airweave sources list --collection my-data          # list source connections
airweave sources sync <source-connection-id>        # trigger sync
airweave sources sync <id> --force                  # full re-sync

Agent Usage

The CLI is designed for non-interactive use by AI agents. Every command:

  • Outputs clean JSON to stdout (default)
  • Sends all errors to stderr
  • Uses correct exit codes (0 = success, 1 = error)

Environment variables

export AIRWEAVE_API_KEY="sk-..."
export AIRWEAVE_COLLECTION="my-knowledge-base"
export AIRWEAVE_BASE_URL="https://api.airweave.ai"  # optional

Piping

# Get the top result's content
airweave search "how to reset password" | jq -r '.results[0].md_content'

# Get the AI-generated answer
airweave search "what is our refund policy" | jq -r '.completion'

# List collection IDs
airweave collections list | jq -r '.[].readable_id'

CI / Cloud Functions

# GitHub Actions example
- name: Search Airweave
  env:
    AIRWEAVE_API_KEY: ${{ secrets.AIRWEAVE_API_KEY }}
    AIRWEAVE_COLLECTION: docs
  run: |
    result=$(airweave search "deployment guide")
    echo "$result" | jq '.results[:3]'

No SDK imports, no MCP server, no config files — just an env var and a shell.

Configuration

Config file location: ~/.airweave/config.json

{
  "api_key": "sk-...",
  "base_url": "https://api.airweave.ai",
  "collection": "my-default-collection"
}

Resolution order for all settings:

  1. CLI flag (e.g. --collection)
  2. Environment variable (e.g. AIRWEAVE_COLLECTION)
  3. Config file
  4. Default / error

Contributing

git clone https://github.com/airweave-ai/cli.git
cd cli
poetry install
poetry run airweave --help

About

The Airweave CLI for developers and AI agents. Search across your connected sources, manage collections, and integrate Airweave into any environment, no SDK or MCP server required.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors