### Install Dependencies and Start Development Server

Source: https://github.com/airweave-ai/airweave/blob/main/connect/README.md

Install project dependencies using npm and start the development server. The application will be accessible at http://localhost:3000.

```bash
npm install
npm run dev
```

--------------------------------

### Install and Build MCP Server from Source

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

For developers building from source. Installs dependencies, builds the project, and starts the server.

```bash
cd mcp
npm install
npm run build
npm run start
```

--------------------------------

### Install Dependencies and Run Server

Source: https://github.com/airweave-ai/airweave/blob/main/examples/webhook-demo/README.md

Installs project dependencies and starts the FastAPI development server. Access the UI at http://localhost:8000.

```bash
cd examples/webhook-demo
pip install -r requirements.txt
uvicorn app:app --port 8000
```

--------------------------------

### Install and Setup Pre-commit Hooks

Source: https://github.com/airweave-ai/airweave/blob/main/CONTRIBUTING.md

Install the pre-commit package and set up the hooks to automatically check code before committing.

```bash
pip install pre-commit
pre-commit install
```

--------------------------------

### Start Temporal Services for Development (Alternative)

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/domains/temporal/README.md

An alternative command to start Temporal services specifically for development environments.

```bash
# Or for development
docker-compose -f docker/docker-compose.dev.yml up -d
```

--------------------------------

### Install llama-index and airweave tools

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/framework-integrations/llamaindex.mdx

Install the necessary packages for LlamaIndex and the Airweave integration.

```bash
pip install llama-index llama-index-tools-airweave
```

--------------------------------

### Install Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/framework-integrations/vercel-ai-sdk.mdx

Install the necessary packages for Vercel AI SDK and Airweave integration.

```bash
npm install ai @ai-sdk/openai @airweave/vercel-ai-sdk
```

--------------------------------

### Install Airweave SDK

Source: https://github.com/airweave-ai/airweave/blob/main/examples/intro_to_airweave.ipynb

Install the Airweave SDK using pip. This command should be run once.

```python
# First, pip install the Airweave SDK (run this once):
%pip install airweave-sdk
```

--------------------------------

### Install Frontend Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/frontend/README.md

Installs project dependencies using npm or bun. Ensure Node.js v18+ is installed.

```sh
git clone https://github.com/airweave-ai/airweave

cd airweave/frontend

npm install
# or
bun install
```

--------------------------------

### Start Development Server and Open Test Harness

Source: https://github.com/airweave-ai/airweave/blob/main/connect/README.md

Start the development server and then open `public/test-parent.html` in your browser to test iframe communication. This HTML file simulates a parent application embedding the Connect widget.

```bash
# Start the dev server
npm run dev

# Open test-parent.html in your browser
# It simulates a parent application embedding the Connect widget
```

--------------------------------

### Install Airweave SDK

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/quickstart.mdx

Install the Airweave SDK for Python or Node.js using pip or npm.

```bash
pip install airweave-sdk
```

```bash
npm install @airweave/sdk
```

--------------------------------

### Install Backend Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Install Python dependencies for the backend using Poetry. This should be run after cloning the repository.

```bash
cd backend
poetry install
```

--------------------------------

### Install @airweave/connect-react

Source: https://github.com/airweave-ai/airweave/blob/main/connect/packages/react/README.md

Install the connect-react package using npm.

```bash
npm install @airweave/connect-react
```

--------------------------------

### Install Frontend Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Install Node.js dependencies for the frontend using npm. This should be run after cloning the repository.

```bash
cd frontend
npm install
```

--------------------------------

### Install Vanilla JS Connect Package

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/connect.mdx

Install the vanilla JavaScript package for the Airweave Connect widget.

```bash
npm install @airweave/connect-js
```

--------------------------------

### Clone and Start Airweave Locally

Source: https://github.com/airweave-ai/airweave/blob/main/README.md

Use these commands to clone the Airweave repository and start the services locally. Requires Docker and docker-compose. The script handles environment setup, secret generation, and service startup.

```bash
git clone https://github.com/airweave-ai/airweave.git
cd airweave
./start.sh
```

--------------------------------

### Install Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

Install project dependencies using npm.

```bash
npm install
```

--------------------------------

### Install Airweave CLI from Source

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/cli.mdx

Clone the repository and install the Airweave CLI from source using Poetry. This is useful for development or if you need the latest unreleased features.

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

--------------------------------

### Connector YAML Configuration Example

Source: https://github.com/airweave-ai/airweave/blob/main/monke/README.md

Example of a connector's YAML configuration file, specifying 'composio' as the authentication mode and providing the necessary account and auth config IDs.

```yaml
auth_mode: composio
composio_config:
  account_id: ca_xxx
  auth_config_id: ac_xxx
```

--------------------------------

### Start Temporal Services for Local Development

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/domains/temporal/README.md

Ensures Temporal is running locally, which is part of the docker-compose setup for development.

```bash
docker-compose -f docker/docker-compose.dev.yml up -d
```

--------------------------------

### Start Temporal Services for Production

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/domains/temporal/README.md

Starts the Temporal server and worker using the main docker-compose configuration.

```bash
# From project root
docker-compose -f docker/docker-compose.yml up -d
```

--------------------------------

### Copy .env file

Source: https://github.com/airweave-ai/airweave/blob/main/monke/README.md

Use this command to create a local environment file from the example.

```bash
cp monke/.env.example monke/.env
```

--------------------------------

### Install Airweave SDKs

Source: https://github.com/airweave-ai/airweave/blob/main/README.md

Install the Airweave SDK for Python or TypeScript using pip or npm.

```bash
pip install airweave-sdk        # Python
```

```bash
npm install @airweave/sdk       # TypeScript
```

--------------------------------

### Start Development Server

Source: https://github.com/airweave-ai/airweave/blob/main/frontend/README.md

Launches the development server for local testing. The server typically runs on http://localhost:5173.

```sh
npm run dev
# or
bun run dev
```

--------------------------------

### Install MCP Server Globally with npm

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

Installs the MCP server globally using npm. After installation, you can run the server command directly.

```bash
npm install -g airweave-mcp-search
airweave-mcp-search
```

--------------------------------

### Install Airweave CLI

Source: https://github.com/airweave-ai/airweave/blob/main/README.md

Install the Airweave CLI using pip.

```bash
pip install airweave-cli
```

--------------------------------

### Test Configuration Example

Source: https://github.com/airweave-ai/airweave/blob/main/monke/README.md

Example YAML configuration file defining test parameters, including entity count, rate limiting, and deletion strategy.

```yaml
name: github
connector_type: github

config_fields:
  entity_count: 5          # How many test entities to create
  rate_limit_delay_ms: 1000  # API rate limiting
  test_branch: monke-test    # GitHub-specific config

deletion:
  partial_delete_count: 2    # Delete 2 entities first
  verify_partial_deletion: true  # Then verify they're gone
```

--------------------------------

### Install Test Dependencies

Source: https://github.com/airweave-ai/airweave/blob/main/backend/tests/e2e/README.md

Installs all necessary Python packages for running the tests. Ensure you are in the project's root directory.

```bash
pip install -r requirements.txt
```

--------------------------------

### Install Airweave Skills using CLI

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/skills.mdx

Install both Airweave skills at once or individually using the skills CLI. The CLI detects your AI assistant and places the skill files in the correct location.

```bash
npx skills add airweave-ai/skills
```

```bash
npx skills add airweave-ai/skills --skill airweave-setup
```

```bash
npx skills add airweave-ai/skills --skill airweave-search
```

--------------------------------

### Started Event

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/search.mdx

Emitted once when the search begins. Includes request details and initial parameters.

```json
{
  "type": "started",
  "request_id": "req-abc123",
  "tier": "agentic",
  "collection_readable_id": "my-collection",
  "query": "What authentication methods do we support?",
  "thinking": true,
  "filter": null,
  "limit": null
}
```

--------------------------------

### Development Installation Script for MCP

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

A script for developers to install dependencies, build, and test the MCP project from source. Requires Node.js 20+.

```bash
git clone https://github.com/airweave-ai/airweave.git
cd airweave/mcp
./install.sh
```

--------------------------------

### Run Frontend Development Server

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Start the Vite development server for the frontend. The application will be accessible at http://localhost:8080.

```bash
npm run dev
```

--------------------------------

### Install and Run Airweave MCP Search Server

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

Install the Airweave MCP Search server using npx and run it. This command is typically used for local development or direct integration with desktop AI clients.

```bash
npx airweave-mcp-search
```

--------------------------------

### Verify Docker Installation

Source: https://github.com/airweave-ai/airweave/blob/main/README.md

Before starting Airweave, verify that Docker is installed and running by checking its version and system info.

```bash
docker --version
docker info
```

--------------------------------

### Initialize Development Environment with Docker

Source: https://github.com/airweave-ai/airweave/blob/main/CONTRIBUTING.md

Run the start script to set up the initial development environment using Docker Compose.

```bash
./start.sh
```

--------------------------------

### Run Airweave Quickstart Tutorial with Interactive Input

Source: https://github.com/airweave-ai/airweave/blob/main/examples/README.md

Execute the Python tutorial script and enter your Airweave API key when prompted. This method allows for interactive API key entry during script execution.

```bash
python quickstart_tutorial.py
# Enter your API key when prompted
```

--------------------------------

### Verify Airweave CLI Installation

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/cli.mdx

Check the installed version of the Airweave CLI to confirm the installation was successful.

```bash
airweave --version
```

--------------------------------

### Run Airweave Quickstart Tutorial with Self-Hosted Instance

Source: https://github.com/airweave-ai/airweave/blob/main/examples/README.md

Configure both the Airweave API key and the base URL for a self-hosted Airweave instance as environment variables before running the Python tutorial script.

```bash
export AIRWEAVE_API_KEY="your-api-key-here"
export AIRWEAVE_BASE_URL="http://localhost:8001"
python quickstart_tutorial.py
```

--------------------------------

### Install Airweave CLI with npm

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/cli.mdx

Install the Airweave CLI globally using npm. This method installs the Python CLI as a dependency.

```bash
npm install -g @airweave/cli
```

--------------------------------

### Environment Configuration Examples

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/analytics/README.md

Configure analytics by setting environment variables. Ensure `ANALYTICS_ENABLED` is true and specify the `ENVIRONMENT` for proper filtering in PostHog.

```bash
# Production environment (.env.prod)
ANALYTICS_ENABLED=true
ENVIRONMENT=prd

# Development environment (.env.dev)
ANALYTICS_ENABLED=true
ENVIRONMENT=dev

# Local development (.env.local)
ANALYTICS_ENABLED=false
ENVIRONMENT=local

# Testing (.env.test)
ANALYTICS_ENABLED=false
ENVIRONMENT=test
```

--------------------------------

### Container Partial Override Example

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/architecture-refactor.md

Demonstrates how to create a container with a real event bus and a fake publisher for specific testing scenarios.

```python
from airweave.core.container import Container
from airweave.core.protocols.event_bus import InMemoryEventBus

# Assuming test_container is already defined as in the previous example
# container_with_real_bus = test_container.replace(event_bus=InMemoryEventBus())

```

--------------------------------

### Build Frontend for Production

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Create a production-ready build of the frontend application. This optimizes assets for deployment.

```bash
npm run build
```

--------------------------------

### Start Model Context Protocol Server

Source: https://github.com/airweave-ai/airweave/blob/main/CONTRIBUTING.md

Run the MCP server for local development and testing of source integrations. Ensure LOCAL_CURSOR_DEVELOPMENT is set to true in your .env file.

```python
python .cursor/mcp/sync_test/server.py
```

--------------------------------

### Start Airweave Backend Only

Source: https://github.com/airweave-ai/airweave/blob/main/README.md

To start only the backend services without the frontend, use the --skip-frontend flag.

```bash
./start.sh --skip-frontend
```

--------------------------------

### Configure Direct Credentials

Source: https://github.com/airweave-ai/airweave/blob/main/monke/README.md

For local development, set core settings and direct connector tokens. All connector tokens should be prefixed with MONKE_.

```bash
# Core settings
AIRWEAVE_API_URL=http://localhost:8001
OPENAI_API_KEY=sk-...

# Connector-specific tokens (all use MONKE_ prefix)
MONKE_GITHUB_PERSONAL_ACCESS_TOKEN=ghp_...
MONKE_GITHUB_REPO_NAME=owner/repo
MONKE_NOTION_ACCESS_TOKEN=secret_...
MONKE_ASANA_PERSONAL_ACCESS_TOKEN=1/...
MONKE_STRIPE_API_KEY=sk_test_...
# ... see .env.example for more
```

--------------------------------

### Install Ollama LLM for LlamaIndex

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/framework-integrations/llamaindex.mdx

Install the necessary package to use Ollama models with LlamaIndex. This is required for local model integration.

```bash
pip install llama-index-llms-ollama
```

--------------------------------

### Example Conventional Commit Message

Source: https://github.com/airweave-ai/airweave/blob/main/CONTRIBUTING.md

An example illustrating the conventional commit message format, specifying a new feature for the sources component.

```bash
feat(sources): add support for Notion API
```

--------------------------------

### Initialize MCP Server via HTTP POST

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/mcp-server.mdx

Initialize a connection to the hosted MCP server using a POST request. This example demonstrates the required headers and JSON payload for the `initialize` method over Streamable HTTP.

```bash
curl -X POST https://mcp.airweave.ai/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: text/event-stream" \
  -H "X-API-Key: your-api-key" \
  -H "X-Collection-Readable-ID: your-collection-id" \
  -d '{"jsonrpc": "2.0", "method": "initialize", "params": {"protocolVersion": "2025-03-26", "capabilities": {}, "clientInfo": {"name": "my-client", "version": "1.0.0"}}, "id": 1}'
```

--------------------------------

### Start All Services with Docker

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Use this script to start all Airweave services locally using Docker. Options are available to skip the frontend or restart services.

```bash
./start.sh
./start.sh --skip-frontend
./start.sh --restart
./start.sh --destroy
```

--------------------------------

### Example Claude Desktop Queries

Source: https://github.com/airweave-ai/airweave/blob/main/mcp/README.md

Examples of natural language queries that can be used with the Airweave MCP server in Claude Desktop to search for specific information.

```text
# "Search for customer feedback about pricing"
# "Find the most recent documents about API changes"
# "Show me support tickets from the last week"
```

--------------------------------

### Clone and Setup Airweave Repository

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/add-new-source.mdx

Clone the Airweave repository and set up your development environment using the provided script.

```bash
git clone https://github.com/YOUR_USERNAME/airweave.git
cd airweave
./start.sh
```

--------------------------------

### Concrete Domain Event Example

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/architecture-refactor.md

An example of a concrete domain event that inherits from `BaseDomainEvent`, narrows the `event_type` using a specific enum, and adds domain-specific fields.

```python
class SyncLifecycleEvent(BaseDomainEvent):
    event_type: SyncEventType           # narrowed from str
    sync_id: UUID
    sync_job_id: UUID
    collection_id: UUID
    source_connection_id: UUID
    source_type: str = ""
    # ... metrics, error, etc.
```

--------------------------------

### Run Backend Development Server

Source: https://github.com/airweave-ai/airweave/blob/main/CLAUDE.md

Start the FastAPI development server for the backend. This command enables hot-reloading for rapid development.

```bash
poetry run uvicorn airweave.main:app --host 0.0.0.0 --port 8001 --reload
```

--------------------------------

### Webhook Delivery Example

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/webhooks/overview.mdx

This is an example of an HTTP POST request that Airweave sends to your webhook endpoint when a sync completes. Your server should respond with a 200 OK status to acknowledge receipt.

```http
POST /webhooks/airweave HTTP/1.1
Host: your-server.com
Content-Type: application/json
svix-id: msg_2xKvB8LPqM4nRst
svix-timestamp: 1705329000
svix-signature: v1,g0hM9SsE+OTPJTGt/tmIKtSyZlE3uFJELVlNIOLJ1OE=

{
  "event_type": "sync.completed",
  "sync_id": "440e8400-e29b-41d4-a716-446655440099",
  "sync_job_id": "550e8400-e29b-41d4-a716-446655440000",
  "collection_id": "770e8400-e29b-41d4-a716-446655440002",
  "collection_readable_id": "sales-data-ab123",
  "collection_name": "Sales Data",
  "source_connection_id": "660e8400-e29b-41d4-a716-446655440001",
  "source_type": "salesforce",
  "entities_inserted": 42,
  "entities_updated": 10,
  "entities_deleted": 3,
  "entities_skipped": 120,
  "chunks_written": 215,
  "timestamp": "2025-01-15T14:30:00Z"
}
```

--------------------------------

### Centralized Protocols Example

Source: https://github.com/airweave-ai/airweave/blob/main/backend/airweave/architecture-refactor.md

Shows how protocols are organized by capability rather than scattered across domains. Domains import from these centralized protocols, and adapters implement them.

```python
core/protocols/
├── messaging.py      # EventPublisher, StatePublisher
├── storage.py        # FileStorage, CredentialStore
├── sources.py        # Source
├── destinations.py   # Destination
└── embeddings.py     # Embedder
```

--------------------------------

### API Validation Error Example

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/auth-providers/pipedream.mdx

This JSON shows an example error response when the Pipedream provider does not support the specified source. This indicates a configuration mismatch between the provider and the intended source application.

```json
{
  "detail": "Source 'github' does not support 'pipedream' as an auth provider. Supported providers: []"
}
```

--------------------------------

### Run E2E Tests

Source: https://github.com/airweave-ai/airweave/blob/main/backend/tests/README.md

Instructions for setting up and executing End-to-End tests. Ensure you are in the `tests/e2e` directory, install dependencies, and create a `.env.test` file with your credentials before running `pytest`.

```bash
cd tests/e2e
pip install -r requirements.txt

# Create .env.test with your credentials

# Run tests
pytest smoke/
```

--------------------------------

### List Collections

Source: https://github.com/airweave-ai/airweave/blob/main/fern/docs/pages/framework-integrations/pipedream.mdx

Get all collections in your organization.

```APIDOC
## List Collections

### Description
Get all collections in your organization.

### Parameters
#### Query Parameters
- **skip** (integer) - Optional - Number of collections to skip (default: 0)
- **limit** (integer) - Optional - Maximum collections to return (default: 50)
```

--------------------------------

### Complete Example - Combining Advanced Search Features

Source: https://github.com/airweave-ai/airweave/blob/main/examples/search_concepts.ipynb

Demonstrates a comprehensive search using multiple advanced features together, including AI query expansion, hybrid search, structured filtering, recency bias, score threshold, AI reranking, and pagination. Requires proper filter imports and valid data.

```python
print("🚀 COMPLETE EXAMPLE")
print("=" * 50)

print("Example 14: Advanced search with all features")
try:
    # Import the required filter classes
    from airweave.models import Filter, FieldCondition, MatchAny
    
    results = client.collections.search_advanced(
        readable_id=COLLECTION_ID,
        query="customer feedback about pricing",
        expansion_strategy="llm",           # AI query expansion
        search_method="hybrid",            # Best search method
        filter=Filter(
            must=[FieldCondition(
                key="source_name",
                match=MatchAny(any=["Zendesk", "Slack"])
            )]
        ),
        recency_bias=0.5,                 # Prefer recent content
        score_threshold=0.7,              # High confidence only
        enable_reranking=True,            # AI reranking
        response_type="raw",              # Raw results
        limit=50,                         # Pagination
        offset=0
    )
    
    print(f"Advanced search completed!")
    print(f"Results: {len(results.results)}")
    print("This example demonstrates:")
    print("- AI query expansion")
    print("- Hybrid search method")
    print("- Source filtering")
    print("- Recency bias")
    print("- Score threshold")
    print("- AI reranking")
    print("- Pagination")
    
except Exception as e:
    print(f"Error: {e}")
    print("Note: This example requires proper filter imports and valid data")

print()
print("🎉 Tutorial completed! You now know how to use Airweave search effectively.")
print()
print("Next steps:")
print("1. Try these examples with your own data")
print("2. Experiment with different parameters")
print("3. Check out the interactive API docs: https://docs.airweave.ai/api-reference")
print("4. Read our blog for advanced tips: https://airweave.ai/blog")


# ============================================================================ 
# HELPER FUNCTIONS & TIPS

```

--------------------------------

### AI Answer Generation - Get Synthesized Responses

Source: https://github.com/airweave-ai/airweave/blob/main/examples/search_concepts.ipynb

Generate a synthesized answer based on search results for question-answering scenarios. Use `response_type="completion"` to get a direct AI-generated response instead of a list of documents. Perfect for chatbots.

```python
print("💬 AI ANSWER GENERATION")
print("=" * 50)
    
print("Example 13: Get AI-generated answers")
try:
        results = client.collections.search_advanced(
            readable_id=COLLECTION_ID,
            query="What are our customer refund policies?",
            response_type="completion"  # Get AI-generated answer
        )
        
        if hasattr(results, 'completion') and results.completion:
            print("AI Answer:")
            print(results.completion)
        else:
            print("No completion generated")
except Exception as e:
        print(f"Error: {e}")
    
print()

```

--------------------------------

### API Client Usage Example

Source: https://github.com/airweave-ai/airweave/blob/main/frontend/README.md

Demonstrates correct usage of the `apiClient` for making requests to the backend. Use relative paths; the client handles URL construction.

```tsx
import { apiClient } from '@/lib/api';

// Correct
const response = await apiClient.get('/sources');

// Incorrect
const response = await apiClient.get('api/v1/sources');
```