|
|
|
@ -19,31 +19,44 @@ pip install qdrant-client fastembed swarms-memory litellm
|
|
|
|
|
|
|
|
|
|
## Tutorial Steps
|
|
|
|
|
|
|
|
|
|
1. **Install Swarms**: First, install the latest version of Swarms:
|
|
|
|
|
### Step 1: Install Swarms
|
|
|
|
|
|
|
|
|
|
```bash
|
|
|
|
|
pip3 install -U swarms
|
|
|
|
|
```
|
|
|
|
|
First, install the latest version of Swarms:
|
|
|
|
|
|
|
|
|
|
2. **Environment Setup**: Set up your environment variables in a `.env` file:
|
|
|
|
|
```bash
|
|
|
|
|
pip3 install -U swarms
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
```plaintext
|
|
|
|
|
OPENAI_API_KEY="your-api-key-here"
|
|
|
|
|
QDRANT_URL="https://your-cluster.qdrant.io"
|
|
|
|
|
QDRANT_API_KEY="your-api-key"
|
|
|
|
|
WORKSPACE_DIR="agent_workspace"
|
|
|
|
|
```
|
|
|
|
|
### Step 2: Environment Setup
|
|
|
|
|
|
|
|
|
|
Set up your environment variables in a `.env` file:
|
|
|
|
|
|
|
|
|
|
```plaintext
|
|
|
|
|
OPENAI_API_KEY="your-api-key-here"
|
|
|
|
|
QDRANT_URL="https://your-cluster.qdrant.io"
|
|
|
|
|
QDRANT_API_KEY="your-api-key"
|
|
|
|
|
WORKSPACE_DIR="agent_workspace"
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
### Step 3: Choose Deployment
|
|
|
|
|
|
|
|
|
|
Select your Qdrant deployment option:
|
|
|
|
|
|
|
|
|
|
- **In-memory**: For testing and development (data is not persisted)
|
|
|
|
|
- **Local server**: For production deployments with persistent storage
|
|
|
|
|
- **Qdrant Cloud**: Managed cloud service (recommended for production)
|
|
|
|
|
|
|
|
|
|
### Step 4: Configure Database
|
|
|
|
|
|
|
|
|
|
Set up the vector database wrapper with your preferred embedding model and collection settings
|
|
|
|
|
|
|
|
|
|
3. **Choose Deployment**: Select your Qdrant deployment option:
|
|
|
|
|
- **In-memory**: For testing and development (data is not persisted)
|
|
|
|
|
- **Local server**: For production deployments with persistent storage
|
|
|
|
|
- **Qdrant Cloud**: Managed cloud service (recommended for production)
|
|
|
|
|
### Step 5: Add Documents
|
|
|
|
|
|
|
|
|
|
4. **Configure Database**: Set up the vector database wrapper with your preferred embedding model and collection settings
|
|
|
|
|
Load documents using individual or batch processing methods
|
|
|
|
|
|
|
|
|
|
5. **Add Documents**: Load documents using individual or batch processing methods
|
|
|
|
|
### Step 6: Create Agent
|
|
|
|
|
|
|
|
|
|
6. **Create Agent**: Initialize your agent with RAG capabilities and start querying
|
|
|
|
|
Initialize your agent with RAG capabilities and start querying
|
|
|
|
|
|
|
|
|
|
## Code
|
|
|
|
|
|
|
|
|
|