llmswap

https://llmswap.org/documentation
Admin
Universal AI CLI and Python SDK providing seamless access to 8 AI providers (OpenAI, Claude, Gemini,...
Tokens:1,092
Snippets:14
Trust Score:4.3
Update:4 months ago
Show doc for...
Tokens:
Raw
### Install llmswap with Homebrew

Source: https://llmswap.org

Installs llmswap using Homebrew and configures an API key for a provider. It then demonstrates how to start an interactive chat session.

```bash
# Install with Homebrew
brew install llmswap/tap/llmswap

# Configure provider
export ANTHROPIC_API_KEY="sk-ant-..."

# Start using
llmswap chat
```

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

### Install llmswap from Source

Source: https://llmswap.org

Installs llmswap by cloning the repository, installing dependencies, and then configuring API keys and running the CLI. This method is suitable for development or custom builds.

```bash
# Clone repository
git clone https://github.com/sreenathmmenon/llmswap
cd llmswap

# Install dependencies
pip install -e .

# Configure and run
export OPENAI_API_KEY="sk-..."
llmswap chat
```

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

### Install llmswap with Pip

Source: https://llmswap.org

Installs the llmswap package using pip and sets up environment variables for API keys for supported providers. Then, starts an interactive chat session.

```bash
# Install with pip
pip install llmswap

# Set up your preferred provider (only need one)
export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
export GEMINI_API_KEY="..."

# Start using
llmswap chat
```

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

### Generate Code with llmswap

Source: https://llmswap.org

Use llmswap to generate code based on a natural language description. This example shows generating an Nginx configuration for load balancing.

```bash
$ llmswap generate "create nginx config for load balancing"

upstream backend {
    server backend1.example.com:8080;
    server backend2.example.com:8080;
    server backend3.example.com:8080;
}

server {
    listen 80;
    location / {
        proxy_pass http://backend;
    }
}
```

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

### Compare AI Provider Costs

Source: https://llmswap.org

Compares the cost of using different AI providers for a specific number of input and output tokens. This helps in identifying cost-saving opportunities.

```bash
$ llmswap compare --input-tokens 1000 --output-tokens 500

Provider Cost Comparison:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Provider    | Cost    | Savings
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Ollama      | $0.000  | 100%
Groq        | $0.001  | 95%
Gemini      | $0.002  | 90%
Claude      | $0.015  | 25%
GPT-4       | $0.020  | 0%
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
```

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

### Interactive Chat with Provider Switching

Source: https://llmswap.org

Demonstrates an interactive chat session where the user can switch between AI providers during the conversation. The CLI remembers context across messages.

```bash
$ llmswap chat
🤖 Starting chat (Provider: claude)
You: What's the weather like?
Assistant: I don't have access to real-time weather data...

You: /switch gemini
🔄 Switched to gemini

You: Tell me about Python decorators
Assistant: Python decorators are a powerful feature...
```

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

### Interactive Chat with Conversation Memory

Source: https://llmswap.org

Illustrates an interactive chat session that maintains conversation context. The AI remembers previous user inputs, such as the user's name.

```bash
$ llmswap chat
You: My name is Alice
Assistant: Nice to meet you, Alice! How can I help you today?

You: What's my name?
Assistant: Your name is Alice.
```
Tokens:
Raw