GitHub - aitrailblazer/anthropic-claude-golang-sdk: Golang SDK for creating messages using Anthropic Claude API.

git clone https://github.com/aitrailblazer/anthropic-claude-golang-sdk.git
## Configuration

The SDK relies on environment variables for configuration to ensure security and flexibility.

- `ANTHROPIC_API_KEY` (required): Your unique API key for authenticating with Anthropic's API.
- `ANTHROPIC_MODEL` (optional): The model name to use (default is `claude-1.3`).
- `ANTHROPIC_MAX_TOKENS` (optional): Maximum number of tokens to generate in the response (default is 300).

### Setting Environment Variables

On Linux/macOS:

```bash
export ANTHROPIC_API_KEY="your-api-key"
export ANTHROPIC_MODEL="claude-1.3"         # Optional
export ANTHROPIC_MAX_TOKENS=300             # Optional

cd anthropic-claude-golang-sdk/examples

2024/09/18 00:28:55 Sending POST request to https://api.anthropic.com/v1/messages with body: {"model":"claude-1.3","messages":[{"role":"user","content":"Hello there."},{"role":"assistant","content":"Hi, I'm Claude. How can I help you?"},{"role":"user","content":"Can you explain LLMs in plain English?"}],"max_tokens":100,"temperature":0.7}
2024/09/18 00:28:57 Received response with status: 200 OK
2024/09/18 00:28:57 Response body: {"id":"msg_01YNjiU5mFbKVy8MNHCP7brd","type":"message","role":"assistant","model":"claude-1.3","content":[{"type":"text","text":"Sure, here's a simple explanation of large language models or LLMs:\n\n• LLMs are AI systems that have been trained on massive amounts of text data. They learn patterns and relationships between words and phrases to understand language.\n\n• The more text data they are trained on, the more they can understand the nuances, complexities and ambiguities of natural language. Some recent LLMs have been trained on hundreds of billions of words.\n\n• LLMs can be use"}],"stop_reason":"max_tokens","stop_sequence":null,"usage":{"input_tokens":41,"output_tokens":100}}
Response: Sure, here's a simple explanation of large language models or LLMs:

• LLMs are AI systems that have been trained on massive amounts of text data. They learn patterns and relationships between words and phrases to understand language.

• The more text data they are trained on, the more they can understand the nuances, complexities and ambiguities of natural language. Some recent LLMs have been trained on hundreds of billions of words.

anthropic-claude-golang-sdk/
│
├── api
│   ├── client.go     # Handles API requests, authentication, and logging
│   └── message.go    # Contains the SendMessage function to interact with the Messages API
│
├── models
│   └── message.go    # Defines the request and response structures
├── examples
│   └── example.go    # Demonstrates how to use the SDK
├── go.mod            # Go module file
└── go.sum            # Go module checksum file