> For the complete documentation index, see [llms.txt](https://doc.datagram.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.datagram.network/apis/api-reference/network-intel-api.md). # Network Intel API ### Overview The Datagram Network Intel API provides access to language models through a chat completions endpoint. This API allows you to interact with various AI models in a conversational format. **Base URL:** `https://intel.api.datagram.network` ### Authentication All API requests require authentication using an API key passed in the Authorization header. **Authorization:**`Bearer YOUR_API_KEY` ### Chat Completions **Endpoint** ``` POST /api/v1/chat/completions ``` **URL** ``` https://intel.api.datagram.network/api/v1/chat/completions ``` Creates a chat completion response for the given conversation. **Headers** | Header | Required | Description | Example | | ---------------------- | -------- | ----------------------------------- | --------------------------------- | | **Authorization** | Yes | Bearer token for API authentication | `Bearer sk_live_abc123...xyz456` | | **Content-Type** | Yes | Must be application/json | `application/json; charset=utf-8` | | **sec-ch-ua-platform** | No | Client platform information | `"Windows"` | **Request Body** | Parameter | Type | Required | Description | Example | | ------------ | ------- | -------- | -------------------------------------------------------- | ------------------------------------------------------------ | | **model** | string | Yes | ID of the model to use (e.g., "llama3.2:1b") | `"llama3.2:1b"` | | **messages** | array | Yes | Array of message objects representing the conversation | `[{"role": "user", "content": "Explain quantum computing"}]` | | **stream** | boolean | No | Whether to stream back partial progress (default: false) | true | **Message Object** | Parameter | Type | Required | Description | Example | | ----------- | ------ | -------- | -------------------------------------------------------- | ------------------------------------------------- | | **role** | string | Yes | The role of the message author (system, user, assistant) | `"user"` | | **content** | array | Yes | Array of content objects containing the message text | `[{"type": "text", "text": "Explain AI safety"}]` | **Content Object**
ParameterTypeRequiredDescriptionExample
typestringYesType of content (e.g., "text")"text"
textstringYesThe actual text content"Explain quantum entanglement"
### Examples #### Basic Chat Completion ``` curl 'https://intel.api.datagram.network/api/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ --data-raw '{ "model": "llama3.2:1b", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "What is the capital of France?" } ] } ], "stream": false }' ``` #### Chat with System Message ``` curl 'https://intel.api.datagram.network/api/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ --data-raw '{ "model": "llama3.2:1b", "messages": [ { "role": "system", "content": [ { "type": "text", "text": "You are a helpful assistant that speaks like a pirate." } ] }, { "role": "user", "content": [ { "type": "text", "text": "Tell me about the weather" } ] } ], "stream": false }' ``` #### Streaming Response ``` curl 'https://intel.api.datagram.network/api/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ --data-raw '{ "model": "llama3.2:1b", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Write a short story about a robot" } ] } ], "stream": true }' ``` #### Multi-turn Conversation ``` curl 'https://intel.api.datagram.network/api/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ --data-raw '{ "model": "llama3.2:1b", "messages": [ { "role": "system", "content": [ { "type": "text", "text": "You are a helpful coding assistant." } ] }, { "role": "user", "content": [ { "type": "text", "text": "How do I create a Python function?" } ] }, { "role": "assistant", "content": [ { "type": "text", "text": "To create a Python function, use the def keyword followed by the function name and parameters in parentheses." } ] }, { "role": "user", "content": [ { "type": "text", "text": "Can you show me an example?" } ] } ], "stream": false }' ``` ### Response Format #### Non-streaming Response ``` { "id": "chatcmpl-123", "object": "chat.completion", "created": 1677652288, "model": "llama3.2:1b", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "The capital of France is Paris." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 9, "completion_tokens": 12, "total_tokens": 21 } } ``` #### Streaming Response When stream: true is set, the server sends data in Server-Sent Events (SSE) format: ``` data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"llama3.2:1b","choices":[{"index":0,"delta":{"role":"assistant","content":"The"},"finish_reason":null}]} data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"llama3.2:1b","choices":[{"index":0,"delta":{"content":" capital"},"finish_reason":null}]} data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"llama3.2:1b","choices":[{"index":0,"delta":{"content":" of"},"finish_reason":null}]} data: [DONE] ``` ### Available Models Based on the example, the following model is available: * `llama3.2:1b` - Llama 3.2 1B parameter model Note: Contact the API provider for a complete list of available models. ### Error Handling The API returns standard HTTP status codes: * `200` - Success * `400` - Bad Request (invalid parameters) * `401` - Unauthorized (invalid API key) * `429` - Rate Limit Exceeded * `500` - Internal Server Error #### Example Error Response ``` { "error": { "message": "Invalid API key provided", "type": "invalid_request_error", "code": "invalid_api_key" } } ``` ### Rate Limits Rate limits may apply depending on your API plan. Check the response headers for rate limit info: * `X-RateLimit-Limit` - Max requests per time window * `X-RateLimit-Remaining` - Remaining requests in current window * `X-RateLimit-Reset` - Time when limit resets ### Best Practices 1. **Include System Messages**: Use them to define assistant behavior. 2. **Handle Streaming**: Implement proper error handling. 3. **Token Management**: Monitor usage. 4. **Conversation Context:** Maintain full message history. 5. **Error Handling:** Gracefully handle failures.