💬Language Models

Available language models provided by SYNAPSE

List Language Models

GET /llm/list

Provides a JSON array of currently available language models

Headers

Name	Value
Content-Type	application/json

Response

200

[
  "mixtral-8x7b",
  "mistral-7b",
  "dolphin-2.6-mixtral-8x7b",
  "nous-mixtral-8x7b",
  "llama-2-70b",
  "llama-2-13b",
  "llama-2-7b",
  "codellama-70b",
  "codellama-34b",
  "airoboros",
  "airoboros-l2-70b-gpt4",
  "pygmalion-13b-4bit-128g",
  "lzlv-70b",
  "gemma-7b-it",
  "llava-1.5-7b",
  "gpt-3.5-turbo",
  "gpt-3.5-turbo-16k",
  "gpt-4",
  "gpt-4-turbo",
  "gemini-pro"
]

400

{
  "error": "Endpoint Unavailable"
}

Using a LLM

POST /llm/:model

Calls a model for a response

Headers

Name	Value
Content-Type	application/json
Authorization	Bearer <token>

Body

Name	Type	Description	Default
messages	message[]	Name of the user	none
temperature	number	LLM Temperature	0.7
max_tokens	number	Max response tokens	1024

Response

200

{
  "answer": "Hello! How may I assist you?"
}

400

{
  "error": "Invalid request"
}

500

{
  "error": "Error during generation (LLM)"
}

Example

example.js

const res = await fetch('https://synapselabs.onrender.com/llm/mistral-7b', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer <your_api_key>'
  },
  body: JSON.stringify({
    messages: [{
      "role": "user",
      "content": "Tell me a random fact!"
    }],
  }),
});

const data = await res.json();
console.log(data) // {"answer":"Did you know..."}