{
  "item": [
    {
      "id": "f1a0c1e0-1111-4aaa-8001-000000000001",
      "name": "Inference",
      "description": {
        "content": "Text completion and streaming generation endpoints.",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "f1a0c1e0-1111-4aaa-8001-000000000002",
          "name": "Generate a completion",
          "request": {
            "name": "Generate a completion",
            "description": {
              "content": "Generate a text completion from a base or tuned model. Supports a typed output schema via output_type for structured generation.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "completions"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"What is the capital of France?\",\n  \"model_name\": \"meta-llama/Llama-3.1-8B-Instruct\",\n  \"output_type\": null,\n  \"max_new_tokens\": 128\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8001-000000000003",
          "name": "Generate a streaming completion",
          "request": {
            "name": "Generate a streaming completion",
            "description": {
              "content": "Generate a completion as an incremental stream of token chunks for the provided prompt and model.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v3", "streaming_completions"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"Write a short poem about APIs.\",\n  \"model_name\": \"meta-llama/Llama-3.1-8B-Instruct\",\n  \"max_new_tokens\": 256\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        }
      ]
    },
    {
      "id": "f1a0c1e0-1111-4aaa-8002-000000000001",
      "name": "Fine-Tuning",
      "description": {
        "content": "Tuning and Memory Tuning job submission and management.",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "f1a0c1e0-1111-4aaa-8002-000000000002",
          "name": "Submit a tuning job",
          "request": {
            "name": "Submit a tuning job",
            "description": {
              "content": "Submit a fine-tuning or Memory Tuning job for a base model against an uploaded dataset. The train_type field selects the tuning method.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "train"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"model_name\": \"meta-llama/Llama-3.1-8B-Instruct\",\n  \"dataset_id\": \"your-dataset-id\",\n  \"train_type\": \"memory_rag\"\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8002-000000000003",
          "name": "List tuning jobs",
          "request": {
            "name": "List tuning jobs",
            "description": {
              "content": "List tuning jobs for the authenticated account.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "train", "jobs"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [{ "key": "Accept", "value": "application/json" }],
            "method": "GET"
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8002-000000000004",
          "name": "Get a tuning job",
          "request": {
            "name": "Get a tuning job",
            "description": {
              "content": "Retrieve the status and metadata of a single tuning job.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "train", "jobs", ":job_id"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": [{ "key": "job_id", "value": "123" }]
            },
            "header": [{ "key": "Accept", "value": "application/json" }],
            "method": "GET"
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8002-000000000005",
          "name": "Cancel a tuning job",
          "request": {
            "name": "Cancel a tuning job",
            "description": {
              "content": "Cancel a running tuning job by its job id.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "train", "jobs", ":job_id", "cancel"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": [{ "key": "job_id", "value": "123" }]
            },
            "header": [{ "key": "Accept", "value": "application/json" }],
            "method": "POST"
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8002-000000000006",
          "name": "Resume a tuning job",
          "request": {
            "name": "Resume a tuning job",
            "description": {
              "content": "Resume a previously paused or cancelled tuning job.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "train", "jobs", ":job_id", "resume"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": [{ "key": "job_id", "value": "123" }]
            },
            "header": [{ "key": "Accept", "value": "application/json" }],
            "method": "POST"
          },
          "response": []
        }
      ]
    },
    {
      "id": "f1a0c1e0-1111-4aaa-8003-000000000001",
      "name": "Classify",
      "description": {
        "content": "LLM classifier classification and prediction endpoints.",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "f1a0c1e0-1111-4aaa-8003-000000000002",
          "name": "Classify text",
          "request": {
            "name": "Classify text",
            "description": {
              "content": "Classify one or more text prompts with a trained classifier model, returning scored class labels.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "classifier", ":model_id", "classification"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": [{ "key": "model_id", "value": "your-model-id" }]
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"My order never arrived and I want a refund.\",\n  \"top_n\": 3\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        },
        {
          "id": "f1a0c1e0-1111-4aaa-8003-000000000003",
          "name": "Predict a class",
          "request": {
            "name": "Predict a class",
            "description": {
              "content": "Return the single predicted class for one or more text prompts using a trained classifier model.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "classifier", ":model_id", "prediction"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": [{ "key": "model_id", "value": "your-model-id" }]
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": \"My order never arrived and I want a refund.\"\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        }
      ]
    },
    {
      "id": "f1a0c1e0-1111-4aaa-8004-000000000001",
      "name": "Embeddings",
      "description": {
        "content": "Text embedding generation.",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "f1a0c1e0-1111-4aaa-8004-000000000002",
          "name": "Generate embeddings",
          "request": {
            "name": "Generate embeddings",
            "description": {
              "content": "Encode one or more text prompts into embedding vectors for similarity search, retrieval, and indexing.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "embedding"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [
              { "key": "Content-Type", "value": "application/json" },
              { "key": "Accept", "value": "application/json" }
            ],
            "method": "POST",
            "body": {
              "mode": "raw",
              "raw": "{\n  \"prompt\": [\"The quick brown fox.\", \"Lorem ipsum dolor sit amet.\"]\n}",
              "options": { "raw": { "language": "json" } }
            }
          },
          "response": []
        }
      ]
    },
    {
      "id": "f1a0c1e0-1111-4aaa-8005-000000000001",
      "name": "Platform",
      "description": {
        "content": "Version and platform metadata endpoints.",
        "type": "text/plain"
      },
      "item": [
        {
          "id": "f1a0c1e0-1111-4aaa-8005-000000000002",
          "name": "Get platform version",
          "request": {
            "name": "Get platform version",
            "description": {
              "content": "Return server and client version metadata and the list of available API endpoints and their versions.",
              "type": "text/plain"
            },
            "url": {
              "path": ["v1", "version"],
              "host": ["{{baseUrl}}"],
              "query": [],
              "variable": []
            },
            "header": [{ "key": "Accept", "value": "application/json" }],
            "method": "GET"
          },
          "response": []
        }
      ]
    }
  ],
  "event": [],
  "variable": [
    {
      "type": "string",
      "value": "https://api.lamini.ai",
      "key": "baseUrl"
    }
  ],
  "auth": {
    "type": "bearer",
    "bearer": [
      {
        "key": "token",
        "value": "{{bearerToken}}"
      }
    ]
  },
  "info": {
    "_postman_id": "a7f3c2d1-lam1-4ee0-9f00-c0ffee000001",
    "name": "Lamini Platform API",
    "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json",
    "description": {
      "content": "REST API for the Lamini enterprise LLM platform: inference (completions), fine-tuning and Memory Tuning jobs, classification, and embeddings over open base and tuned models. Authenticate with Authorization: Bearer <API_KEY>.\n\nContact Support:\n Name: Lamini Support\n URL: https://www.lamini.ai",
      "type": "text/plain"
    }
  }
}