{
  "opencollection": "1.0.0",
  "info": {
    "name": "Predibase Adapters Inference API",
    "version": "2.0"
  },
  "request": {
    "auth": {
      "type": "bearer",
      "token": "{{bearerToken}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Inference",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "OpenAI-compatible chat completion.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{model}/v1/chat/completions",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Creates a chat completion against the deployment named in the server URL. OpenAI Chat Completions v1 compatible. Set model to an adapter ID (\"repo\"/\"version\") to serve a fine-tuned LoRA on top of the base model, or leave it empty to use the base model. Set stream to true to receive Server-Sent Events."
        },
        {
          "info": {
            "name": "OpenAI-compatible text completion.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{model}/v1/completions",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Creates a text completion against the deployment named in the server URL. OpenAI Completions v1 compatible. Set model to an adapter ID to serve a fine-tuned LoRA."
        },
        {
          "info": {
            "name": "Native text generation.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{model}/generate",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Generates text from a deployed model. The full URL is https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{deployment}/generate. Optionally specify a LoRA adapter via parameters.adapter_id and parameters.adapter_source (pbase, hub, or s3)."
        },
        {
          "info": {
            "name": "Native streaming text generation.",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{model}/generate_stream",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Streams generated tokens from a deployed model as Server-Sent Events. The full URL is https://serving.app.predibase.com/{tenant}/deployments/v2/llms/{deployment}/generate_stream."
        }
      ]
    }
  ],
  "bundled": true
}