Langbase

Pipe: Run v1

The Run API allows you to execute any pipe and receive its response. It supports all use cases of Pipes, including chat interactions, single generation tasks, and function calls.

Note

The /run API consolidates the functionality of the previously separate /generate and /chat endpoints, providing a unified interface. As a result, we will soon be deprecating both /generate and /chat in favor of /run.

The Run API supports:

  • Single generation requests for straightforward tasks.
  • Dynamic variables to create adaptable prompts in real-time.
  • Thread management for handling multi-turn conversations.
  • Seamless conversation continuation, ensuring smooth transitions across interactions.

If needed, Langbase can store messages and conversation threads, allowing for persistent conversation history for chat use cases.

POST/v1/pipes/run

Run a pipe

Run a pipe by sending the required data with the request. For basic request, send a messages array inside request body.

Headers

  • Name
    Content-Type
    Type
    string
    Required
    Required
    Description

    Request content type. Needs to be application/json

  • Name
    Authorization
    Type
    string
    Required
    Required
    Description

    Replace PIPE_API_KEY with your Pipe API key

Body Parameters

  • Name
    messages
    Type
    Array<Message>
    Required
    Required
    Description

    An array containing message objects.

    Message Object

    interface Message {
  role: string;
  content?: string | ContentType[] | null;
  tool_call_id?: string;
  name?: string;
}
    • Name
      role
      Type
      string
      Required
      Required
      Description

      The role of the message, i.e., system | user | assistant | tool

    • Name
      content
      Type
      string | ContentType[] | null
      Description

      The content of the message.

      1. String For text generation, it's a plain string.

      2. Null or undefined Tool call messages can have no content.

      3. ContentType[] Array used in vision and audio models, where content consists of structured parts (e.g., text, image URLs).

      ContentType Object

      interface ContentType {
 type: string;
 text?: string | undefined;
 image_url?:
   | {
       url: string;
       detail?: string | undefined;
     }
   | undefined;
};
    • Name
      tool_call_id
      Type
      string
      Description

      The id of the called LLM tool if the role is tool

    • Name
      name
      Type
      string
      Description

      The name of the called tool if the role is tool

  • Name
    variables
    Type
    array
    Description

    An array containing different variable objects

    Variable Object

    interface Variable {
  name: string;
  value: string;
}
    • Name
      name
      Type
      string
      Required
      Required
      Description

      The name of the variable

    • Name
      value
      Type
      string
      Required
      Required
      Description

      The value of the variable

  • Name
    threadId
    Type
    string
    Description

    The ID of an existing chat thread. The conversation will continue in this thread.

  • Name
    tools
    Type
    Array<Tools>
    Description

    A list of tools the model may call.

    Tools Object

    interface ToolsOptions {
  type: 'function';
  function: FunctionOptions
}
    • Name
      type
      Type
      'function'
      Description

      The type of the tool. Currently, only function is supported.

    • Name
      function
      Type
      FunctionOptions
      Description

      The function that the model may call.

      FunctionOptions Object

      export interface FunctionOptions {
  name: string;
  description?: string;
  parameters?: Record<string, unknown>
}
    • Name
      name
      Type
      string
      Description

      The name of the function to call.

    • Name
      description
      Type
      string
      Description

      The description of the function.

    • Name
      parameters
      Type
      Record<string, unknown>
      Description

      The parameters of the function.

Basic request without streaming

POST
/v1/pipes/run
import { Langbase } from 'langbase';

const langbase = new Langbase({
  apiKey: '<LANGBASE_API_KEY>' // User/Org API key
});

const response = await langbase.pipe.run({
  apiKey: '<PIPE-API-KEY>', // Replace with your pipe API key.
  messages: [
    {
      role: 'user',
      content: 'Who is an AI Engineer?'
    }
  ]
});

Response Headers

  • Name
    lb-thread-id
    Type
    string
    Description

    The ID of the new/existing thread. If you want to continue conversation in this thread, send it as threadId in the next request.

Learn how to use tool calling with this API.

Response Header

HTTP/2 200
lb-thread-id: "…-…-…-…-… ID of the thread"
… … … rest of the headers … : … … …

Response Body

Response of the endpoint is a Promise<RunResponse | RunResponseStream> object.

RunResponse Object

RunResponse Object

interface RunResponse {
  completion: string;
  raw: RawResponse;
}
  • Name
    completion
    Type
    string
    Description

    The generated text completion.

  • Name
    raw
    Type
    RawResponse
    Description

    The raw response object.

    RawResponse Object

    interface RawResponse {
  id: string;
  object: string;
  created: number;
  model: string;
  choices: ChoiceGenerate[];
  usage: Usage;
  system_fingerprint: string | null;
}
    • Name
      id
      Type
      string
      Description

      The ID of the raw response.

    • Name
      object
      Type
      string
      Description

      The object type name of the response.

    • Name
      created
      Type
      number
      Description

      The timestamp of the response creation.

    • Name
      model
      Type
      string
      Description

      The model used to generate the response.

    • Name
      choices
      Type
      ChoiceGenerate[]
      Description

      A list of chat completion choices. Can contain more than one elements if n is greater than 1.

      Choice Object for langbase.pipe.run() with stream off

      interface ChoiceGenerate {
  index: number;
  message: Message;
  logprobs: boolean | null;
  finish_reason: string;
}

    • Name
      usage
      Type
      Usage
      Description

      The usage object including the following properties.

      Usage Object

      interface Usage {
  prompt_tokens: number;
  completion_tokens: number;
  total_tokens: number;
}

    • Name
      system_fingerprint
      Type
      string
      Description

      This fingerprint represents the backend configuration that the model runs with.

RunResponseStream Object

Response of the endpoint with stream: true is a Promise<RunResponseStream>.

RunResponseStream Object

interface RunResponseStream {
  id: string;
  object: string;
  created: number;
  model: string;
  system_fingerprint: string | null;
  choices: ChoiceStream[];
}
  • Name
    id
    Type
    string
    Description

    The ID of the response.

  • Name
    object
    Type
    string
    Description

    The object type name of the response.

  • Name
    created
    Type
    number
    Description

    The timestamp of the response creation.

  • Name
    model
    Type
    string
    Description

    The model used to generate the response.

  • Name
    system_fingerprint
    Type
    string
    Description

    This fingerprint represents the backend configuration that the model runs with.

  • Name
    choices
    Type
    ChoiceStream[]
    Description

    A list of chat completion choices. Can contain more than one elements if n is greater than 1.

    Choice Object with stream true

    interface ChoiceStream {
  index: number;
  delta: Delta;
  logprobs: boolean | null;
  finish_reason: string;
}

RunResponse type

{
  "completion": "AI Engineer is a person who designs, builds, and maintains AI systems.",
  "raw": {
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1720131129,
    "model": "gpt-4o-mini",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "AI Engineer is a person who designs, builds, and maintains AI systems."
        },
        "logprobs": null,
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 28,
      "completion_tokens": 36,
      "total_tokens": 64
    },
    "system_fingerprint": "fp_123"
  }
}

RunResponseStream type with stream true

// A stream chunk looks like this …
{
  "id": "chatcmpl-123",
  "object": "chat.completion.chunk",
  "created": 1719848588,
  "model": "gpt-4o-mini",
  "system_fingerprint": "fp_44709d6fcb",
  "choices": [{
    "index": 0,
    "delta": { "content": "Hi" },
    "logprobs": null,
    "finish_reason": null
  }]
}

// More chunks as they come in...
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1719848588,"model":"gpt-4o-mini","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{"content":"there"},"logprobs":null,"finish_reason":null}]}
…
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1719848588,"model":"gpt-4o-mini","system_fingerprint":"fp_44709d6fcb","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}