Pipe API: Create beta

The create pipe API endpoint allows you to create a new pipe on Langbase dynamically with API. You can use this endpoint to create a new pipe with all the custom configuration. This endpoint requires a User or Org API key. To generate a User or Org API key visit your profile/organization settings page on Langbase.

Deprecation Notice

This API endpoint has been deprecated. Please use the new create pipe API endpoint.

Generate a User/Org API key

You will need to generate an API key to authenticate your requests. For more information, visit the User/Org API key documentation.

Deprecated/beta/org/{org}/pipes

Create a new org pipe

Create a new organization pipe by sending the pipe configuration inside the request body.

Required headers

Name
Content-Type
Type
string
Description
Request content type. Needs to be application/json.
Name
Authorization
Type
string
Description
Replace YOUR_API_KEY with your Organization API key.

Required path parameters

Name
org
Type
string
Description
The organization name.
Replace {org} with your organization name.

Required attributes

Name
name
Type
string
Description
Name of the pipe.

Optional attributes

Name
description
Type
array
Description
Short description of the pipe.
Default: ''
Name
status
Type
string
Description
Status of the pipe.
Default: public
Can be one of: public, private
Name
type
Type
string
Description
Type of the pipe.
Default: generate
Can be one of: generate, chat
Name
config
Type
object
Description
Configuration object of the pipe.
Default: {}
Name
config.meta.stream
Type
boolean
Description
If enabled, the output will be streamed in real-time like ChatGPT. This is helpful if user is directly reading the text.
Default: true
Name
config.meta.json
Type
boolean
Description
Enforce the output to be in JSON format.
Default: false
Name
config.meta.store
Type
boolean
Description
If enabled, both prompt and completions will be stored in the database. Otherwise, only system prompt and few shot messages will be saved.
Default: true
Name
config.meta.moderate
Type
boolean
Description
If enabled, Langbase blocks flagged requests automatically.
Default: false
Name
config.model.name
Type
string
Description
ID of the LLM model. You can copy the ID of a model from the list of supported LLM models at Langbase.
Default: gpt-4o-mini
Name
config.model.provider
Type
string
Description
Name of the LLM model provider. Check out the list of all the supported LLM providers at Langbase.
Default: OpenAI
Can be one of the supported providers: OpenAI, Together, Anthropic, Groq, Google, Cohere.
Name
config.model.tool_choice
Type
'auto' | 'required' | 'object'
Description
Controls which (if any) tool is called by the model.
- auto - the model can pick between generating a message or calling one or more tools.
- required - the model must call one or more tools.
- object - Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Default: auto
Name
config.model.parallel_tool_calls
Type
boolean
Description
Call multiple tools in parallel, allowing the effects and results of these function calls to be resolved in parallel.
Default: true
Name
config.model.params.top_p
Type
number
Description
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Default: 1
Name
config.model.params.max_tokens
Type
number
Description
Maximum number of tokens in the response message returned.
Default: 1000
Name
config.model.params.temperature
Type
number
Description
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random. Lower values like 0.2 will make it more focused and deterministic.
Default: 0.7
Name
config.model.params.presence_penalty
Type
number
Description
Penalizes a word based on its occurrence in the input text.
Default: 1
Name
config.model.params.frequency_penalty
Type
number
Description
Penalizes a word based on how frequently it appears in the training data.
Default: 1
Name
config.model.params.stop
Type
array
Description
Up to 4 sequences where the API will stop generating further tokens.
Default: []
Name
config.prompt.system
Type
string
Description
System prompt. Insert variables in the prompt with syntax like .
Default: You're a helpful AI assistant.
Name
config.prompt.opening
Type
string
Description
Chat opening prompt.
Default: Welcome to Langbase. Prompt away!
Name
config.prompt.safety
Type
string
Description
AI Safety prompt.
Default: ''
Name
config.prompt.messages
Type
array
Description
An array containing message objects.
Default: []
Name
config.prompt.variables
Type
array
Description
An array containing different variable objects.
Default: []
Name
config.prompt.json
Type
string
Description
Use this prompt to define the JSON output format, schema, and more. It will be appended to the system prompt.
Default: ''
Name
config.prompt.rag
Type
string
Description
Use this prompt to make the LLM answer questions from Memoryset documents.
Default: ''
Name
config.tools
Type
array
Description
An array of objects with valid tool definitions.
Read more about valid tool definition
Default: []
Name
config.memorysets
Type
array
Description
An array of memoryset names.
Default: []

Basic Pipe

POST

/beta/org/{org}/pipes

curl https://api.langbase.com/beta/org/{org}/pipes \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-d '{
  "name": "Test Pipe",
  "description": "This is a test pipe",
  "status": "public",
  "type": "chat"
}'

Response

{
  "name": "test-pipe",
  "type": "chat",
  "description": "This is a create Pipe test from API",
  "status": "private",
  "api_key": "pipe_4FVBn2DgrzfJf...",
  "owner_login": "langbase",
  "url": "https://langbase.com/langbase/test-pipe"
}

Deprecated/beta/user/pipes

Create a new user pipe

Create a new user pipe by sending the pipe configuration inside the request body.