> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Langbase

> Langbase is a serverless AI developer platform that enables developers to build, collaborate, and deploy AI agents and applications with composable AI infrastructure.

![Langbase logo](https://mintcdn.com/composio-preview/tIuAovF9-7pXq2wA/images/toolkits/langbase.svg?fit=max\&auto=format\&n=tIuAovF9-7pXq2wA\&q=85\&s=afaccd1267f2527ceb37a55fb7ef565c)

* **Category:** ai agents
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 20
* **Triggers:** 0
* **Slug:** `LANGBASE`
* **Version:** 20261101\_00

## Tools

> [accordion] Append Thread Messages
>
> **Slug:** `LANGBASE_APPEND_THREAD_MESSAGES`
>
> Tool to add new messages to an existing conversation thread. Use when continuing a chat session or adding context to a thread.
>
> #### Input Parameters
>
> **messages** `array` *required*
>
> Array of one or more messages to append to the thread. Each message must have at minimum a 'role' field.
>
> **threadId** `string` *required*
>
> Unique identifier of the thread to append messages to.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Check API Health
>
> **Slug:** `LANGBASE_CHECK_HEALTH`
>
> Tool to check the health status of the Langbase API service. Use when you need to verify API availability.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Split Content into Chunks
>
> **Slug:** `LANGBASE_CHUNKER_SPLIT_CONTENT`
>
> Tool to split content into smaller chunks. Use when processing large text segments to fit downstream limits.
>
> #### Input Parameters
>
> **content** `string` *required*
>
> The input text content to be chunked.
>
> **overlap** `integer`
>
> Number of characters to overlap between consecutive chunks. Must be ≥256 and \< chunk\_size.
>
> **chunk\_size** `integer`
>
> Desired size of each chunk in characters. Must be between 1024 and 30000. Default: 1024.
>
> **chunker\_type** `string ("basic" | "semantic")`
>
> Mode for chunking. Use 'semantic' to preserve sentence boundaries; 'basic' for fixed-size splits.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Thread
>
> **Slug:** `LANGBASE_CREATE_THREAD`
>
> Tool to create a new conversation thread. Use when starting a fresh chat session or grouping messages into a distinct thread.
>
> #### Input Parameters
>
> **messages** `array`
>
> Optional initial messages for the thread
>
> **metadata** `object`
>
> Key-value pairs to store with the thread for organizational purposes
>
> **threadId** `string`
>
> Custom thread identifier. If not provided, a unique ID will be generated.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Thread
>
> **Slug:** `LANGBASE_DELETE_THREAD`
>
> Tool to delete a thread that is no longer needed to manage conversation history. Use when you need to permanently remove a thread by its ID.
>
> #### Input Parameters
>
> **threadId** `string` *required*
>
> The unique identifier of the thread to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Thread Message
>
> **Slug:** `LANGBASE_DELETE_THREAD_MESSAGE`
>
> Tool to delete a specific message from a conversation thread. Use when you need to remove a message from a thread by its ID.
>
> #### Input Parameters
>
> **threadId** `string` *required*
>
> The unique identifier of the thread containing the message
>
> **messageId** `string` *required*
>
> The unique identifier of the message to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Documents in Memory
>
> **Slug:** `LANGBASE_DOCUMENT_LIST`
>
> List document metadata in a specific Langbase memory. The request can include limit and startAfter parameters.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of documents to return
>
> **memoryName** `string` *required*
>
> Name of the memory to list documents from
>
> **startAfter** `string`
>
> Pagination token to start after a specific document
>
> **includeVectors** `boolean`
>
> Whether to include vector embeddings in each document
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Pipe Details
>
> **Slug:** `LANGBASE_GET_PIPE`
>
> Tool to retrieve details of a specific pipe by owner and name. Use when you need to fetch configuration and settings of a particular pipe.
>
> #### Input Parameters
>
> **pipe\_name** `string` *required*
>
> The name of the pipe to retrieve
>
> **owner\_login** `string` *required*
>
> The login/username of the pipe owner
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Thread Details
>
> **Slug:** `LANGBASE_GET_THREAD`
>
> Tool to retrieve details of a specific conversation thread. Use when you need the full thread details by its ID after confirming its existence.
>
> #### Input Parameters
>
> **threadId** `string` *required*
>
> The unique identifier of the thread to retrieve
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Available Models
>
> **Slug:** `LANGBASE_LIST_MODELS`
>
> Tool to get available AI models supported by Langbase. Use to discover text and image generation models from various providers.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Thread Messages
>
> **Slug:** `LANGBASE_LIST_THREAD_MESSAGES`
>
> List messages in a Langbase conversation thread by thread ID to review its conversation history. You can optionally request a page using a limit and a before-message cursor; messages are returned in chronological order.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Number of messages to return per page.
>
> **before** `string`
>
> Return messages created before this message ID.
>
> **threadId** `string` *required*
>
> Unique identifier of the conversation thread.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Execution Traces
>
> **Slug:** `LANGBASE_LIST_TRACES`
>
> Tool to get execution traces for debugging and monitoring pipe runs. Use when you need to retrieve trace logs for a specific primitive.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of traces to return
>
> **order** `string ("asc" | "desc")`
>
> Order for trace results
>
> **offset** `integer`
>
> Number of traces to skip for pagination
>
> **primitiveId** `string` *required*
>
> ID of the primitive (pipe) to get traces for
>
> **primitiveName** `string` *required*
>
> Name of the primitive (pipe) to get traces for
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Memory
>
> **Slug:** `LANGBASE_MEMORY_CREATE`
>
> Tool to create a new memory. Use when storing a new memory record in Langbase after confirming memory details.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name (identifier) of the memory.
>
> **top\_k** `integer`
>
> Number of chunks to return. Default 10, range 1-100.
>
> **chunk\_size** `integer`
>
> Maximum number of characters in a single chunk. Default 10000, min 1024, max 30000.
>
> **description** `string`
>
> A short description of the memory.
>
> **chunk\_overlap** `integer`
>
> Number of characters to overlap between chunks. Default 2048, min 256, must be less than chunk\_size.
>
> **embedding\_model** `string`
>
> The embedding model to use. Supported: 'openai:text-embedding-3-large', 'cohere:embed-v4.0', 'cohere:embed-multilingual-v3.0', 'cohere:embed-multilingual-light-v3.0', 'google:text-embedding-004'. Defaults to 'openai:text-embedding-3-large'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Memory
>
> **Slug:** `LANGBASE_MEMORY_DELETE`
>
> Tool to delete a specific memory. Use when you need to permanently remove a stored memory by its name.
>
> #### Input Parameters
>
> **memory\_name** `string` *required*
>
> Name of the memory to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Memories
>
> **Slug:** `LANGBASE_MEMORY_LIST`
>
> Tool to list all memory objects. Use when you need to fetch stored memories for context retrieval.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create a new pipe
>
> **Slug:** `LANGBASE_PIPE_CREATE`
>
> Create a Langbase pipe with configurable settings, or update an existing pipe with the same name when upsert is enabled. Returns a pipe object including its API key and URL.
>
> #### Input Parameters
>
> **json** `boolean`
>
> Enforce the output to be in JSON format
>
> **name** `string` *required*
>
> Name of the pipe
>
> **stop** `array`
>
> Up to 4 sequences where the API will stop generating further tokens
>
> **model** `string`
>
> Pipe LLM model in format 'provider:model\_id'
>
> **store** `boolean`
>
> If enabled, both prompt and completions will be stored
>
> **top\_p** `number`
>
> Nucleus sampling parameter between 0.0 and 1.0
>
> **status** `string ("public" | "private")`
>
> Visibility status of the pipe
>
> **stream** `boolean`
>
> If enabled, the output will be streamed in real-time
>
> **upsert** `boolean`
>
> Upsert pipe. If true, updates existing pipe with same name
>
> **moderate** `boolean`
>
> If enabled, Langbase blocks flagged requests automatically
>
> **max\_tokens** `integer`
>
> Maximum number of tokens in the response
>
> **description** `string`
>
> Short description of the pipe
>
> **temperature** `number`
>
> Sampling temperature between 0.0 and 2.0
>
> **tool\_choice** `string ("auto" | "required")`
>
> Controls which (if any) tool is called by the model
>
> **presence\_penalty** `number`
>
> Penalizes a word based on its occurrence in the input text
>
> **frequency\_penalty** `number`
>
> Penalizes a word based on how frequently it appears in the training data
>
> **parallel\_tool\_calls** `boolean`
>
> If true, calls multiple tools in parallel
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List all pipes
>
> **Slug:** `LANGBASE_PIPE_LIST`
>
> List pipes in the authenticated Langbase account, returning pipe objects in a pipes collection.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update an existing pipe
>
> **Slug:** `LANGBASE_UPDATE_PIPE`
>
> Tool to update an existing pipe's configuration on Langbase. Use when modifying model settings, parameters, prompts, tools, or memory. The pipe must already exist.
>
> #### Input Parameters
>
> **json** `boolean`
>
> Enforce the output to be in JSON format
>
> **name** `string`
>
> New name for the pipe
>
> **stop** `array`
>
> Up to 4 sequences where the API will stop generating further tokens
>
> **model** `string`
>
> Pipe LLM model in format 'provider:model\_id'
>
> **store** `boolean`
>
> If enabled, both prompt and completions will be stored
>
> **tools** `array`
>
> List of tools to make available to the pipe
>
> **top\_p** `number`
>
> Nucleus sampling parameter between 0.0 and 1.0
>
> **memory** `array`
>
> List of memory objects to attach to the pipe
>
> **status** `string ("public" | "private")`
>
> Visibility status of the pipe
>
> **stream** `boolean`
>
> If enabled, the output will be streamed in real-time
>
> **messages** `array`
>
> List of messages to configure the pipe's prompts
>
> **moderate** `boolean`
>
> If enabled, Langbase blocks flagged requests automatically
>
> **pipe\_name** `string` *required*
>
> Name of the pipe to update
>
> **variables** `string`
>
> Variables for the pipe, can be an array or object
>
> **max\_tokens** `integer`
>
> Maximum number of tokens in the response
>
> **description** `string`
>
> Short description of the pipe
>
> **temperature** `number`
>
> Sampling temperature between 0.0 and 2.0
>
> **tool\_choice** `string`
>
> Controls which (if any) tool is called by the model. Can be a string like 'auto' or 'required', or a structured ToolChoice object
>
> **presence\_penalty** `number`
>
> Penalizes a word based on its occurrence in the input text
>
> **regenerateApiKey** `boolean`
>
> If true, regenerates the API key for this pipe
>
> **frequency\_penalty** `number`
>
> Penalizes a word based on how frequently it appears in the training data
>
> **parallel\_tool\_calls** `boolean`
>
> If true, calls multiple tools in parallel
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Thread Metadata
>
> **Slug:** `LANGBASE_UPDATE_THREAD`
>
> Tool to update an existing thread's metadata. Use when you need to modify metadata fields for managing and organizing conversation threads.
>
> #### Input Parameters
>
> **metadata** `object`
>
> Key-value pairs to store with the thread for organizational purposes. Each value must be a string with max length of 2048 characters.
>
> **threadId** `string` *required*
>
> The unique identifier of the thread to update
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Thread Message
>
> **Slug:** `LANGBASE_UPDATE_THREAD_MESSAGE`
>
> Tool to update an existing message in a conversation thread. Use when you need to modify the content or metadata of a specific message.
>
> #### Input Parameters
>
> **content** `string`
>
> Updated text content of the message
>
> **metadata** `object`
>
> Key-value pairs to store with the message. Each value must be a string with max length of 2048 characters.
>
> **threadId** `string` *required*
>
> Unique identifier of the thread containing the message
>
> **messageId** `string` *required*
>
> Unique identifier of the message to update
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
