NAiOS IconNAiOS Logo
Contacto
Contacto

Suscríbete a la newsletter

Novedades de IA y de producto. Sin spam, puedes darte de baja cuando quieras.

Consejo: usa tu email de empresa para una respuesta más relevante.

Comprobando seguridad…
NAiOS Icon
NAiOS Logo

El primer integrador de IA para empresas reales. Conecta todas tus herramientas de IA de forma segura y escalable.

+34 695482054info@naios.netinfo@netretina.ai
LinkedInNAiOS AcademyNetretina.AiContact UsX

Plataforma

  • Características
  • Integraciones
  • Planes y precios

Empresa

  • Sobre nosotros
  • Blog
  • Contacto

Compliance

  • Reglamento Europeo de IA
  • Transparencia de IA

Legal

  • Aviso legal
  • Política de privacidad
  • Términos y condiciones
  • Política de cookies
  • Devoluciones

© 2026 NAiOS. Todos los derechos reservados.

Un producto de Netretina.Ai

    Volver al catálogo

    Langbase

    langbase

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

    AI AgentsDeveloper ToolsWeb del proveedor
    Acciones
    10
    Triggers
    0
    Autenticación
    —
    OAuth gestionado
    No
    Información técnica: el detalle de parámetros, schemas y triggers de esta página está pensado para equipos de integración. Si solo necesitas saber si tu herramienta favorita está disponible, basta con ver la lista de acciones.

    Acciones disponibles (10)

    Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.

    Split Content into ChunksLANGBASE_CHUNKER_SPLIT_CONTENTAcción

    Tool to split content into smaller chunks. use when processing large text segments to fit downstream limits.

    Parámetros de entrada

    • contentstringObligatorio

      The input text content to be chunked.

    • overlapinteger

      Number of characters to overlap between consecutive chunks. Must be ≥0.

    • chunk_sizeinteger

      Desired size of each chunk in characters. Must be ≥1 if provided.

    • chunker_typestringenum

      Mode for chunking. Use 'semantic' to preserve sentence boundaries; 'basic' for fixed-size splits.

      basicsemantic

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    Create ThreadLANGBASE_CREATE_THREADAcción

    Tool to create a new conversation thread. use when starting a fresh chat session or grouping messages into a distinct thread.

    Parámetros de entrada

    • messagesobject[]

      Optional initial messages for the thread

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    List Documents in MemoryLANGBASE_DOCUMENT_LISTAcción

    Tool to list documents in a specific memory. use when you need to fetch document metadata (and optionally vectors) from a memory after confirming its name. supports pagination via limit and startafter parameters.

    Parámetros de entrada

    • limitinteger

      Maximum number of documents to return

    • memoryNamestringObligatorio

      Name of the memory to list documents from

    • startAfterstring

      Pagination token to start after a specific document

    • includeVectorsboolean

      Whether to include vector embeddings in each document

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    Get Thread DetailsLANGBASE_GET_THREADAcción

    Tool to retrieve details of a specific conversation thread. use when you need the full thread details by its id after confirming its existence.

    Parámetros de entrada

    • threadIdstringObligatorio

      The unique identifier of the thread to retrieve

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    List Thread MessagesLANGBASE_LIST_THREAD_MESSAGESAcción

    Tool to list all messages in a conversation thread. use after obtaining the thread id to fetch its messages.

    Parámetros de entrada

    • limitinteger

      Number of messages to return per page.

    • beforestring

      Return messages created before this message ID.

    • threadIdstringObligatorio

      Unique identifier of the conversation thread.

    Parámetros de salida

    • dataobject[]Obligatorio

      Array of message objects.

    • errorstring

      Error if any occurred during the execution of the action

    • objectstringObligatorio

      Response object type, value is 'list'.

    • has_morebooleanObligatorio

      Whether there are more messages available.

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    Create MemoryLANGBASE_MEMORY_CREATEAcción

    Tool to create a new memory. use when storing a new memory record in langbase after confirming memory details.

    Parámetros de entrada

    • namestringObligatorio

      The name of the memory.

    • metadataobject

      Arbitrary metadata for the memory.

    • descriptionstring

      A description of the memory.

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    Delete MemoryLANGBASE_MEMORY_DELETEAcción

    Tool to delete a specific memory. use when you need to permanently remove a stored memory by its name.

    Parámetros de entrada

    • memory_namestringObligatorio

      Name of the memory to delete

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    List MemoriesLANGBASE_MEMORY_LISTAcción

    Tool to list all memory objects. use when you need to fetch stored memories for context retrieval.

    Parámetros de entrada

    • limitinteger

      Maximum number of memory objects to return

    • offsetinteger

      Number of memory objects to skip for pagination

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    Create a new pipeLANGBASE_PIPE_CREATEAcción

    Tool to create a new pipe. use after configuring pipe parameters. returns pipe details including api key and url.

    Parámetros de entrada

    • jsonboolean

      Enforce the output to be in JSON format

    • namestringObligatorio

      Name of the pipe

    • stopstring[]

      Up to 4 sequences where the API will stop generating further tokens

    • modelstring

      Pipe LLM model in format 'provider:model_id'

    • storeboolean

      If enabled, both prompt and completions will be stored

    • top_pnumber

      Nucleus sampling parameter between 0.0 and 1.0

    • statusstringenum

      Visibility status of the pipe

      publicprivate
    • streamboolean

      If enabled, the output will be streamed in real-time

    • upsertboolean

      Upsert pipe. If true, updates existing pipe with same name

    • moderateboolean

      If enabled, Langbase blocks flagged requests automatically

    • max_tokensinteger

      Maximum number of tokens in the response

    • descriptionstring

      Short description of the pipe

    • temperaturenumber

      Sampling temperature between 0.0 and 2.0

    • tool_choicestringenum

      Controls which (if any) tool is called by the model

      autorequiredobject
    • presence_penaltynumber

      Penalizes a word based on its occurrence in the input text

    • frequency_penaltynumber

      Penalizes a word based on how frequently it appears in the training data

    • parallel_tool_callsboolean

      If true, calls multiple tools in parallel

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not

    List all pipesLANGBASE_PIPE_LISTAcción

    Tool to list all pipes. use after authentication to retrieve the complete list of pipes.

    Parámetros de entrada

    Sin parámetros.

    Parámetros de salida

    • dataobjectObligatorio

      Data from the action execution

    • errorstring

      Error if any occurred during the execution of the action

    • successfulbooleanObligatorio

      Whether or not the action execution was successful or not