Docs
Configuration
librechat.yaml
Object Structure
Assistants Endpoint

Assistants Endpoint Object Structure

This page applies to both the assistants and azureAssistants endpoints.

Note: To enable azureAssistants, see the Azure OpenAI Configuration for more information.

Example

Assistants Endpoint
endpoints:
  # azureAssistants: # <-- Azure-specific configuration has the same structure as `assistants`
    #  pollIntervalMs: 500
    #  timeoutMs: 10000
 
  assistants:
    disableBuilder: false
    # Use either `supportedIds` or `excludedIds` but not both
    supportedIds: ["asst_supportedAssistantId1", "asst_supportedAssistantId2"]
    # excludedIds: ["asst_excludedAssistantId"]
    # `privateAssistants` do not work with `supportedIds` or `excludedIds`
    # privateAssistants: false
    # (optional) Models that support retrieval, will default to latest known OpenAI models that support the feature
    # retrievalModels: ["gpt-4-turbo-preview"]
    # (optional) Assistant Capabilities available to all users. Omit the ones you wish to exclude. Defaults to list below.
    # capabilities: ["code_interpreter", "retrieval", "actions", "tools", "image_vision"]

This configuration enables the builder interface for assistants, sets a polling interval of 500ms to check for run updates, and establishes a timeout of 10 seconds for assistant run operations.

disableBuilder

Key:

KeyTypeDescriptionExample
disableBuilderBooleanControls the visibility and use of the builder interface for assistants.When set to `true`, disables the builder interface for the assistant, limiting direct manual interaction.

Default: false

Example:

endpoints / assistants / disableBuilder
disableBuilder: false

pollIntervalMs

Key:

KeyTypeDescriptionExample
pollIntervalMsIntegerSpecifies the polling interval in milliseconds for checking run updates or changes in assistant run states.Specifies the polling interval in milliseconds for checking assistant run updates.

Default: 2000

Example:

endpoints / assistants / pollIntervalMs
pollIntervalMs: 2500

Note: Currently, this is only used by Azure Assistants. Higher values are recommended for Azure Assistants to avoid rate limiting errors.

timeoutMs

Key:

KeyTypeDescriptionExample
timeoutMsIntegerDefines the maximum time in milliseconds that an assistant can run before the request is cancelled.Sets a timeout in milliseconds for assistant runs. Helps manage system load by limiting total run operation time.

Default: 180000

Example:

endpoints / assistants / timeoutMs
timeoutMs: 10000

Note: Defaults to 3 minutes (180,000 ms). Run operation times can range between 50 seconds to 2 minutes but also exceed this. If the timeoutMs value is exceeded, the run will be cancelled.

supportedIds

Key:

KeyTypeDescriptionExample
supportedIdsArray/List of StringsList of supported assistant IdsUse this or `excludedIds` but not both (the `excludedIds` field will be ignored if so).

Example:

endpoints / assistants / supportedIds
supportedIds:
  - "asst_supportedAssistantId1"
  - "asst_supportedAssistantId2"

excludedIds

Key:

KeyTypeDescriptionExample
excludedIdsArray/List of StringsList of excluded assistant IdsUse this or `supportedIds` but not both (the `excludedIds` field will be ignored if so).

Example:

endpoints / assistants / excludedIds
excludedIds:
  - "asst_excludedAssistantId1"
  - "asst_excludedAssistantId2"

privateAssistants

Key:

KeyTypeDescriptionExample
privateAssistantsBooleanControls whether assistants are private to the user that created themDoes not work with `supportedIds` or `excludedIds` (`supportedIds` and `excludedIds` will be ignored).

Default: false

Example:

endpoints / assistants / privateAssistants
privateAssistants: false

retrievalModels

Key:

KeyTypeDescriptionExample
retrievalModelsArray/List of StringsSpecifies the models that support retrieval for the assistants endpoint.Defines the models that support retrieval capabilities for the assistants endpoint. By default, it uses the latest known OpenAI models that support the official Retrieval feature.

Default: [] (uses the latest known OpenAI models that support retrieval)

Example:

endpoints / assistants / retrievalModels
retrievalModels:
  - "gpt-4-turbo-preview"

capabilities

Key:

KeyTypeDescriptionExample
capabilitiesArray/List of StringsSpecifies the assistant capabilities available to all users for the assistants endpoint.Defines the assistant capabilities that are available to all users for the assistants endpoint. You can omit the capabilities you wish to exclude from the list.

Default: ["code_interpreter", "image_vision", "retrieval", "actions", "tools"]

Example:

endpoints / assistants / capabilities
capabilities:
  - "code_interpreter"
  - "retrieval"
  - "actions"
  - "tools"
  - "image_vision"

Note: This field is optional. If omitted, the default behavior is to include all the capabilities listed in the example.