> For a complete documentation index, fetch https://docs.voximplant.ai/llms.txt

# Vendor

## Enums

* [Role](/api-reference/voxengine/ccai/vendor/role) — Enumeration of the roles a participant can play in a conversation.

## Types

### ConversationProfile

Defines the services to connect to the incoming Dialogflow conversations.

*optional*

Optional. A human-readable name for this profile. Max length is **1024 bytes**.

The unique identifier of this conversation profile. Format: projects/\<Project ID>/conversationProfiles/\<Conversation Profile ID>.

### EventInput

Events allow matching intents by event name instead of the natural language input. For instance, the  input can trigger a personalized welcome response. The parameter `name` may be used by the agent in the response: `"Hello #welcome_event.name! What can I do for you today?"`.

The language of this query. See [Language Support](https://cloud.google.com/dialogflow/docs/reference/language) for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to have the same language.

The unique identifier of the event.

*optional*

The collection of parameters associated with the event.
Depending on your protocol or client library language, this is a map, associative array, symbol table, dictionary, or JSON object composed of a collection of (MapKey, MapValue) pairs:

* MapKey type: string
* MapKey value: parameter name
* MapValue type:
* If parameter's entity type is a composite entity: map
* Else: string or number, depending on the parameter value type
* MapValue value:
* If parameter's entity type is a composite entity: map from composite entity property names to property values
* Else: parameter value

### Participant

Represents a single side of the conversation.

*optional*

Optional. Key-value filters on the metadata of documents returned by article suggestion. If specified, article suggestion only returns suggested documents that match all filters in their **Document.metadata**. Multiple values for a metadata key should be concatenated by a comma. For example, filters to match all documents that have 'US' or 'CA' in their market metadata values and 'agent' in their user metadata values are documents\_metadata\_filters \{ key: "market" value: "US,CA" } documents\_metadata\_filters \{ key: "user" value: "agent" }.

*optional*

Optional. The unique identifier of this participant. Format: `projects/<Project ID>/conversations/<Conversation ID>/participants/<Participant ID>`.

*optional*

Optional. Obfuscated user id that should be associated with the created participant.
You can specify a user id as follows:

* If you set this field in `CreateParticipantRequest` or `UpdateParticipantRequest`, Dialogflow adds the obfuscated user id with the participant.
* If you set this field in `AnalyzeContent` or `StreamingAnalyzeContent`, Dialogflow updates `Participant.obfuscated_external_user_id`.
  Dialogflow returns an error if you try to add a user id for a non-`END_USER` participant.
  Dialogflow uses this user id for billing and measurement purposes. For example, Dialogflow determines whether a user in one conversation returned in a later conversation.
  NOTE:
* Never pass raw user ids to Dialogflow. Always obfuscate your user id first.
* Dialogflow only accepts a UTF-8 encoded string, e.g., a hex digest of a hash function like SHA-512.
* The length of the user id must be \<= 256 characters.

Immutable. The role this participant plays in the conversation. This field can only be set during creation.

*optional*

Optional. Label applied to streams representing this participant in SIPREC XML metadata and SDP. Use it to assign transcriptions from that media stream to this participant. This field can be updated.

### TextInput

Represents a natural language text to be processed.

Whether to split the text into single sentence text entries at serving time. This provides a way for a user to input email content as text input.

The language of this conversational query. See [Language Support](https://cloud.google.com/dialogflow/docs/reference/language) for a list of the currently supported language codes. Note that queries in the same session do not necessarily need to have the same language.

The UTF-8 encoded natural language text to be processed. Text length must not exceed **256 characters**.