- Resource: Conversation
- Methods
Resource: Conversation
External conversation proto definition.
| JSON representation | 
|---|
| { "name": string, "state": enum ( | 
| Fields | |
|---|---|
| name | 
 Immutable. Fully qualified name  | 
| state | 
 The state of the Conversation. | 
| userPseudoId | 
 A unique identifier for tracking users. | 
| messages[] | 
 Conversation messages. | 
| startTime | 
 Output only. The time the conversation started. Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples:  | 
| endTime | 
 Output only. The time the conversation finished. Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples:  | 
State
Enumeration of the state of the conversation.
| Enums | |
|---|---|
| STATE_UNSPECIFIED | Unknown. | 
| IN_PROGRESS | Conversation is currently open. | 
| COMPLETED | Conversation has been completed. | 
ConversationMessage
Defines a conversation message.
| JSON representation | 
|---|
| { "createTime": string, // Union field | 
| Fields | |
|---|---|
| createTime | 
 Output only. Message creation timestamp. Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples:  | 
| Union field  
 | |
| userInput | 
 User text input. | 
| reply | 
 Search reply. | 
TextInput
Defines text input.
| JSON representation | 
|---|
| {
  "input": string,
  "context": {
    object ( | 
| Fields | |
|---|---|
| input | 
 Text input. | 
| context | 
 Conversation context of the input. | 
ConversationContext
Defines context of the conversation
| JSON representation | 
|---|
| { "contextDocuments": [ string ], "activeDocument": string } | 
| Fields | |
|---|---|
| contextDocuments[] | 
 The current list of documents the user is seeing. It contains the document resource references. | 
| activeDocument | 
 The current active document the user opened. It contains the document resource reference. | 
Reply
Defines a reply message to user.
| JSON representation | 
|---|
| { "reply": string, "references": [ { object ( | 
| Fields | |
|---|---|
| reply | 
 DEPRECATED: use  | 
| references[] | 
 References in the reply. | 
| summary | 
 Summary based on search results. | 
Reference
Defines reference in reply.
| JSON representation | 
|---|
| { "uri": string, "anchorText": string, "start": integer, "end": integer } | 
| Fields | |
|---|---|
| uri | 
 URI link reference. | 
| anchorText | 
 Anchor text. | 
| start | 
 Anchor text start index. | 
| end | 
 Anchor text end index. | 
Summary
Summary of the top N search results specified by the summary spec.
| JSON representation | 
|---|
| { "summaryText": string, "summarySkippedReasons": [ enum ( | 
| Fields | |
|---|---|
| summaryText | 
 The summary content. | 
| summarySkippedReasons[] | 
 Additional summary-skipped reasons. This provides the reason for ignored cases. If nothing is skipped, this field is not set. | 
| safetyAttributes | 
 A collection of Safety Attribute categories and their associated confidence scores. | 
| summaryWithMetadata | 
 Summary with metadata information. | 
SummarySkippedReason
An Enum for summary-skipped reasons.
| Enums | |
|---|---|
| SUMMARY_SKIPPED_REASON_UNSPECIFIED | Default value. The summary skipped reason is not specified. | 
| ADVERSARIAL_QUERY_IGNORED | The adversarial query ignored case. Only used when  | 
| NON_SUMMARY_SEEKING_QUERY_IGNORED | The non-summary seeking query ignored case. Google skips the summary if the query is chit chat. Only used when  | 
| OUT_OF_DOMAIN_QUERY_IGNORED | The out-of-domain query ignored case. Google skips the summary if there are no high-relevance search results. For example, the data store contains facts about company A but the user query is asking questions about company B. | 
| POTENTIAL_POLICY_VIOLATION | The potential policy violation case. Google skips the summary if there is a potential policy violation detected. This includes content that may be violent or toxic. | 
| LLM_ADDON_NOT_ENABLED | The LLM addon not enabled case. Google skips the summary if the LLM addon is not enabled. | 
| NO_RELEVANT_CONTENT | The no relevant content case. Google skips the summary if there is no relevant content in the retrieved search results. | 
| JAIL_BREAKING_QUERY_IGNORED | The jail-breaking query ignored case. For example, "Reply in the tone of a competing company's CEO". Only used when [SearchRequest.ContentSearchSpec.SummarySpec.ignore_jail_breaking_query] is set to  | 
| CUSTOMER_POLICY_VIOLATION | The customer policy violation case. Google skips the summary if there is a customer policy violation detected. The policy is defined by the customer. | 
| NON_SUMMARY_SEEKING_QUERY_IGNORED_V2 | The non-answer seeking query ignored case. Google skips the summary if the query doesn't have clear intent. Only used when [SearchRequest.ContentSearchSpec.SummarySpec.ignore_non_answer_seeking_query] is set to  | 
| TIME_OUT | The time out case. Google skips the summary if the time out. | 
SafetyAttributes
Safety Attribute categories and their associated confidence scores.
| JSON representation | 
|---|
| { "categories": [ string ], "scores": [ number ] } | 
| Fields | |
|---|---|
| categories[] | 
 The display names of Safety Attribute categories associated with the generated content. Order matches the Scores. | 
| scores[] | 
 The confidence scores of the each category, higher value means higher confidence. Order matches the Categories. | 
SummaryWithMetadata
Summary with metadata information.
| JSON representation | 
|---|
| { "summary": string, "citationMetadata": { object ( | 
| Fields | |
|---|---|
| summary | 
 Summary text with no citation information. | 
| citationMetadata | 
 Citation metadata for given summary. | 
| references[] | 
 Document References. | 
| blobAttachments[] | 
 Output only. Store multimodal data for answer enhancement. | 
CitationMetadata
Citation metadata.
| JSON representation | 
|---|
| {
  "citations": [
    {
      object ( | 
| Fields | |
|---|---|
| citations[] | 
 Citations for segments. | 
Citation
Citation info for a segment.
| JSON representation | 
|---|
| {
  "startIndex": string,
  "endIndex": string,
  "sources": [
    {
      object ( | 
| Fields | |
|---|---|
| startIndex | 
 Index indicates the start of the segment, measured in bytes/unicode. | 
| endIndex | 
 End of the attributed segment, exclusive. | 
| sources[] | 
 Citation sources for the attributed segment. | 
CitationSource
Citation source.
| JSON representation | 
|---|
| { "referenceIndex": string } | 
| Fields | |
|---|---|
| referenceIndex | 
 Document reference index from SummaryWithMetadata.references. It is 0-indexed and the value will be zero if the referenceIndex is not set explicitly. | 
Reference
Document reference.
| JSON representation | 
|---|
| {
  "title": string,
  "document": string,
  "uri": string,
  "chunkContents": [
    {
      object ( | 
| Fields | |
|---|---|
| title | 
 Title of the document. | 
| document | 
 Required.  | 
| uri | 
 Cloud Storage or HTTP uri for the document. | 
| chunkContents[] | 
 List of cited chunk contents derived from document content. | 
ChunkContent
Chunk content.
| JSON representation | 
|---|
| { "content": string, "pageIdentifier": string, "blobAttachmentIndexes": [ string ] } | 
| Fields | |
|---|---|
| content | 
 Chunk textual content. | 
| pageIdentifier | 
 Page identifier. | 
| blobAttachmentIndexes[] | 
 Output only. Stores indexes of blobattachments linked to this chunk. | 
BlobAttachment
Stores binarydata attached to text answer, e.g. image, video, audio, etc.
| JSON representation | 
|---|
| { "data": { object ( | 
| Fields | |
|---|---|
| data | 
 Output only. The blob data. | 
| attributionType | 
 Output only. The attribution type of the blob. | 
Blob
Stores type and data of the blob.
| JSON representation | 
|---|
| { "mimeType": string, "data": string } | 
| Fields | |
|---|---|
| mimeType | 
 Output only. The media type (MIME type) of the generated data. | 
| data | 
 Output only. Raw bytes. A base64-encoded string. | 
AttributionType
Defines the attribution type of the blob.
| Enums | |
|---|---|
| ATTRIBUTION_TYPE_UNSPECIFIED | Unspecified attribution type. | 
| CORPUS | The attachment data is from the corpus. | 
| GENERATED | The attachment data is generated by the model through code generation. | 
| Methods | |
|---|---|
| 
 | Converses a conversation. | 
| 
 | Creates a Conversation. | 
| 
 | Deletes a Conversation. | 
| 
 | Gets a Conversation. | 
| 
 | Lists all Conversations by their parent DataStore. | 
| 
 | Updates a Conversation. |