Ai platforms

This event will be published when conversations have been received from the LLM provider.

Payload

object

id string

Required

Identifies the event.

minLength = 1
time string

Timestamp of when the occurrence happened. Must adhere to RFC 3339.

minLength = 1, format = "date-time"
type string

Required

Unique identifier for the event type.

default = "com.qlik.core.ai-platform.conversations-job.finished"
source string

Required

Identifies the context in which an event happened.

minLength = 1, format = "uri-reference"
specversion string

Required

The version of the CloudEvents specification which the event uses.

minLength = 1
datacontenttype string

Content type of the data value. Must adhere to RFC 2046 format.

minLength = 1, default = "application/json"
host string

Unique identifier for the host related to the event.
reason string

Reason associated with the occurrence, when applicable.
userid string

Unique identifier for the user related to the event.
ownerid string

Unique identifier for the owner related to the event.
spaceid string

Unique identifier for the space related to the event.
authtype string

Representing the type of principal that triggered the occurrence.
clientid string

Unique identifier for the client related to the event.
tenantid string

Required

Unique identifier for the tenant related to the event.
sessionid string

Unique identifier for the session related to the event.
authclaims string

A JSON string representing the impersonating entity (the JWT "act" claim), if any.
tracestate string

A comma-delimited list of key-value pairs.
traceparent string

Contains a version, trace ID, span ID, and trace options.
toplevelresourceid string

If the event originated from a sub resource the toplevelresourceid MUST contain the id of the top level resource associated with the sub resource. If the event originated from a top level resource it MUST NOT be defined.
data object

Conversations finished event specific data.
Show data properties
- id string
  
  Required
  
  A unique identifier for the completion.
- cost object
  
  Estimated token cost in USD. When per-token pricing is configured for the model, the object contains input, output, and total cost values. When pricing is not configured for the model, this property is omitted entirely. Prompt-cache token pricing is not included.
  
  Show cost properties
  
  inputCost string
  
  Cost of prompt/input tokens in USD.
  
  totalCost string
  
  Sum of inputCost and outputCost.
  
  outputCost string
  
  Cost of completion/output tokens in USD.
- _meta object
  
  Internal metadata associated with the request.
  
  Show _meta properties
  
  act object
  
  Details of the impersonating entity.
  
  Show act properties
  
  iss string
  
  Issuer of the impersonating entity's identity.
  
  sub string
  
  Subject of the impersonating entity.
  
  subType string
  
  Type of the impersonating entity's subject.
  
  aud array of strings
  
  Audience(s) the JWT was issued for.
  
  iss string
  
  Issuer of the principal's identity.
  
  sid string
  
  ID of the session associated with this JWT, if any.
  
  sub string
  
  Subject of the principal's identity.
  
  level string
  
  Access level of the principal.
  
  userId string
  
  Internal ID of the user making the request. Present when subType is "user".
  
  subType string
  
  Type of the principal's subject.
  
  clientId string
  
  ID of the client making the request.
  
  tenantId string
  
  Internal ID of the tenant to restrict access to.
  
  licenseId string
  
  License ID associated with the principal.
  
  parentLicenseId string
  
  Parent license ID associated with the principal.
- jobId string
  
  Optional RFS job ID forwarded from the X-Qlik-RFS-JobID request header to correlate triggered and finished events.
- model string
  
  The model used for conversation.
- usage object
  
  Token usage for a conversations response, including optional prompt-cache token counts.
  
  Show usage properties
  
  totalTokens integer
  
  Required
  
  Addition of the completion and prompt tokens.
  
  promptTokens integer
  
  Required
  
  Tokens explicitly provided as input to the model.
  
  completionTokens integer
  
  Required
  
  Tokens generated by the model in response to the input.
  
  cacheReadInputTokens integer
  
  Tokens read from the prompt cache.
  
  cacheWriteInputTokens integer
  
  Tokens written to the prompt cache.
- callId string
  
  The call ID associated with this request.
- object string
  
  Required
  
  The object type. Always set to conversation.
- choices array of objects
  
  Required
  
  A list of conversation choices.
  
  Show choices properties
  
  index integer
  
  Required
  
  Position of a specific token within the generated output. Each token in the model's response has an associated index, starting from 0.
  
  message object
  
  Individual communication within a conversation. This field (along with toolCalls/functionCall and any other generated content) is redacted and is never present on the published event; it is documented here only for historical/reference purposes.
  
  Show message properties
  
  role string
  
  Required
  
  The role of the message sender, either "user" or "assistant".
  
  Can be one of: "user""assistant"
  
  finishReason string
  
  Required
  
  Reason why a model's response generation process ended.
- traceId string
  
  The trace ID associated with this request.
- createdAt integer
  
  Required
  
  Unix timestamp of when the response was generated.
- systemFingerprint string|null
  
  This fingerprint represents the backend configuration that the model runs with.
- performanceMetrics object
  
  Only present on streaming requests.
  
  Show performanceMetrics properties
  
  ttft string|null
  
  Required
  
  Time to first token (TTFT) in seconds. Null when timing data is unavailable.
  
  endTime string
  
  Required
  
  Finishing time of the task.
  
  startTime string
  
  Required
  
  Starting time of the task.
  
  totalTime string|null
  
  Required
  
  Total time of the task in seconds. Null when timing data is unavailable.
  
  inferenceSpeed string|null
  
  Required
  
  Tokens per second generated by the model in response to the input. Null when timing data is unavailable.

com.qlik.core.ai-platform.conversations-job.finished

Example payload of the "Conversations finished" event

{
  "id": "A234-1234-1234",
  "time": "2023-01-01T12:00:00Z",
  "type": "com.qlik.core.ai-platform.conversations-job.finished",
  "source": "com.qlik/ai-platform",
  "specversion": "1.0",
  "datacontenttype": "application/json",
  "host": "ai-platform-llm-gateway-844db7d4c7-4glrb",
  "reason": "string",
  "userid": "00000000-0000-0000-0000-000000000000",
  "ownerid": "00000000-0000-0000-0000-000000000000",
  "spaceid": "00000000-0000-0000-0000-000000000000",
  "authtype": "user",
  "clientid": "00000000-0000-0000-0000-000000000000",
  "tenantid": "00000000-0000-0000-0000-000000000000",
  "sessionid": "00000000-0000-0000-0000-000000000000",
  "authclaims": "{\"sub\":\"1234567890\",\"subType\":\"user\",\"iss\":\"qlik.api.internal\"}",
  "tracestate": "congo=t61rcWkgMzE",
  "traceparent": "00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01",
  "toplevelresourceid": "id123",
  "data": {
    "id": "converse-393592ed-ca78-4740-aa87-0ca97480706f",
    "cost": {
      "inputCost": "0.000300",
      "totalCost": "0.003300",
      "outputCost": "0.003000"
    },
    "model": "anthropic.claude-3-sonnet-20240229-v1:0",
    "usage": {
      "totalTokens": 238,
      "promptTokens": 16,
      "completionTokens": 222
    },
    "object": "conversation",
    "createdAt": 1728909071,
    "systemFingerprint": null,
    "performanceMetrics": {
      "ttft": "0.57",
      "endTime": "2024-07-10T15:48:30.416262",
      "startTime": "2024-07-10T15:48:21.598495",
      "totalTime": "8.82",
      "inferenceSpeed": "34.5"
    }
  }
}