Embeddable AI

 View Only
Expand all | Collapse all

Precision Analysis on Watson assistant chatbotUI

  • 1.  Precision Analysis on Watson assistant chatbotUI

    Posted Wed September 14, 2022 10:03 AM
    Hello Team,
    Please I have struggling with consuming watson assistant log API. currently we use watson assistant log API for fetching daily conversation log between our chatbot and customer and feed the log into NLC for classifying the intents for precision analyst. Recently we observed that IBM has decomission the NLC and advice that we migrate to NLU. since then we've being having issues getting our the component running.
    right now the assistant log return empty log for this filter 
    response1 = watsonInfo.assistant.list_logs(workspace_id=workspaceId, page_limit=1000, filter='response_timestamp>2022-09-04',
    cursor=cursor).get_result()

    at a point its returning 
    Error: Rate limit exceeded, Code: 429 , X-global-transaction-id: 4039abf9-4c9a-42c8-bbe8-131a3f19f7b2

    ------------------------------
    Afeez Ishola
    ------------------------------

    #BuildwithWatsonApps
    #EmbeddableAI


  • 2.  RE: Precision Analysis on Watson assistant chatbotUI

    Posted Fri September 16, 2022 01:10 PM
    Afeez,

      You are getting rate limit errors (https://cloud.ibm.com/apidocs/assistant/assistant-v2#rate-limiting), because you are calling the Assistant API too much.  When trying to get logs, it is best to get them in bunches (the default "page" size is 100 at a time) for processing, and use a cursor (https://cloud.ibm.com/apidocs/assistant/assistant-v2#listlogs) to keep getting the next set of logs until to reach the end of your query.  Using a cursor also allows you to have higher rate limits (120 per minute).  Rate limiting is used so your Assistant does not become overrun with API requests.

    ------------------------------
    Daniel Toczala
    Community Leader and Customer Success Manager - Watson
    dtoczala@us.ibm.com
    ------------------------------