[
https://issues.apache.org/jira/browse/CAMEL-25766?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Claus Ibsen resolved CAMEL-25766.
---------------------------------
Fix Version/s: (was: 4.24.0)
Resolution: Duplicate
Moved to apache/camel-jbang-examples#124
(https://github.com/apache/camel-jbang-examples/issues/124):
camel-jbang-examples tracks its work in its own GitHub issues. The example is
in PR #119 there.
_Claude Code on behalf of davsclaus_
> camel-jbang-examples - ai/ticket-classifier: a local model sorts support
> tickets, and the route checks its answer
> -----------------------------------------------------------------------------------------------------------------
>
> Key: CAMEL-25766
> URL: https://issues.apache.org/jira/browse/CAMEL-25766
> Project: Camel
> Issue Type: Improvement
> Components: camel-jbang
> Reporter: Claus Ibsen
> Assignee: Claus Ibsen
> Priority: Minor
>
> The ai rung of camel-jbang-examples has a local model that writes text
> (langchain4j-chat), but no example where a model's answer drives the routing.
> A new example, ai/ticket-classifier, shows it with the web shop's support
> tickets:
> * a local model (granite4:3b on Ollama, from camel infra or installed) names
> the category of each ticket: shipping, billing or account,
> * the prompt is sent from a variable and the answer goes to one
> (variableSend, variableReceive), so the ticket stays the body,
> * the route does not trust the answer: it is normalized, and anything other
> than the three categories files the ticket under unknown,
> * a circuit breaker with a timeout files the ticket under unknown when the
> model is slow or down.
> It comes with a Citrus YAML test on the camel infra Ollama (ciSkip, like
> langchain4j-chat), and it is also a new task for the AI benchmark.
> _Claude Code on behalf of davsclaus_
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
