Arafat Khan created HDDS-15906:
----------------------------------
Summary: Add gateway LLM provider for Recon chatbot
(OpenAI-compatible gateways)
Key: HDDS-15906
URL: https://issues.apache.org/jira/browse/HDDS-15906
Project: Apache Ozone
Issue Type: Sub-task
Components: Ozone Recon
Reporter: Arafat Khan
Fix For: 2.3.0
*Problem*
When customers route all LLM traffic through an OpenAI-compatible gateway (e.g.
LiteLLM or similar), they must configure {{openai.*}} and put non-OpenAI model
names under {{{}openai.models{}}}. That is confusing and error-prone.
*Solution*
Add a dedicated {{gateway}} provider that uses the same OpenAI-compatible
client, with explicit config keys:
* {{ozone.recon.chatbot.provider=gateway}}
* {{ozone.recon.chatbot.gateway.api.key}}
* {{ozone.recon.chatbot.gateway.base.url}} (required)
* {{ozone.recon.chatbot.gateway.models}} (comma-separated aliases)
Existing {{{}openai{}}}, {{{}gemini{}}}, and {{anthropic}} providers are
unchanged.
*Notes*
* Model names in {{gateway.models}} must match the gateway’s configured
aliases exactly.
* No auto-discovery; admins maintain the model list in config.
*Testing*
* Unit tests for routing and dispatcher
* Manual smoke test against an OpenAI-compatible gateway
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
