Skip to content

ENG-24977 initial draft on how to enable and access the chatbot inter… #808

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 46 additions & 0 deletions modules/accessing-the-chat-bot-interface.adoc
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
:_module-type: PROCEDURE

[id="accessing-the-chat-bot-interface_{context}"]
= Accessing the chat bot interface

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@alexcreasy, in RHOAI 2.21 RC1, when following these instructions I see the Chatbot tab appearing in Dashboard but, when writing in the chat, nothing happens. Looking at the Network tab in the Developer Tools there are no network calls.

Is it possible that we need ODH master to run the chatbot?


[role='_abstract']
Embedding a Llama stack large language model (LLM) chat bot interface directly into a data science project gives you immediate, context-aware assistance without switching tools. You can use this interface to quickly explore model parameters, troubleshoot errors, and experiment interactively within a data science project.

[IMPORTANT]
====
By default, the chat bot interface is hidden from display within the data science project user interface. To show the user interface components for the chat bot interface, set the `disableLlamaStackClient` value to `false` in the `OdhDashboardConfig` custom resource (CR) in {openshift-platform}.
ifndef::upstream[]
For more information, see link:{rhoaidocshome}/html/managing_openshift_ai/customizing-the-dashboard#ref-dashboard-configuration-options_dashboard[Dashboard configuration options].
endif::[]
ifdef::upstream[]
For more information, see link:{odhdocshome}/managing-odh/#ref-dashboard-configuration-options_dashboard[Dashboard configuration options].
endif::[]
====

.Prerequisites
* You have logged in to {productname-long}.
* The `disableLlamaStackClient` feature flag value is set to `false` in the `OdhDashboardConfig` custom resource (CR) in {openshift-platform}.
ifndef::upstream[]
* If you are using {productname-short} groups, you are part of the user group or admin group (for example, {oai-user-group} or {oai-admin-group}) in OpenShift.
endif::[]
ifdef::upstream[]
* If you are using {productname-short} groups, you are part of the user group or admin group (for example, {odh-user-group} or {odh-admin-group}) in OpenShift.
endif::[]
* You have created a data science project.
* You have deployed the Llama Stack Operator.
* You have configured a LlamaStackDistribution custom resource (CR) with a vLLM inference service and a Milvus vector database.

.Procedure
. From the {productname-short} dashboard, click *Data science projects*.
+
The *Data science projects* page opens.
. Click the data science project for which you want to access the chat bot.
+
A project details page opens.
. Click the *Chat bot* tab.
+
The LlamaStack chat bot interface displays.

.Verification
* You can access the *Chat bot* tab from within a data science project.
* You can successfully send queries to the chat bot and then receive relevant answers.