Skip to content
Open
Show file tree
Hide file tree
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
117 changes: 104 additions & 13 deletions references/owui-helm-overrides.xml
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,7 @@
<title>&owui; override file with &ollama; included</title>
<para>
The following override file installs &ollama; during the &owui;
installation. Replace <replaceable>SUSE_AI_NAMESPACE</replaceable> with
your &kube; namespace.
installation.
</para>
<screen>global:
imagePullSecrets:
Expand All @@ -51,16 +50,26 @@ ollama:
number: 1
persistentVolume:<co xml:id="co-ollama-persistent1"/>
enabled: true
storageClass: local-path<co xml:id="co-ollama-localpath2"/>
storageClass: local-path
pipelines:
enabled: False
enabled: true
persistence:
storageClass: local-path<co xml:id="co-ollama-localpath3"/>
storageClass: local-path
extraEnvVars: <co xml:id="co-pipelines-extraenvvars"/>
- name: PIPELINES_URLS <co xml:id="co-pipelines-extraenvvars-pipelines-urls"/>
value: "https://raw.githubusercontent.com/SUSE/suse-ai-observability-extension/refs/heads/main/integrations/oi-filter/suse_ai_filter.py"
- name: OTEL_SERVICE_NAME <co xml:id="co-pipelines-extraenvvars-otel-service-name"/>
value: "Open WebUI"
- name: OTEL_EXPORTER_HTTP_OTLP_ENDP&owui;NT <co xml:id="co-pipelines-extraenvvars-otel-exporter-http-otlp-endpoint"/>
value: "http://opentelemetry-collector.suse-observability.svc.cluster.local:4318"
- name: PRICING_JSON <co xml:id="co-pipelines-extraenvvars-pricing-json"/>
value: "https://raw.githubusercontent.com/SUSE/suse-ai-observability-extension/refs/heads/main/integrations/oi-filter/pricing.json"
ingress:
enabled: true
class: ""
annotations:
nginx.ingress.kubernetes.io/ssl-redirect: "true"
nginx.ingress.kubernetes.io/proxy-body-size: "1024m"
host: suse-ollama-webui<co xml:id="co-ollama-webui"/>
tls: true
extraEnvVars:
Expand All @@ -79,8 +88,20 @@ extraEnvVars:
- name: MILVUS_URI
value: http://milvus.<replaceable>SUSE_AI_NAMESPACE</replaceable>.svc.cluster.local:19530
- name: INSTALL_NLTK_DATASETS<co xml:id="co-ollama-extravars-nltk"/>
value: "true"</screen>
value: "true"
- name: OMP_NUM_THREADS
value: "1"
- name: OPENAI_API_KEY <co xml:id="co-extraenvvars-openai-api-key"/>
value: "0p3n-w3bu!"</screen>
<calloutlist>
<callout arearefs="co-ollama-localpath1">
<para>
Use <option>local-path</option> storage only for testing purposes. For
production use, we recommend using a storage solution more suitable
for persistent storage. To use &sstorage;, specify
<literal>longhorn</literal>.
</para>
</callout>
<callout arearefs="co-ollama-models">
<para>
Specifies that two large language models (LLM) will be loaded in
Expand All @@ -102,11 +123,34 @@ extraEnvVars:
when the container is restarted.
</para>
</callout>
<callout arearefs="co-ollama-localpath1 co-ollama-localpath2 co-ollama-localpath3">
<callout arearefs="co-pipelines-extraenvvars">
<para>
Use <option>local-path</option> storage only for testing purposes. For
production use, we recommend using a storage solution suitable for
persistent storage, such as &sstorage;.
The environment variables that you are making available for the
pipeline's runtime container.
</para>
</callout>
<callout arearefs="co-pipelines-extraenvvars-pipelines-urls">
<para>
A list of pipeline URLs to be downloaded and installed by default.
Individual URLs are separated by a semicolon <literal>;</literal>.
</para>
</callout>
<callout arearefs="co-pipelines-extraenvvars-otel-service-name">
<para>
The service name that appears in traces and topological
representations in &sobservability;.
</para>
</callout>
<callout arearefs="co-pipelines-extraenvvars-otel-exporter-http-otlp-endpoint">
<para>
The endpoint for the &otelemetry; collector. Make sure to use the HTTP
port of your collector.
</para>
</callout>
<callout arearefs="co-pipelines-extraenvvars-pricing-json">
<para>
A file for the model multipliers in cost estimation. You can customize
it to match your actual infrastructure experimentally.
</para>
</callout>
<callout arearefs="co-ollama-extravars">
Expand All @@ -128,14 +172,19 @@ extraEnvVars:
licensing information.
</para>
</callout>
<callout arearefs="co-extraenvvars-openai-api-key">
<para>
The value for the API key between &owui; and &owui; Pipelines. The
default value is <quote>0p3n-w3bu!</quote>.
</para>
</callout>
</calloutlist>
</example>
<example xml:id="owui-ollama-deploy-separate">
<title>&owui; override file with &ollama; installed separately</title>
<para>
The following override file installs &ollama; separately from the &owui;
installation. Replace <replaceable>SUSE_AI_NAMESPACE</replaceable> with
your &kube; namespace.
installation.
</para>
<screen>global:
imagePullSecrets:
Expand Down Expand Up @@ -177,7 +226,9 @@ extraEnvVars:
- name: ENABLE_OTEL<co xml:id="co-owui-otel1"/>
value: "true"
- name: OTEL_EXPORTER_OTLP_ENDPOINT<co xml:id="co-owui-otel2"/>
value: http://opentelemetry-collector.observability.svc.cluster.local:4317<co xml:id="co-llama-otel"/></screen>
value: http://opentelemetry-collector.observability.svc.cluster.local:4317<co xml:id="co-llama-otel"/>
- name: OMP_NUM_THREADS
value: "1"</screen>
<calloutlist>
<callout arearefs="co-ollama-localpath4 co-ollama-localpath5">
<para>
Expand All @@ -204,6 +255,46 @@ extraEnvVars:
</callout>
</calloutlist>
</example>
<example xml:id="owui-ollama-deploy-pipelines">
<title>&owui; override file with pipelines enabled</title>
<para>
The following override file installs &ollama; separately and enables
&owui; pipelines. This simple filter adds a limit to the number of
question and answer turns during the LLM chat.
</para>
<tip>
<para>
Pipelines normally require additional configuration provided either via
environment variables or specified in the &owui; Web UI.
</para>
</tip>
<screen>global:
imagePullSecrets:
- application-collection
<phrase condition="deployment_airgap">imageRegistry: <replaceable>LOCAL_DOCKER_REGISTRY_URL</replaceable>:5043</phrase>
ollamaUrls:
- http://ollama.<replaceable>SUSE_AI_NAMESPACE</replaceable>.svc.cluster.local:11434
persistence:
enabled: true
storageClass: local-path
ollama:
enabled: false
pipelines:
enabled: true
persistence:
storageClass: local-path
extraEnvVars:
- name: PIPELINES_URLS
value: "https://raw.githubusercontent.com/SUSE/suse-ai-observability-extension/refs/heads/main/integrations/oi-filter/conversation_turn_limit_filter.py"
ingress:
enabled: true
class: ""
annotations:
nginx.ingress.kubernetes.io/ssl-redirect: "true"
host: suse-ollama-webui
tls: true
[...]</screen>
</example>
<example xml:id="owui-ollama-deploy-vllm" condition="deployment_standard">
<title>&owui; override file with a connection to &vllm;</title>
<para>
Expand Down
4 changes: 3 additions & 1 deletion snippets/helm-chart-overrides-intro.xml
Original file line number Diff line number Diff line change
Expand Up @@ -11,5 +11,7 @@ xmlns:xlink="http://www.w3.org/1999/xlink">
To override the default values during the &helm; chart installation or update,
you can create an override YAML file with custom values. Then, apply these
values by specifying the path to the override file with the
<option>-f</option> option of the <command>helm</command> command.
<option>-f</option> option of the <command>helm</command> command. Remember to
replace <replaceable>SUSE_AI_NAMESPACE</replaceable> with your &kube;
namespace.
</para>
2 changes: 1 addition & 1 deletion tasks/observability-settingup-ai.xml
Original file line number Diff line number Diff line change
Expand Up @@ -423,7 +423,7 @@ clusterName: <replaceable>OBSERVED_SERVER_NAME</replaceable>
<para>
The difference between deployment scenarios affects the
<emphasis role="bold">OTEL Collector exporter configuration</emphasis> and
the <emphasis role="bold">SUSE Observability Agent URL</emphasis> as
the <emphasis role="bold">&sobservability; Agent URL</emphasis> as
described in the following list.
</para>
<variablelist>
Expand Down