[release-1.10] RHIDP-12596: Personal AI Notebooks (#2212)

openshift-cherrypick-robot · pabel-rh · web-flow · commit cf1f3db7fa8f · 2026-05-18T18:52:48.000+05:30
* Personal AI Notebooks

* CQA-related changes

* Incorporated Ben's comments

* Fixing UI button name

* Incorporate tech comments

* Incorporated Fabrice's comments

* Remove orphaned files

* Incorporated Fabrice's comments

---------

Co-authored-by: Priyanka Abel &lt;pabel@redhat.com&gt;
diff --git a/assemblies/shared/assembly-build-a-private-knowledge-base-with-notebooks.adoc b/assemblies/shared/assembly-build-a-private-knowledge-base-with-notebooks.adoc
@@ -0,0 +1,25 @@
+:_mod-docs-content-type: ASSEMBLY
+ifdef::context[:parent-context: {context}]
+
+[id="build-a-private-knowledge-base-with-notebooks_{context}"]
+= Build a private knowledge base with {ls-short} Notebooks
+
+:context: build-a-private-knowledge-base-with-notebooks
+
+[role="_abstract"]
+Use {ls-short} notebooks to create isolated research environments. These workspaces allow you to analyze project data securely by using a large language model (LLM) grounded in your specific documentation.
+
+include::{docdir}/artifacts/snip-developer-preview.adoc[]
+
+include::../modules/shared/proc-create-isolated-research-workspaces.adoc[leveloffset=+1]
+
+include::../modules/shared/proc-provide-project-context-to-the-ai.adoc[leveloffset=+1]
+
+include::../modules/shared/proc-extract-and-verify-document-based-insights.adoc[leveloffset=+1]
+
+// [role="_additional-resources"]
+// == Additional resources
+//* 
+//
+ifdef::parent-context[:context: {parent-context}]
+ifndef::parent-context[:!context:]
diff --git a/assemblies/shared/assembly-customize.adoc b/assemblies/shared/assembly-customize.adoc
@@ -15,6 +15,9 @@ include::../modules/shared/proc-update-the-system-prompt-in.adoc[leveloffset=+1]
 
 include::../modules/shared/proc-customize-the-chat-history-storage-in.adoc[leveloffset=+1]
 
+include::../modules/shared/proc-enable-secure-ai-research-with-developer-lightspeed-notebooks.adoc[leveloffset=+2]
+
 // include::../modules/shared/proc-changing-your-llm-provider.adoc[leveloffset=+1]
 ifdef::parent-context[:context: {parent-context}]
 ifndef::parent-context[:!context:]
+
diff --git a/assemblies/shared/assembly-get-ai-assisted-help-for-your-development-tasks.adoc b/assemblies/shared/assembly-get-ai-assisted-help-for-your-development-tasks.adoc
@@ -20,5 +20,8 @@ include::../modules/shared/ref-best-results-for-assistant-queries.adoc[leveloffs
 include::../modules/shared/con-ai-response-monitoring-and-context-management.adoc[leveloffset=+1]
 
 include::../modules/shared/proc-manage-chats.adoc[leveloffset=+1]
+
+include::assembly-build-a-private-knowledge-base-with-notebooks.adoc[leveloffset=+1]
+
 ifdef::parent-context[:context: {parent-context}]
 ifndef::parent-context[:!context:]
diff --git a/assemblies/shared/assembly-solve-project-specific-challenges-with-notebooks.adoc b/assemblies/shared/assembly-solve-project-specific-challenges-with-notebooks.adoc
@@ -0,0 +1,34 @@
+:_mod-docs-content-type: ASSEMBLY
+ifdef::context[:parent-context: {context}]
+
+[id="solve-project-specific-challenges-with-notebooks_{context}"]
+= Solve project-specific challenges with {ls-short} Notebooks
+:context: solve-project-specific-challenges-with-developer-lightspeed-notebooks
+
+[role="_abstract"]
+Use {ls-short} Notebooks to research, troubleshoot, and analyze projects by using a large language model (LLM) grounded in your own documentation. Notebooks use Retrieval-Augmented Generation (RAG) to ensure that responses are based strictly on the files you upload.
+
+Use Notebooks to achieve the following goals:
+
+`Query your documentation`:: Upload project files to ask questions, summarize content, or brainstorm ideas based on those specific documents.
+`Troubleshoot with project-specific context`:: Upload project logs, architecture diagrams, or onboarding files to receive technical answers tailored to your specific environment.
+`Securely analyze private data`:: Conduct research in isolated sessions. Your uploaded data and chat history remain private and are inaccessible to other users.
+`Run multiple Notebooks`:: Uploaded documents and chat history remain available and are re-opened through the *Notebook* dashboard.
+`Verify AI responses with citations`:: Use the *Sources* chips to view the exact document excerpts used to generate an answer.
+`Organize research`:: Use metadata and tagging to categorize different research topics.
+
+The following constraints apply during the {developer-preview}:
+
+`Data boundaries`:: The AI can only access data within the active Notebook session.
+`Private access`:: You cannot share notebooks or documents with other team members.
+`Manual uploads`:: You must upload files directly. The tool does not support URL ingestion or web scraping.
+`Ephemeral defaults`:: Without a configured Persistent Volume (PV), all Notebook data and uploaded files are lost upon service restart.
+
+include::{docdir}/artifacts/snip-developer-preview.adoc[]
+
+include::../modules/shared/proc-enable-secure-ai-research-with-developer-lightspeed-notebooks.adoc[leveloffset=+1]
+include::../modules/shared/proc-enable-data-persistence-for-developer-lightspeed-notebooks.adoc[leveloffset=+1]
+
+ifdef::parent-context[:context: {parent-context}]
+ifndef::parent-context[:!context:]
+
diff --git a/modules/shared/proc-create-isolated-research-workspaces.adoc b/modules/shared/proc-create-isolated-research-workspaces.adoc
@@ -0,0 +1,15 @@
+:_mod-docs-content-type: PROCEDURE
+[id="create-isolated-research-workspaces_{context}"]
+= Create isolated research workspaces
+
+[role="_abstract"]
+Organize your work into individual notebook sessions to keep research topics separate and private.
+
+.Procedure
+. In the {product-very-short} interface, click the *Open Lightspeed* floating action button (FAB).
+. In your *Developer Lightspeed* page, select the *Notebooks* tab.
+. Click *Create a new notebook* to start a new workspace.
+. Optional: To manage your workspaces, click the *More options* icon on a notebook card to *Rename*, *Delete*, or add *Tags* to the session.
+
+.Verification
+* Confirm the new notebook card appears on the *My Notebooks* dashboard.
diff --git a/modules/shared/proc-enable-data-persistence-for-developer-lightspeed-notebooks.adoc b/modules/shared/proc-enable-data-persistence-for-developer-lightspeed-notebooks.adoc
@@ -0,0 +1,120 @@
+:_mod-docs-content-type: PROCEDURE
+
+[id="enable-data-persistence-for-developer-lightspeed-notebooks_{context}"]
+= Enable data persistence for Developer Lightspeed Notebooks
+
+[role="_abstract"]
+To persist Notebook sessions, documents, and AI history across service restarts, you must configure the Notebooks storage backends to use persistent volumes. 
+
+By default, the service uses ephemeral storage in the `/tmp` directory, which the system clears during a pod restart.
+
+.Prerequisites
+
+* By using the link:https://docs.redhat.com/en/documentation/openshift_container_platform/{ocp-version}/html-single/cli_tools/index#cli-about-cli_cli-developer-commands[{openshift-cli}], you have access, with developer permissions, to the {ocp-short} cluster aimed at containing your {product-short} instance.
+* You have authored and provisioned a custom config map for your deployment. For more information, see link:{configuring-book-link}#provision-your-custom-rhdh-configuration_provision-and-use-your-custom-rhdh-configuration[Provision your custom {product} configuration].
+* A Persistent Volume Claim (PVC) is provisioned in your cluster and mounted to the {lcs-short} container (for example, at `/var/lib/lightspeed-data`).
+
+.Procedure
+
+. Update your custom config map `llama-stack-configs/config.yaml` file to point the `kv_notebooks` storage backend to your persistent mount point:
++
+[source,yaml]
+----
+spec:
+  initContainers:
+    - name: init-notebooks-dir
+      # ... complete init container
+  containers:
+    - name: lightspeed-core
+      image: quay.io/lightspeed-core/lightspeed-stack:0.5.1
+      ports:
+        - containerPort: 8080
+      volumeMounts:
+        - name: notebooks-storage
+          mountPath: /var/lib/lightspeed-data
+        - name: config  # ← Added all ConfigMap mounts
+          mountPath: /app-root/config.yaml
+          subPath: config.yaml
+        - name: lightspeed-config
+          mountPath: /app-root/lightspeed-stack.yaml
+          subPath: lightspeed-stack.yaml
+        - name: profile
+          mountPath: /app-root/rhdh-profile.py
+          subPath: rhdh-profile.py
+      livenessProbe:  # ← Added health checks
+        httpGet:
+          path: /readiness
+          port: 8080          
+      readinessProbe:
+        httpGet:
+          path: /readiness
+          port: 8080
+  volumes:  # ← Added all volume definitions
+    - name: notebooks-storage
+      persistentVolumeClaim:
+        claimName: lightspeed-notebooks-pvc
+    - name: config
+      configMap:
+        name: llama-stack-config
+    - name: lightspeed-config
+      configMap:
+        name: lightspeed-core-config
+    - name: profile
+      configMap:
+        name: rhdh-profile
+----
+. Update your deployment manifest to include the init container, volume mounts, and volume definitions:
++
+[source,yaml]
+----
+spec:
+  template:
+    spec:
+      initContainers:
+        - name: init-notebooks-storage
+          image: registry.access.redhat.com/ubi9/ubi-minimal
+          command: ["sh", "-c", "mkdir -p /var/lib/lightspeed-data/notebooks && chmod -R 777 /var/lib/lightspeed-data/notebooks"]
+          volumeMounts:
+            - name: lightspeed-notebooks
+              mountPath: /var/lib/lightspeed-data
+      containers:
+        - name: lightspeed-stack
+          image: quay.io/lightspeed-core/lightspeed-stack:0.5.1
+          ports:
+            - containerPort: 8080
+          volumeMounts:
+            - name: lightspeed-notebooks
+              mountPath: /var/lib/lightspeed-data
+            - name: config
+              mountPath: /app-root/config.yaml
+              subPath: config.yaml
+          livenessProbe:
+            httpGet:
+              path: /readiness
+              port: 8080
+          readinessProbe:
+            httpGet:
+              path: /readiness
+              port: 8080
+      volumes:
+        - name: lightspeed-notebooks
+          persistentVolumeClaim:
+            claimName: lightspeed-notebooks-pvc
+        - name: config
+          configMap:
+            name: llama-stack-config
+----
+. Apply the updated configuration and restart the service.
+
+.Verification
+
+. In {product}, create a Notebook and upload a test document.
+. Send a message to the virtual assistant and verify that the response is based on the document.
+. Restart the pod:
++
+[source,terminal]
+----
+$ oc delete pod <pod_name>
+----
+. After the pod recovers, refresh the *My Notebooks* dashboard.
+. Verify that the Notebook and the uploaded file are still accessible.
diff --git a/modules/shared/proc-enable-secure-ai-research-with-developer-lightspeed-notebooks.adoc b/modules/shared/proc-enable-secure-ai-research-with-developer-lightspeed-notebooks.adoc
@@ -0,0 +1,52 @@
+:_mod-docs-content-type: PROCEDURE
+
+[id="enable-secure-ai-research-with-developer-lightspeed-notebooks_{context}"]
+= Enable secure AI research with Developer Lightspeed Notebooks
+
+[role="_abstract"]
+Configure {product} and {ls-brand-name} to provide users with private, document-based AI workspaces.
+
+.Prerequisites
+* A deployed instance of {product-very-short}.
+* By using the link:https://docs.redhat.com/en/documentation/openshift_container_platform/{ocp-version}/html-single/cli_tools/index#cli-about-cli_cli-developer-commands[{openshift-cli}], you have access, with developer permissions, to the {ocp-short} cluster aimed at containing your {product-short} instance.
+* A Lightspeed Stack service is running and accessible to the backend.
+* A supported large language model (LLM), such as Granite 7B or higher, is available.
+
+.Procedure
+. Enable the notebook feature and define your model by adding the following configuration to your `{my-app-config-file}` file:
++
+[source,yaml]
+----
+lightspeed:
+  notebooks:
+    enabled: true
+    queryDefaults:
+      model: ${NOTEBOOKS_QUERY_MODEL} # Use the exact model name
+      provider_id: ${NOTEBOOKS_QUERY_PROVIDER_ID}
+----
++
+[NOTE]
+====
+If the model name is incorrect, an error message appears in the logs and the user interface.
+====
+
+. Grant user access through role-based access control (RBAC) policies by defining permissions in your `rbac-policy-csv` file:
+.. Add the permission policy:
++
+[source,text]
+----
+p, role:default/_<your_team_name>_, lightspeed.notebooks.use, update, allow
+----
+.. Assign the role to specific users:
++
+[source,text]
+----
+g, user:default/_<your_user_name>_, role:default/_<your_team_name>_
+----
+
+. Apply the updated configuration and restart the service.
+
+.Verification
+. Log in to {product-very-short} using an account assigned to the RBAC role defined in the configuration.
+. Confirm that the *Notebooks* tab is visible next to the *Chat* tab in the primary navigation bar.
+. Click the *Notebooks* tab and ensure the *My Notebooks* dashboard loads without error messages.
diff --git a/modules/shared/proc-extract-and-verify-document-based-insights.adoc b/modules/shared/proc-extract-and-verify-document-based-insights.adoc
@@ -0,0 +1,22 @@
+:_mod-docs-content-type: PROCEDURE
+[id="extract-and-verify-document-based-insights_{context}"]
+= Extract and verify document-based insights
+
+[role="_abstract"]
+After providing context, use the AI to perform reasoning across your files and verify the accuracy of the responses.
+
+.Prerequisites
+* You have uploaded documents or URLs to the active chat session to establish context.
++
+[NOTE]
+====
+If no documents are uploaded, you cannot communicate with the AI.
+====
+.Procedure
+. Enter a question in the prompt bar at the bottom of the screen.
+. Analyze the response. The AI identifies relationships across all uploaded documents and URLs in the session.
+. To verify accuracy, click the *Sources* chip to view the specific document excerpts used to generate the answer.
+. Manage your workflow by using the history panel in the sidebar to expand or collapse previous interactions.
+
+.Verification
+* Confirm that the *Sources* panel displays the correct filenames and text snippets corresponding to the AI's response.
diff --git a/modules/shared/proc-provide-project-context-to-the-ai.adoc b/modules/shared/proc-provide-project-context-to-the-ai.adoc
@@ -0,0 +1,29 @@
+:_mod-docs-content-type: PROCEDURE
+[id="provide-project-context-to-the-ai_{context}"]
+= Provide project context to the AI
+
+[role="_abstract"]
+To receive answers tailored to your project, upload relevant source material to your active session.
+
+.Procedure
+
+. Open a Notebook card from the dashboard.
+
+. Add resources by using one of the following methods:
+** In the sidebar, click the *Add (+)* icon.
+** In the main user interface, click *Upload a resource*.
+
+. Select your sources:
+Local files:: Upload `.txt`, `.md`, `.pdf`, `.docx`, `.log`, `.yaml`, or `.json` files.
+Web content:: Enter a URL to ingest web-based content.
+
+. Adhere to the following constraints:
+`File size`:: Individual files or URL content must be 20MB or smaller.
+`Notebook Capacity`:: The total token count per session must not exceed 100k.
+`Unsupported content`:: Avoid scanned PDF images without text, audio, video, and general image files.
+`Persistence requirement`:: The internal SQL and KV stores must be mapped to a persistent backend to maintain the 100k token context across sessions.
+
+. Wait for the system to process and vectorize the files. This might take several seconds for larger PDFs.
+
+.Verification
+* Ensure the uploaded files appear in the *Resources* list in the sidebar with a `Processed` status.
diff --git a/titles/integrate_interacting-with-developer-lightspeed-for-rhdh/master.adoc b/titles/integrate_interacting-with-developer-lightspeed-for-rhdh/master.adoc
@@ -26,6 +26,8 @@ include::modules/shared/proc-install-and-configure.adoc[leveloffset=+1]
 
 include::assemblies/shared/assembly-customize.adoc[leveloffset=+1]
 
+include::assemblies/shared/assembly-solve-project-specific-challenges-with-notebooks.adoc[leveloffset=+1]
+
 include::assemblies/shared/assembly-get-ai-assisted-help-for-your-development-tasks.adoc[leveloffset=+1]
 
 include::assemblies/shared/assembly-ai-model-evaluation-data-to-select-the-right-ai-model.adoc[leveloffset=+1]
