Merge branch 'main' into thinking-0127

.github/CODEOWNERS

@@ -81,3 +81,4 @@
 /generative-ai/vision/use-cases/hey_llm                     @tushuhei @GoogleCloudPlatform/generative-ai-devrel
 /generative-ai/gemini/sample-apps/llamaindex-rag/backend/indexing/ @Lionel-Lim @GoogleCloudPlatform/generative-ai-devrel
 /generative-ai/gemini/multimodal-live-api/websocket-demo-app/ @ZackAkil @GoogleCloudPlatform/generative-ai-devrel
+/generative-ai/gemini/sample-apps/genai-mlops-tune-and-eval                       @willisc7 @GoogleCloudPlatform/generative-ai-devrel

.github/actions/spelling/allow.txt

@@ -958,6 +958,7 @@ podcast
 podcasts
 podfile
 podhelper
+podman
 powerups
 praw
 prcntg

README.md

@@ -47,7 +47,7 @@ For more Vertex AI samples, please visit the [Vertex AI samples GitHub repositor
       <br>
       <a href="search/"><code>search/</code></a>
     </td>
-    <td>Use this folder if you're interested in using <a href="https://cloud.google.com/enterprise-search">Vertex AI Search</a>, a Google-managed solution to help you rapidly build search engines for websites and across enterprise data. (Formerly known as Enterprise Search on Generative AI App Builder)</td>
+    <td>Use this folder if you're interested in using <a href="https://cloud.google.com/enterprise-search">Vertex AI Search</a>, a Google-managed solution to help you rapidly build search engines for websites and across enterprise data. (Formerly known as Enterprise Search on Generative AI App Builder).</td>
   </tr>
   <tr>
     <td>
@@ -63,7 +63,7 @@ For more Vertex AI samples, please visit the [Vertex AI samples GitHub repositor
       <br>
       <a href="conversation/"><code>conversation/</code></a>
     </td>
-    <td>Use this folder if you're interested in using <a href="https://cloud.google.com/generative-ai-app-builder">Vertex AI Conversation</a>, a Google-managed solution to help you rapidly build chat bots for websites and across enterprise data. (Formerly known as Chat Apps on Generative AI App Builder)</td>
+    <td>Use this folder if you're interested in using <a href="https://cloud.google.com/generative-ai-app-builder">Vertex AI Conversation</a>, a Google-managed solution to help you rapidly build chat bots for websites and across enterprise data. (Formerly known as Chat Apps on Generative AI App Builder).</td>
   </tr>
   <tr>
     <td>
@@ -116,7 +116,7 @@ For more Vertex AI samples, please visit the [Vertex AI samples GitHub repositor
       <br>
       <a href="RESOURCES.md"><code>RESOURCES.md</code></a>
     </td>
-    <td>Learning resources (e.g. blogs, YouTube playlists) about Generative AI on Google Cloud</td>
+    <td>Learning resources (e.g. blogs, YouTube playlists) about Generative AI on Google Cloud.</td>
   </tr>
 </table>
 <!-- markdownlint-enable MD033 -->

gemini/reasoning-engine/tutorial_langgraph.ipynb

@@ -107,7 +107,7 @@
         "This notebook covers the following steps:\n",
         "\n",
         "- **Define Tools**: Create custom Python functions to act as tools your AI application can use.\n",
-        "- **Define Router**: Create custom Python functions to act as tools your AI application can use.\n",
+        "- **Define Router**: Set up routing logic to control conversation flow and tool selection.\n",
         "- **Build a LangGraph Application**: Structure your application using LangGraph, including the Gemini model and custom tools that you define.\n",
         "- **Local Testing**: Test your LangGraph application locally to ensure functionality.\n",
         "- **Deploying to Vertex AI**: Seamlessly deploy your LangGraph application to Reasoning Engine for scalable execution.\n",

gemini/sample-apps/e2e-gen-ai-app-starter-pack/app/patterns/multimodal_live_agent/Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.11-slim
+
+RUN pip install  --no-cache-dir poetry==1.6.1
+
+RUN poetry config virtualenvs.create false
+
+WORKDIR /code
+
+COPY ./pyproject.toml ./README.md ./poetry.lock* ./
+
+COPY ./app ./app
+
+RUN poetry install  --no-interaction --no-ansi --no-dev
+
+EXPOSE 8080
+
+CMD ["uvicorn", "app.server:app", "--host", "0.0.0.0", "--port", "8080"]

gemini/tuning/genai-mlops-tune-and-eval/.gitignore

@@ -0,0 +1,6 @@
+__pycache__
+pipeline.json
+venv
+local/local_outputs
+local/pipeline.json
+local/venv

gemini/tuning/genai-mlops-tune-and-eval/README.md

@@ -0,0 +1,83 @@
+# Gen AI MLOps Tune and Evaluation
+
+Author: [Chris Willis](https://github.com/willisc7)
+
+This tutorial will take you through using Vertex AI Pipelines to automate tuning an LLM and evaluating it against a previously tuned LLM. The example used is an LLM that summarizes a week of glucose values for a diabetes patient.
+
+![Diagram](https://storage.googleapis.com/github-repo/generative-ai/gemini/tuning/mlops-tune-and-eval/diagram.png)
+
+## Optional: Prepare the data
+
+This step is optional because I've already prepared the data in `gs://github-repo/generative-ai/gemini/tuning/mlops-tune-and-eval/patient_1_glucose_examples.jsonl`.
+
+- Create a week of glucose sample data for one patient using the following prompt with Gemini:
+
+  ```none
+  Create a CSV with a week's worth of example glucose values for a diabetic patient. The columns should be date, time, patient ID, and glucose value.  Each day there should be timestamps for 7am, 8am, 11am, 12pm, 5pm, and 6pm. Most of the glucose values should be between 70 and 100. Some of the glucose values should be 100-150.
+  ```
+
+- Flatten the CSV by doing the following:
+  1. Open the CSV
+  2. Press Ctrl + a to select all text
+  3. Press Alt + Shift + i to go to the end of each line
+  4. Add a newline character (i.e. \n)
+  5. Press Delete to squash it all to a single line
+- Copy `glucose_examples_template.jsonl` (or create it if it doesn't exist) to `patient_X_glucose_examples.jsonl`
+- Copy the flattened CSV and paste it into the patient_X_glucose_examples.jsonl
+- Flatten the contents of the patient_X_glucose_examples.jsonl file using a JSON to JSONL converter online
+
+## Setup IAM, Tuning Examples, and Vertex AI Pipelines
+
+- Grant Default Compute Service Account IAM permissions
+
+  ```sh
+  PROJECT_NUMBER=$(gcloud projects describe $(gcloud config get-value project) --format="value(projectNumber)")
+  SERVICE_ACCOUNT="${PROJECT_NUMBER}[email protected]"
+
+  gcloud projects add-iam-policy-binding $PROJECT_NUMBER \
+    --member="serviceAccount:${SERVICE_ACCOUNT}" \
+    --role="roles/aiplatform.user"
+  gcloud projects add-iam-policy-binding $PROJECT_NUMBER \
+    --member="serviceAccount:${SERVICE_ACCOUNT}" \
+    --role="roles/storage.objectUser"
+  ```
+
+- Enable the Cloud Resource Manager API
+
+  ```sh
+  gcloud services enable cloudresourcemanager.googleapis.com
+  ```
+
+- Create the pipeline root bucket
+
+  ```sh
+  gsutil mb gs://vertex-ai-pipeline-root-$(date +%Y%m%d)
+  ```
+
+## Run Vertex AI Pipelines
+
+- Install required packages and compile the pipeline
+
+  ```sh
+  python3 -m venv venv
+  source venv/bin/activate
+  pip install -r requirements.txt
+  kfp dsl compile --py pipeline.py --output pipeline.json
+  ```
+
+- Edit `pipeline.py` and change the following:
+
+  - `project` - change to your project ID
+
+- Edit `submit_pipeline_job.py` and change the following:
+
+  - `pipeline_root` - change to the `gs://vertex-ai-pipeline-root-<DATETIME>` bucket you created earlier
+  - `project` - change to your project ID
+
+- Create the pipeline run
+
+  ```sh
+  python submit_pipeline_job.py
+  ```
+
+- For subsequent runs, change `baseline_model_endpoint` in `submit_pipeline_job.py` to a tuned model endpoint you want to compare against (typically the previously trained endpoint)