Merge branch 'main' into bigframes_terabytes_rag_pipeline_notebook

.github/actions/spelling/allow.txt

@@ -13,6 +13,7 @@ APAC
 APIENTRY
 APSTUDIO
 ASF
+ASGI
 ASML
 AUVs
 Aktu
@@ -757,6 +758,7 @@ hovermode
 https
 httpx
 hwnd
+hypercorn
 iban
 icudtl
 idcg

README.md

@@ -1,18 +1,15 @@
 # Generative AI
 
-> NOTE: [Gemini 2.0 Flash](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2) has been released! Here are the latest notebooks and demos using the new model:
+> NOTE: [Gemini 2.0 Flash-Lite and Gemini 2.0 Pro](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2) have been released!
 >
+> Here are the latest notebooks and demos using the new models:
+> - [Intro to Gemini 2.0 Pro](gemini/getting-started/intro_gemini_2_0_pro.ipynb)
+> - [Intro to Gemini 2.0 Flash-Lite](gemini/getting-started/intro_gemini_2_0_flash_lite.ipynb)
 > - [Intro to Gemini 2.0 Flash](gemini/getting-started/intro_gemini_2_0_flash.ipynb)
 > - [Intro to Multimodal Live API with Gen AI SDK](gemini/multimodal-live-api/intro_multimodal_live_api_genai_sdk.ipynb)
 > - [Intro to Gemini 2.0 Thinking Mode](gemini/getting-started/intro_gemini_2_0_flash_thinking_mode.ipynb)
 > - [Intro to Code Execution](gemini/code-execution/intro_code_execution.ipynb)
 > - [Multimodal Live API Demo App](gemini/multimodal-live-api/websocket-demo-app/)
-> - [Intro to Google Gen AI SDK](gemini/getting-started/intro_genai_sdk.ipynb)
-> - [Real-Time RAG with Multimodal Live API](gemini/multimodal-live-api/real_time_rag_retail_gemini_2_0.ipynb)
-> - [Creating Marketing Assets using Gemini 2.0](gemini/use-cases/marketing/creating_marketing_assets_gemini_2_0.ipynb)
-> - [Vertex AI Gemini Research Multi Agent Demo Research Agent for EV Industry](gemini/agents/research-multi-agents)
-> - [Create a Multi-Speaker Podcast with Gemini 2.0 & Text-to-Speech](audio/speech/use-cases/podcast/multi-speaker-podcast.ipynb)
-> - [Intro to Gemini 2.0 Flash REST API](gemini/getting-started/intro_gemini_2_0_flash_rest_api.ipynb)
 
 <!-- markdownlint-disable MD033 -->
 

audio/speech/use-cases/podcast/multi-speaker-podcast.ipynb

@@ -313,7 +313,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_ID = \"gemini-2.0-flash-exp\"  # @param {type: \"string\"}"
+        "MODEL_ID = \"gemini-2.0-flash-001\"  # @param {type: \"string\"}"
       ]
     },
     {

gemini/agents/research-multi-agents/intro_research_multi_agents_gemini_2_0.ipynb

@@ -97,18 +97,6 @@
         "| Author(s) |  [Lavi Nigam](https://github.com/lavinigam-gcp)|"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "CSt0qUR2Sg61"
-      },
-      "source": [
-        "<div class=\"alert alert-block alert-warning\">\n",
-        "<b>\n",
-        "⚠️ Gemini 2.0 Flash (Model ID: gemini-2.0-flash-exp) and the Google Gen AI SDK are currently experimental and output can vary ⚠️</b>\n",
-        "</div>\n"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -256,7 +244,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "[Gemini 2.0 Flash](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2) is a new multimodal generative ai model from the Gemini family developed by [Google DeepMind](https://deepmind.google/). It now available as an experimental preview release through the Gemini API in Vertex AI and Vertex AI Studio. The model introduces new features and enhanced core capabilities:\n",
+        "[Gemini 2.0 Flash](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2) is a new multimodal generative ai model from the Gemini family developed by [Google DeepMind](https://deepmind.google/). It now available through the Gemini API in Vertex AI and Vertex AI Studio. The model introduces new features and enhanced core capabilities:\n",
         "\n",
         "- Multimodal Live API: This new API helps you create real-time vision and audio streaming applications with tool use.\n",
         "- Speed and performance: Gemini 2.0 Flash is the fastest model in the industry, with a 3x improvement in time to first token (TTFT) over 1.5 Flash.\n",
@@ -463,7 +451,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_ID = \"gemini-2.0-flash-exp\"  # @param {type: \"string\"}\n",
+        "MODEL_ID = \"gemini-2.0-flash-001\"  # @param {type: \"string\"}\n",
         "MODEL_ID_Flash = \"gemini-1.5-flash-002\"  # For control generation for grounding with google search as a Tool"
       ]
     },