Merge branch 'main' into patents-batch

GoogleCloudPlatform · Jan 8, 2025 · 6298ecf · 6298ecf
2 parents f46ad24 + 560c0b4
commit 6298ecf
Show file tree

Hide file tree

Showing 78 changed files with 30,191 additions and 395 deletions.
diff --git a/.github/actions/spelling/allow.txt b/.github/actions/spelling/allow.txt
@@ -353,6 +353,7 @@ PYINK
 Pakeman
 Paquete
 Parmar
+Pastra
 Pengyu
 Persero
 Phaidon
@@ -452,6 +453,7 @@ TPUs
 TSLA
 TSMC
 TSNE
+TTFB
 TTFT
 TTH
 TTT
@@ -555,6 +557,7 @@ alloydb
 antiword
 apikey
 apikeys
+apk
 appspot
 appuser
 apredict
@@ -719,6 +722,7 @@ etils
 eur
 evals
 evse
+evt
 expl
 faiss
 fastapi
@@ -856,6 +860,7 @@ kenleejr
 keras
 keychain
 kfp
+khz
 kickstart
 konnte
 kotlin
@@ -921,6 +926,7 @@ mrag
 mrr
 mrtydi
 msmarco
+msr
 multitool
 mvn
 mvnw
@@ -948,6 +954,7 @@ newaxis
 newaxisngram
 nfcorpus
 nfl
+nginx
 ngram
 ngrams
 nlp
@@ -972,6 +979,7 @@ onesie
 onesies
 openai
 openfda
+opsz
 osm
 osx
 outdir
@@ -1150,6 +1158,7 @@ timechart
 tion
 titlebar
 tobytes
+toolcall
 toself
 toset
 tqdm
@@ -1201,11 +1210,14 @@ webcam
 webclient
 webpage
 webpages
+webfonts
+webrtc
 websites
 weightage
 welcom
 werden
 whatsapp
+wght
 wiffle
 wikipedia
 wil
@@ -1215,6 +1227,7 @@ wip
 wishlist
 womens
 workarounds
+worklets
 wparam
 wscore
 wscores

diff --git a/.github/workflows/spelling.yaml b/.github/workflows/spelling.yaml
@@ -105,7 +105,7 @@ jobs:
           dictionary_source_prefixes: '{"cspell": "https://raw.githubusercontent.com/streetsidesoftware/cspell-dicts/main/dictionaries/"}'
           extra_dictionaries: |
             cspell:aws/dict/aws.txt
-            cspell:bash/src/bash-words.txt    
+            cspell:bash/samples/bash-words.txt
             cspell:companies/dict/companies.txt
             cspell:css/dict/css.txt
             cspell:data-science/dict/data-science-models.txt

diff --git a/audio/speech/use-cases/podcast/multi-speaker-podcast.ipynb b/audio/speech/use-cases/podcast/multi-speaker-podcast.ipynb
@@ -103,6 +103,7 @@
         "## Overview\n",
         "\n",
         "This notebook demonstrates how to use the [Gemini API in Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/overview) to generate an engaging multi-speaker podcast using studio voices in the [Text-to-Speech API](https://cloud.google.com/text-to-speech). \n",
+        "Note: [Generate dialogue with multiple speakers](https://cloud.google.com/text-to-speech/docs/create-dialogue-with-multispeakers) is only available to projects in allowlist. Please [contact Google Cloud](https://cloud.google.com/contact) if you want to use this feature.\n",
         "\n",
         "This can be useful for creating interviews, interactive storytelling, video games, e-learning platforms, and accessibility solutions.\n",
         "\n",

diff --git a/gemini/chat-completions/intro_chat_completions_api.ipynb b/gemini/chat-completions/intro_chat_completions_api.ipynb
@@ -130,13 +130,13 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "id": "tFy3H3aPgx12"
       },
       "outputs": [],
       "source": [
-        "%pip install --upgrade --quiet openai"
+        "%pip install --upgrade --quiet openai google-auth requests"
       ]
     },
     {
@@ -188,7 +188,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 2,
       "metadata": {
         "id": "NyKGtVQjgx13"
       },
@@ -217,14 +217,19 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 3,
       "metadata": {
         "id": "Nqwi-5ufWp_B"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "LOCATION = \"us-central1\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type: \"string\", placeholder: \"[your-project-id]\", isTemplate: true}\n",
+        "if not PROJECT_ID or PROJECT_ID == \"[your-project-id]\":\n",
+        "    PROJECT_ID = str(os.environ.get(\"GOOGLE_CLOUD_PROJECT\"))\n",
+        "\n",
+        "LOCATION = os.environ.get(\"GOOGLE_CLOUD_REGION\", \"us-central1\")"
       ]
     },
     {
@@ -254,7 +259,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 4,
       "metadata": {
         "id": "kolJkBLdHaw0"
       },
@@ -272,12 +277,12 @@
       "source": [
         "#### Authentication\n",
         "\n",
-        "You can request an access token from the default credentials for the current environment. Note that the access token lives for 1 hour by default (https://cloud.google.com/docs/authentication/token-types#at-lifetime); after expiration, it must be refreshed.\n"
+        "You can request an access token from the default credentials for the current environment. Note that the access token lives for [1 hour by default](https://cloud.google.com/docs/authentication/token-types#at-lifetime); after expiration, it must be refreshed.\n"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 5,
       "metadata": {
         "id": "i0qceuiQEPHv"
       },
@@ -299,7 +304,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 6,
       "metadata": {
         "id": "c-MRhsnlj6iw"
       },
@@ -319,12 +324,16 @@
       "source": [
         "#### Gemini models\n",
         "\n",
-        "You can experiment with [various supported Gemini models](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-gemini-using-openai-library#supported_models). If you are not sure which model to use, then try `gemini-1.5-flash`. `gemini-1.5-flash` is optimized for multimodal use cases where speed and cost are important."
+        "You can experiment with [various supported Gemini models](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/call-gemini-using-openai-library#supported_models).\n",
+        "\n",
+        "If you are not sure which model to use, then try `gemini-1.5-flash`.\n",
+        "\n",
+        "`gemini-1.5-flash` is optimized for multimodal use cases where speed and cost are important."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 7,
       "metadata": {
         "id": "r7OhyH46H2H5"
       },
@@ -348,7 +357,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 8,
       "metadata": {
         "id": "JQTWLCzoHyUA"
       },
@@ -370,7 +379,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 9,
       "metadata": {
         "id": "DdfWBfggOvtf"
       },
@@ -390,7 +399,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 10,
       "metadata": {
         "id": "LxpdxYCxH51u"
       },
@@ -410,7 +419,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 11,
       "metadata": {
         "id": "zOwEvNkCMiMF"
       },
@@ -434,7 +443,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 13,
       "metadata": {
         "id": "3hO8yLqnJEgh"
       },
@@ -447,7 +456,7 @@
         ")\n",
         "\n",
         "for chunk in response:\n",
-        "    print(chunk.choices[0].delta.content)"
+        "    print(chunk.choices[0].delta.content, end=\"\")"
       ]
     },
     {
@@ -464,7 +473,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 15,
       "metadata": {
         "id": "KOIu1Me-PQ6e"
       },
@@ -489,7 +498,7 @@
         "    ],\n",
         ")\n",
         "\n",
-        "print(response.choices[0].message.content)"
+        "Markdown(response.choices[0].message.content)"
       ]
     },
     {
@@ -509,7 +518,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 18,
       "metadata": {
         "id": "arshz2C4W_ck"
       },
@@ -535,22 +544,21 @@
         "    }\n",
         "]\n",
         "\n",
-        "messages = []\n",
-        "messages.append(\n",
+        "messages = [\n",
         "    {\n",
         "        \"role\": \"system\",\n",
         "        \"content\": \"Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\",\n",
-        "    }\n",
-        ")\n",
-        "messages.append({\"role\": \"user\", \"content\": \"What is the weather in Boston?\"})\n",
+        "    },\n",
+        "    {\"role\": \"user\", \"content\": \"What is the weather in Boston?\"},\n",
+        "]\n",
         "\n",
         "response = client.chat.completions.create(\n",
         "    model=MODEL_ID,\n",
         "    messages=messages,\n",
         "    tools=tools,\n",
         ")\n",
         "\n",
-        "print(print(response.choices[0].message.tool_calls))"
+        "print(response.choices[0].message.tool_calls)"
       ]
     },
     {
@@ -568,7 +576,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 19,
       "metadata": {
         "id": "GoEv7CKNXZu1"
       },
@@ -594,14 +602,13 @@
         "    }\n",
         "]\n",
         "\n",
-        "messages = []\n",
-        "messages.append(\n",
+        "messages = [\n",
         "    {\n",
         "        \"role\": \"system\",\n",
         "        \"content\": \"Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.\",\n",
-        "    }\n",
-        ")\n",
-        "messages.append({\"role\": \"user\", \"content\": \"What is the weather in Boston?\"})\n",
+        "    },\n",
+        "    {\"role\": \"user\", \"content\": \"What is the weather in Boston?\"},\n",
+        "]\n",
         "\n",
         "response = client.chat.completions.create(\n",
         "    model=MODEL_ID,\n",