fix: use new Google model names in examples (#32288)

Author: mdrxy

cookbook/Multi_modal_RAG_google.ipynb

@@ -144,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "kWDWfSDBMPl8",
    "metadata": {},
    "outputs": [
@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-2.0-flash-lite-001\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-2.5-flash\", max_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -235,7 +235,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "PeK9bzXv3olF",
    "metadata": {},
    "outputs": [],
@@ -254,7 +254,7 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-2.0-flash\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model=\"gemini-2.5-flash\", max_tokens=1024)\n",
     "\n",
     "    msg = model.invoke(\n",
     "        [\n",
@@ -431,7 +431,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "GlwCErBaCKQW",
    "metadata": {},
    "outputs": [],
@@ -553,7 +553,7 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-2.0-flash\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-2.5-flash\", max_tokens=1024)\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",

docs/docs/how_to/multimodal_inputs.ipynb

@@ -373,7 +373,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "a0b91b29-dbd6-4c94-8f24-05471adc7598",
    "metadata": {},
    "outputs": [
@@ -397,7 +397,7 @@
     "\n",
     "\n",
     "# Pass to LLM\n",
-    "llm = init_chat_model(\"google_genai:gemini-2.0-flash-001\")\n",
+    "llm = init_chat_model(\"google_genai:gemini-2.5-flash\")\n",
     "\n",
     "message = {\n",
     "    \"role\": \"user\",\n",

docs/docs/how_to/response_metadata.ipynb

@@ -23,17 +23,17 @@
     {
      "data": {
       "text/plain": [
-       "{'token_usage': {'completion_tokens': 93,\n",
+       "{'token_usage': {'completion_tokens': 88,\n",
        "  'prompt_tokens': 16,\n",
-       "  'total_tokens': 109,\n",
+       "  'total_tokens': 104,\n",
        "  'completion_tokens_details': {'accepted_prediction_tokens': 0,\n",
        "   'audio_tokens': 0,\n",
        "   'reasoning_tokens': 0,\n",
        "   'rejected_prediction_tokens': 0},\n",
        "  'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}},\n",
        " 'model_name': 'gpt-4o-mini-2024-07-18',\n",
        " 'system_fingerprint': 'fp_34a54ae93c',\n",
-       " 'id': 'chatcmpl-ByJtse6I3U1lmVyPscLCjzydCvfDO',\n",
+       " 'id': 'chatcmpl-ByN1Qkvqb5fAGKKzXXxZ3rBlnqkWs',\n",
        " 'service_tier': 'default',\n",
        " 'finish_reason': 'stop',\n",
        " 'logprobs': None}"
@@ -69,14 +69,14 @@
     {
      "data": {
       "text/plain": [
-       "{'id': 'msg_017S9H7GMwA5RdZ1wHxzXoeX',\n",
+       "{'id': 'msg_01NTWnqvbNKSjGfqQL7xikau',\n",
        " 'model': 'claude-3-7-sonnet-20250219',\n",
        " 'stop_reason': 'end_turn',\n",
        " 'stop_sequence': None,\n",
        " 'usage': {'cache_creation_input_tokens': 0,\n",
        "  'cache_read_input_tokens': 0,\n",
        "  'input_tokens': 17,\n",
-       "  'output_tokens': 180,\n",
+       "  'output_tokens': 197,\n",
        "  'server_tool_use': None,\n",
        "  'service_tier': 'standard'},\n",
        " 'model_name': 'claude-3-7-sonnet-20250219'}"
@@ -100,30 +100,22 @@
    "id": "c1f24f69-18f6-43c1-8b26-3f88ec515259",
    "metadata": {},
    "source": [
-    "## Google VertexAI"
+    "## Google Generative AI"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "39549336-25f5-4839-9846-f687cd77e59b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'is_blocked': False,\n",
-       " 'safety_ratings': [],\n",
-       " 'usage_metadata': {'prompt_token_count': 10,\n",
-       "  'candidates_token_count': 55,\n",
-       "  'total_token_count': 65,\n",
-       "  'prompt_tokens_details': [{'modality': 1, 'token_count': 10}],\n",
-       "  'candidates_tokens_details': [{'modality': 1, 'token_count': 55}],\n",
-       "  'cached_content_token_count': 0,\n",
-       "  'cache_tokens_details': []},\n",
+       "{'prompt_feedback': {'block_reason': 0, 'safety_ratings': []},\n",
        " 'finish_reason': 'STOP',\n",
-       " 'avg_logprobs': -0.251378042047674,\n",
-       " 'model_name': 'gemini-2.0-flash-001'}"
+       " 'model_name': 'gemini-2.5-flash',\n",
+       " 'safety_ratings': []}"
       ]
      },
      "execution_count": 1,
@@ -132,9 +124,9 @@
     }
    ],
    "source": [
-    "from langchain_google_vertexai import ChatVertexAI\n",
+    "from langchain_google_genai import ChatGoogleGenerativeAI\n",
     "\n",
-    "llm = ChatVertexAI(model=\"gemini-2.0-flash-001\")\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.5-flash\")\n",
     "msg = llm.invoke(\"What's the oldest known example of cuneiform\")\n",
     "msg.response_metadata"
    ]
@@ -199,14 +191,14 @@
      "data": {
       "text/plain": [
        "{'token_usage': {'prompt_tokens': 13,\n",
-       "  'total_tokens': 219,\n",
-       "  'completion_tokens': 206},\n",
+       "  'total_tokens': 306,\n",
+       "  'completion_tokens': 293},\n",
        " 'model_name': 'mistral-small-latest',\n",
        " 'model': 'mistral-small-latest',\n",
        " 'finish_reason': 'stop'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/docs/integrations/chat/google_generative_ai.ipynb

@@ -19,7 +19,7 @@
     "\n",
     "Access Google's Generative AI models, including the Gemini family, directly via the Gemini API or experiment rapidly using Google AI Studio. The `langchain-google-genai` package provides the LangChain integration for these models. This is often the best starting point for individual developers.\n",
     "\n",
-    "For information on the latest models, their features, context windows, etc. head to the [Google AI docs](https://ai.google.dev/gemini-api/docs/models/gemini). All examples use the `gemini-2.0-flash` model. Gemini 2.5 Pro and 2.5 Flash can be used via  `gemini-2.5-pro-preview-03-25` and `gemini-2.5-flash-preview-04-17`. All model ids can be found in the [Gemini API docs](https://ai.google.dev/gemini-api/docs/models).\n",
+    "For information on the latest models, their features, context windows, etc. head to the [Google AI docs](https://ai.google.dev/gemini-api/docs/models/gemini). All model ids can be found in the [Gemini API docs](https://ai.google.dev/gemini-api/docs/models).\n",
     "\n",
     "### Integration details\n",
     "\n",
@@ -117,7 +117,7 @@
     "from langchain_google_genai import ChatGoogleGenerativeAI\n",
     "\n",
     "llm = ChatGoogleGenerativeAI(\n",
-    "    model=\"gemini-2.0-flash\",\n",
+    "    model=\"gemini-2.5-flash\",\n",
     "    temperature=0,\n",
     "    max_tokens=None,\n",
     "    timeout=None,\n",
@@ -242,7 +242,7 @@
     "\n",
     "### Image Input\n",
     "\n",
-    "Provide image inputs along with text using a `HumanMessage` with a list content format. The `gemini-2.0-flash` model can handle images."
+    "Provide image inputs along with text using a `HumanMessage` with a list content format. Make sure to use a model that supports image input, such as `gemini-2.5-flash`."
    ]
   },
   {
@@ -297,7 +297,7 @@
     "\n",
     "### Audio Input\n",
     "\n",
-    "Provide audio file inputs along with text. Use a model like `gemini-2.0-flash`."
+    "Provide audio file inputs along with text."
    ]
   },
   {
@@ -340,7 +340,7 @@
    "source": [
     "### Video Input\n",
     "\n",
-    "Provide video file inputs along with text. Use a model like `gemini-2.0-flash`."
+    "Provide video file inputs along with text."
    ]
   },
   {
@@ -384,7 +384,7 @@
    "source": [
     "### Image Generation (Multimodal Output)\n",
     "\n",
-    "The `gemini-2.0-flash` model can generate text and images inline (image generation is experimental). You need to specify the desired `response_modalities`."
+    "Certain models (such as `gemini-2.0-flash-preview-image-generation`) can generate text and images inline. You need to specify the desired `response_modalities`. See more information on the [Gemini API docs](https://ai.google.dev/gemini-api/docs/image-generation) for details."
    ]
   },
   {
@@ -830,7 +830,7 @@
    "source": [
     "from langchain_google_genai import ChatGoogleGenerativeAI\n",
     "\n",
-    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.0-flash\")\n",
+    "llm = ChatGoogleGenerativeAI(model=\"gemini-2.5-flash\")\n",
     "\n",
     "\n",
     "async def run_async_calls():\n",
@@ -900,7 +900,7 @@
    "source": [
     "## API reference\n",
     "\n",
-    "For detailed documentation of all ChatGoogleGenerativeAI features and configurations head to the API reference: https://python.langchain.com/api_reference/google_genai/chat_models/langchain_google_genai.chat_models.ChatGoogleGenerativeAI.html"
+    "For detailed documentation of all ChatGoogleGenerativeAI features and configurations head to the [API reference](https://python.langchain.com/api_reference/google_genai/chat_models/langchain_google_genai.chat_models.ChatGoogleGenerativeAI.html)."
    ]
   }
  ],

docs/docs/integrations/chat/google_vertex_ai_palm.ipynb

@@ -19,7 +19,7 @@
     "\n",
     "This page provides a quick overview for getting started with VertexAI [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatVertexAI features and configurations head to the [API reference](https://python.langchain.com/api_reference/google_vertexai/chat_models/langchain_google_vertexai.chat_models.ChatVertexAI.html).\n",
     "\n",
-    "ChatVertexAI exposes all foundational models available in Google Cloud, like `gemini-1.5-pro`, `gemini-1.5-flash`, etc. For a full and updated list of available models visit [VertexAI documentation](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/overview).\n",
+    "ChatVertexAI exposes all foundational models available in Google Cloud, like `gemini-2.5-pro`, `gemini-2.5-flash`, etc. For a full and updated list of available models visit [VertexAI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/models).\n",
     "\n",
     ":::info Google Cloud VertexAI vs Google PaLM\n",
     "\n",
@@ -60,7 +60,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
    "metadata": {},
    "outputs": [],
@@ -109,15 +109,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_google_vertexai import ChatVertexAI\n",
     "\n",
     "llm = ChatVertexAI(\n",
-    "    model=\"gemini-1.5-flash-001\",\n",
+    "    model=\"gemini-2.5-flash\",\n",
     "    temperature=0,\n",
     "    max_tokens=None,\n",
     "    max_retries=6,\n",
@@ -210,7 +210,7 @@
    "source": [
     "from langchain_google_vertexai import ChatVertexAI\n",
     "\n",
-    "llm = ChatVertexAI(model=\"gemini-2.0-flash-001\").bind_tools([{\"google_search\": {}}])\n",
+    "llm = ChatVertexAI(model=\"gemini-2.5-flash\").bind_tools([{\"google_search\": {}}])\n",
     "\n",
     "response = llm.invoke(\"What is today's news?\")"
    ]
@@ -237,7 +237,7 @@
    "source": [
     "from langchain_google_vertexai import ChatVertexAI\n",
     "\n",
-    "llm = ChatVertexAI(model=\"gemini-2.0-flash-001\").bind_tools([{\"code_execution\": {}}])\n",
+    "llm = ChatVertexAI(model=\"gemini-2.5-flash\").bind_tools([{\"code_execution\": {}}])\n",
     "\n",
     "response = llm.invoke(\"What is 3^3?\")"
    ]