Merge branch 'master' into eugene/responses_api_2

docs/docs/integrations/chat/openai.ipynb

@@ -397,6 +397,56 @@
     "For more on binding tools and tool call outputs, head to the [tool calling](/docs/how_to/function_calling) docs."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f06789fb-61e1-4b35-a2b5-2dea18c1a949",
+   "metadata": {},
+   "source": [
+    "### Structured output and tool calls\n",
+    "\n",
+    "OpenAI's [structured output](https://platform.openai.com/docs/guides/structured-outputs) feature can be used simultaneously with tool-calling. The model will either generate tool calls or a response adhering to a desired schema. See example below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15d2b6e0-f457-4abd-a4d5-08b210d09c04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "from pydantic import BaseModel\n",
+    "\n",
+    "\n",
+    "def get_weather(location: str) -> None:\n",
+    "    \"\"\"Get weather at a location.\"\"\"\n",
+    "    return \"It's sunny.\"\n",
+    "\n",
+    "\n",
+    "class OutputSchema(BaseModel):\n",
+    "    \"\"\"Schema for response.\"\"\"\n",
+    "\n",
+    "    answer: str\n",
+    "    justification: str\n",
+    "\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-4.1\")\n",
+    "\n",
+    "structured_llm = llm.bind_tools(\n",
+    "    [get_weather],\n",
+    "    response_format=OutputSchema,\n",
+    "    strict=True,\n",
+    ")\n",
+    "\n",
+    "# Response contains tool calls:\n",
+    "tool_call_response = structured_llm.invoke(\"What is the weather in SF?\")\n",
+    "\n",
+    "# structured_response.additional_kwargs[\"parsed\"] contains parsed output\n",
+    "structured_response = structured_llm.invoke(\n",
+    "    \"What weighs more, a pound of feathers or a pound of gold?\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "84833dd0-17e9-4269-82ed-550639d65751",

docs/docs/integrations/llms/sambanovacloud.ipynb

@@ -74,14 +74,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_community.llms.sambanova import SambaNovaCloud\n",
     "\n",
     "llm = SambaNovaCloud(\n",
-    "    model=\"Meta-Llama-3.1-70B-Instruct\",\n",
+    "    model=\"Meta-Llama-3.3-70B-Instruct\",\n",
     "    max_tokens_to_generate=1000,\n",
     "    temperature=0.01,\n",
     "    # top_k = 50,\n",

docs/docs/integrations/providers/sambanova.ipynb

@@ -130,7 +130,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "For a more detailed walkthrough of the SambaStudioEmbeddings component, see [this notebook](https://python.langchain.com/docs/integrations/text_embedding/sambanova/)"
+    "For a more detailed walkthrough of the SambaNovaCloudEmbeddings component, see [this notebook](https://python.langchain.com/docs/integrations/text_embedding/sambanova/)"
    ]
   },
   {

libs/partners/groq/tests/integration_tests/test_standard.py

@@ -29,14 +29,10 @@ class BaseTestGroq(ChatModelIntegrationTests):
         return True
 
 
-class TestGroqLlama(BaseTestGroq):
+class TestGroqGemma(BaseTestGroq):
     @property
     def chat_model_params(self) -> dict:
-        return {
+        return {"model": "gemma2-9b-it", "rate_limiter": rate_limiter}
-            "model": "llama-3.1-8b-instant",
-            "temperature": 0,
-            "rate_limiter": rate_limiter,
-        }
 
     @property
     def supports_json_mode(self) -> bool: