feat[openai]: responses API

docs/core_docs/docs/integrations/chat/openai.ipynb

@@ -664,6 +664,94 @@
         "}]);"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "id": "7139f50e",
+      "metadata": {},
+      "source": [
+        "## Responses API\n",
+        "\n",
+        ":::caution Compatibility\n",
+        "\n",
+        "The below points apply to `@langchain/openai>=0.4.5-rc.0`. Please see here for a [guide on upgrading](/docs/how_to/installation/#installing-integration-packages).\n",
+        "\n",
+        ":::\n",
+        "\n",
+        "OpenAI supports a [Responses](https://platform.openai.com/docs/guides/responses-vs-chat-completions) API that is oriented toward building [agentic](/docs/concepts/agents/) applications. It includes a suite of [built-in tools](https://platform.openai.com/docs/guides/tools?api-mode=responses), including web and file search. It also supports management of [conversation state](https://platform.openai.com/docs/guides/conversation-state?api-mode=responses), allowing you to continue a conversational thread without explicitly passing in previous messages.\n",
+        "\n",
+        "`ChatOpenAI` will route to the Responses API if one of these features is used. You can also specify `useResponsesAPI: true` when instantiating `ChatOpenAI`.\n",
+        "\n",
+        "### Built-in tools\n",
+        "\n",
+        "Equipping `ChatOpenAI` with built-in tools will ground its responses with outside information, such as via context in files or the web. The [AIMessage](/docs/concepts/messages/#aimessage) generated from the model will include information about the built-in tool invocation.\n",
+        "\n",
+        "#### Web search\n",
+        "\n",
+        "To trigger a web search, pass `{\"type\": \"web_search_preview\"}` to the model as you would another tool.\n",
+        "\n",
+        ":::tip\n",
+        "\n",
+        "You can also pass built-in tools as invocation params:\n",
+        "\n",
+        "```ts\n",
+        "llm.invoke(\"...\", { tools: [{ type: \"web_search_preview\" }] });\n",
+        "```\n",
+        "\n",
+        ":::\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "1b01f09a",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatOpenAI } from \"@langchain/openai\";\n",
+        "\n",
+        "const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" }).bindTools([\n",
+        "  { type: \"web_search_preview\" },\n",
+        "]);\n",
+        "\n",
+        "await llm.invoke(\"What was a positive news story from today?\");\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e62bae97",
+      "metadata": {},
+      "source": [
+        "Note that the response includes structured [content blocks](/docs/concepts/messages/#content-1) that include both the text of the response and OpenAI [annotations](https://platform.openai.com/docs/guides/tools-web-search?api-mode=responses#output-and-citations) citing its sources. The output message will also contain information from any tool invocations.\n",
+        "\n",
+        "#### File search\n",
+        "\n",
+        "To trigger a file search, pass a [file search tool](https://platform.openai.com/docs/guides/tools-file-search) to the model as you would another tool. You will need to populate an OpenAI-managed vector store and include the vector store ID in the tool definition. See [OpenAI documentation](https://platform.openai.com/docs/guides/tools-file-search) for more details.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "b70c671c",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatOpenAI } from \"@langchain/openai\";\n",
+        "\n",
+        "const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" }).bindTools([\n",
+        "  { type: \"file_search\", vector_store_ids: [\"vs...\"] },\n",
+        "]);\n",
+        "\n",
+        "await llm.invoke(\"Is deep research by OpenAI?\");\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e2a8378c",
+      "metadata": {},
+      "source": [
+        "As with [web search](#web-search), the response will include content blocks with citations. It will also include information from the built-in tool invocations."
+      ]
+    },
     {
       "cell_type": "markdown",
       "id": "0194ec1f",

langchain/package.json

@@ -457,6 +457,7 @@
     "openai": "^4.41.1",
     "peggy": "^3.0.2",
     "prettier": "^2.8.3",
+    "reflect-metadata": "^0.2.2",
     "release-it": "^17.6.0",
     "rimraf": "^5.0.1",
     "rollup": "^3.19.1",

libs/langchain-openai/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@langchain/openai",
-  "version": "0.4.4",
+  "version": "0.4.5-rc.0",
   "description": "OpenAI integrations for LangChain.js",
   "type": "module",
   "engines": {
@@ -36,7 +36,7 @@
   "license": "MIT",
   "dependencies": {
     "js-tiktoken": "^1.0.12",
-    "openai": "^4.77.0",
+    "openai": "^4.87.3",
     "zod": "^3.22.4",
     "zod-to-json-schema": "^3.22.3"
   },