feat(mistral): Mistral 1.3.1 migration

docs/core_docs/docs/integrations/chat/mistral.ipynb

@@ -23,7 +23,7 @@
         "\n",
         "[Mistral AI](https://mistral.ai/) is a platform that offers hosting for their powerful [open source models](https://docs.mistral.ai/getting-started/models/).\n",
         "\n",
-        "This will help you getting started with ChatMistralAI [chat models](/docs/concepts/chat_models). For detailed documentation of all ChatMistralAI features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_mistralai.ChatMistralAI.html).\n",
+        "This will help you getting started with ChatMistralAI [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatMistralAI features and configurations head to the [API reference](https://api.js.langchain.com/classes/langchain_mistralai.ChatMistralAI.html).\n",
         "\n",
         "## Overview\n",
         "### Integration details\n",
@@ -38,7 +38,7 @@
         "\n",
         "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
         "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: |\n",
-        "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | \n",
+        "| ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | \n",
         "\n",
         "## Setup\n",
         "\n",
@@ -88,7 +88,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
       "metadata": {},
       "outputs": [],
@@ -252,7 +252,7 @@
       "source": [
         "## Tool calling\n",
         "\n",
-        "Mistral's API supports [tool calling](/docs/concepts/tool_calling) for a subset of their models. You can see which models support tool calling [on this page](https://docs.mistral.ai/capabilities/function_calling/).\n",
+        "Mistral's API supports [tool calling](/docs/concepts#functiontool-calling) for a subset of their models. You can see which models support tool calling [on this page](https://docs.mistral.ai/capabilities/function_calling/).\n",
         "\n",
         "The examples below demonstrates how to use it:"
       ]
@@ -323,6 +323,117 @@
         "console.log(calcToolRes.tool_calls);"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "id": "85dcbecc",
+      "metadata": {},
+      "source": [
+        "## Hooks\n",
+        "\n",
+        "Mistral AI supports custom hooks for three events: beforeRequest, requestError, and reponse. Examples of the function signature for each hook type can be seen below:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "74b8b855",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "const beforeRequestHook = (req: Request): Request | void | Promise<Request | void> => {\n",
+        "    // Code to run before a request is processed by Mistral\n",
+        "};\n",
+        "\n",
+        "const requestErrorHook = (err: unknown, req: Request): void | Promise<void> => {\n",
+        "    // Code to run when an error occurs as Mistral is processing a request\n",
+        "};\n",
+        "\n",
+        "const responseHook = (res: Response, req: Request): void | Promise<void> => {\n",
+        "    // Code to run before Mistral sends a successful response\n",
+        "};"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "930df6c4",
+      "metadata": {},
+      "source": [
+        "To add these hooks to the chat model, either pass them as arguments and they are automatically added:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "8b8084f6",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatMistralAI } from \"@langchain/mistralai\" \n",
+        "\n",
+        "const modelWithHooks = new ChatMistralAI({\n",
+        "    model: \"mistral-large-latest\",\n",
+        "    temperature: 0,\n",
+        "    maxRetries: 2,\n",
+        "    beforeRequestHooks: [ beforeRequestHook ],\n",
+        "    requestErrorHooks: [ requestErrorHook ],\n",
+        "    responseHooks: [ responseHook ],\n",
+        "    // other params...\n",
+        "});"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "cc9478f3",
+      "metadata": {},
+      "source": [
+        "Or assign and add them manually after instantiation:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "daa70dc3",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatMistralAI } from \"@langchain/mistralai\" \n",
+        "\n",
+        "const model = new ChatMistralAI({\n",
+        "    model: \"mistral-large-latest\",\n",
+        "    temperature: 0,\n",
+        "    maxRetries: 2,\n",
+        "    // other params...\n",
+        "});\n",
+        "\n",
+        "model.beforeRequestHooks = [ ...model.beforeRequestHooks, beforeRequestHook ];\n",
+        "model.requestErrorHooks = [ ...model.requestErrorHooks, requestErrorHook ];\n",
+        "model.responseHooks = [ ...model.responseHooks, responseHook ];\n",
+        "\n",
+        "model.addAllHooksToHttpClient();"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "389f5159",
+      "metadata": {},
+      "source": [
+        "The method addAllHooksToHttpClient clears all currently added hooks before assigning the entire updated hook lists to avoid hook duplication.\n",
+        "\n",
+        "Hooks can be removed one at a time, or all hooks can be cleared from the model at once."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a56b64bb",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model.removeHookFromHttpClient(beforeRequestHook);\n",
+        "\n",
+        "model.removeAllHooksFromHttpClient();"
+      ]
+    },
     {
       "cell_type": "markdown",
       "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
@@ -354,4 +465,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 5
-}
+}

docs/core_docs/docs/integrations/llms/mistral.ipynb

@@ -24,7 +24,7 @@
         ":::\n",
         "\n",
         ":::caution\n",
-        "You are currently on a page documenting the use of Mistral models as [text completion models](/docs/concepts/text_llms). Many popular models available on Mistral are [chat completion models](/docs/concepts/chat_models).\n",
+        "You are currently on a page documenting the use of Mistral models as [text completion models](/docs/concepts/#llms). Many popular models available on Mistral are [chat completion models](/docs/concepts/#chat-models).\n",
         "\n",
         "You may be looking for [this page instead](/docs/integrations/chat/mistral/).\n",
         ":::\n",
@@ -271,6 +271,109 @@
         "console.log(customOutputParser(resWithParser));"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Hooks\n",
+        "\n",
+        "Mistral AI supports custom hooks for three events: beforeRequest, requestError, and reponse. Examples of the function signature for each hook type can be seen below:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "const beforeRequestHook = (req: Request): Request | void | Promise<Request | void> => {\n",
+        "    // Code to run before a request is processed by Mistral\n",
+        "};\n",
+        "\n",
+        "const requestErrorHook = (err: unknown, req: Request): void | Promise<void> => {\n",
+        "    // Code to run when an error occurs as Mistral is processing a request\n",
+        "};\n",
+        "\n",
+        "const responseHook = (res: Response, req: Request): void | Promise<void> => {\n",
+        "    // Code to run before Mistral sends a successful response\n",
+        "};"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "To add these hooks to the chat model, either pass them as arguments and they are automatically added:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatMistralAI } from \"@langchain/mistralai\" \n",
+        "\n",
+        "const modelWithHooks = new ChatMistralAI({\n",
+        "    model: \"mistral-large-latest\",\n",
+        "    temperature: 0,\n",
+        "    maxRetries: 2,\n",
+        "    beforeRequestHooks: [ beforeRequestHook ],\n",
+        "    requestErrorHooks: [ requestErrorHook ],\n",
+        "    responseHooks: [ responseHook ],\n",
+        "    // other params...\n",
+        "});"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "Or assign and add them manually after instantiation:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import { ChatMistralAI } from \"@langchain/mistralai\" \n",
+        "\n",
+        "const model = new ChatMistralAI({\n",
+        "    model: \"mistral-large-latest\",\n",
+        "    temperature: 0,\n",
+        "    maxRetries: 2,\n",
+        "    // other params...\n",
+        "});\n",
+        "\n",
+        "model.beforeRequestHooks = [ ...model.beforeRequestHooks, beforeRequestHook ];\n",
+        "model.requestErrorHooks = [ ...model.requestErrorHooks, requestErrorHook ];\n",
+        "model.responseHooks = [ ...model.responseHooks, responseHook ];\n",
+        "\n",
+        "model.addAllHooksToHttpClient();"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "The method addAllHooksToHttpClient clears all currently added hooks before assigning the entire updated hook lists to avoid hook duplication.\n",
+        "\n",
+        "Hooks can be removed one at a time, or all hooks can be cleared from the model at once."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "model.removeHookFromHttpClient(beforeRequestHook);\n",
+        "\n",
+        "model.removeAllHooksFromHttpClient();"
+      ]
+    },
     {
       "cell_type": "markdown",
       "id": "e9bdfcef",
@@ -307,4 +410,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 5
-}
+}