docs[patch],examples[patch]: Add tooltip with note about unified model params (#5042)

* docs[patch],examples[patch]: Add tooltip with note about unified model params

* chore: lint files

* revert moving back to model name changes

* more

* chore: lint files

Author: bracesproul

docs/core_docs/docs/expression_language/get_started.mdx

@@ -27,6 +27,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/openai @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <CodeBlock language="typescript">{BasicExample}</CodeBlock>
 
 :::tip

docs/core_docs/docs/get_started/quickstart.mdx

@@ -54,6 +54,10 @@ We will cover these at a high level, but keep in mind there is a lot more to eac
 
 import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 

docs/core_docs/docs/integrations/chat/anthropic.mdx

@@ -21,6 +21,10 @@ Set it as an environment variable named `ANTHROPIC_API_KEY`, or pass it into the
 
 ## Usage
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 You can initialize an instance like this:
 
 import CodeBlock from "@theme/CodeBlock";

docs/core_docs/docs/integrations/chat/anthropic_tools.mdx

@@ -27,6 +27,10 @@ npm install @langchain/anthropic
 
 You can initialize this wrapper the same way you'd initialize a standard `ChatAnthropic` instance:
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ```typescript
 import { ChatAnthropicTools } from "@langchain/anthropic/experimental";
 

docs/core_docs/docs/integrations/chat/azure.mdx

@@ -29,6 +29,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <CodeBlock language="typescript">{AzureOpenAI}</CodeBlock>
 
 If your instance is hosted under a domain other than the default `openai.azure.com`, you'll need to use the alternate `AZURE_OPENAI_BASE_PATH` environment variable.

docs/core_docs/docs/integrations/chat/bedrock.mdx

@@ -34,6 +34,10 @@ npm install @aws-crypto/sha256-js @smithy/protocol-http @smithy/signature-v4 @sm
 
 ## Usage
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 Currently, only Anthropic, Cohere, and Mistral models are supported with the chat model integration. For foundation models from AI21 or Amazon, see [the text generation Bedrock variant](/docs/integrations/llms/bedrock).
 
 import CodeBlock from "@theme/CodeBlock";

docs/core_docs/docs/integrations/chat/cloudflare_workersai.mdx

@@ -25,4 +25,8 @@ npm install @langchain/cloudflare
 import CodeBlock from "@theme/CodeBlock";
 import Example from "@examples/models/chat/integration_cloudflare_workersai.ts";
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <CodeBlock language="typescript">{Example}</CodeBlock>

docs/core_docs/docs/integrations/chat/fireworks.mdx

@@ -16,6 +16,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 import Fireworks from "@examples/models/chat/integration_fireworks.ts";
 
 <CodeBlock language="typescript">{Fireworks}</CodeBlock>

docs/core_docs/docs/integrations/chat/google_generativeai.mdx

@@ -31,6 +31,10 @@ npm install @langchain/google-genai
 
 ## Usage
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 import GoogleGenerativeAI from "@examples/models/chat/googlegenerativeai.ts";
 
 <CodeBlock language="typescript">{GoogleGenerativeAI}</CodeBlock>

docs/core_docs/docs/integrations/chat/google_palm.mdx

@@ -22,6 +22,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install google-auth-library @google-ai/generativelanguage @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 Create an **API key** from [Google MakerSuite](https://makersuite.google.com/app/apikey). You can then set
 the key as `GOOGLE_PALM_API_KEY` environment variable or pass it as `apiKey` parameter while instantiating
 the model.

docs/core_docs/docs/integrations/chat/google_vertex_ai.mdx

@@ -25,6 +25,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/google-vertexai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 You should make sure the Vertex AI API is
 enabled for the relevant project and that you've authenticated to
 Google Cloud using one of these methods:

docs/core_docs/docs/integrations/chat/groq.mdx

@@ -20,6 +20,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/groq
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ## Usage
 
 import ChatGroqExample from "@examples/models/chat/chat_groq.ts";

docs/core_docs/docs/integrations/chat/minimax.mdx

@@ -22,6 +22,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ## Basic usage
 
 import Minimax from "@examples/models/chat/integration_minimax.ts";

docs/core_docs/docs/integrations/chat/mistral.mdx

@@ -37,6 +37,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/mistralai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ## Usage
 
 When sending chat messages to mistral, there are a few requirements to follow:

docs/core_docs/docs/integrations/chat/openai.mdx

@@ -18,6 +18,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <CodeBlock language="typescript">{OpenAI}</CodeBlock>
 
 If you're part of an organization, you can set `process.env.OPENAI_ORGANIZATION` with your OpenAI organization id, or pass it in as `organization` when

docs/core_docs/docs/integrations/chat/togetherai.mdx

@@ -25,6 +25,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 import TogetherAI from "@examples/models/chat/integration_togetherai.ts";
 
 <CodeBlock language="typescript">{TogetherAI}</CodeBlock>

docs/core_docs/docs/integrations/llms/azure.mdx

@@ -16,6 +16,10 @@ You'll first need to install the [`@langchain/azure-openai`](https://www.npmjs.c
 npm install -S @langchain/azure-openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 You'll also need to have an Azure OpenAI instance deployed. You can deploy a version on Azure Portal following [this guide](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal).
 
 Once you have your instance running, make sure you have the endpoint and key. You can find them in the Azure Portal, under the "Keys and Endpoint" section of your instance.

docs/core_docs/docs/integrations/llms/huggingface_inference.mdx

@@ -6,6 +6,10 @@ Here's an example of calling a HugggingFaceInference model as an LLM:
 npm install @huggingface/inference@2
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ```typescript
 import { HuggingFaceInference } from "langchain/llms/hf";
 

docs/core_docs/docs/integrations/llms/openai.mdx

@@ -10,6 +10,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ```typescript
 import { OpenAI } from "@langchain/openai";
 

docs/core_docs/docs/integrations/text_embedding/azure_openai.mdx

@@ -22,6 +22,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install -S @langchain/azure-openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 You'll also need to have an Azure OpenAI instance deployed. You can deploy a version on Azure Portal following [this guide](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal).
 
 Once you have your instance running, make sure you have the endpoint and key. You can find them in the Azure Portal, under the "Keys and Endpoint" section of your instance.

docs/core_docs/docs/integrations/text_embedding/bedrock.mdx

@@ -24,6 +24,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/community
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 ## Usage
 
 The `BedrockEmbeddings` class uses the AWS Bedrock API to generate embeddings for a given text. It strips new line characters from the text as recommended.

docs/core_docs/docs/mdx_components/unified_model_params_tooltip.mdx

@@ -0,0 +1,3 @@
+:::tip
+We're unifying model params across all packages. We now suggest using `model` instead of `modelName`, and `apiKey` for API keys.
+:::

docs/core_docs/docs/modules/model_io/chat/caching.mdx

@@ -9,6 +9,10 @@ LangChain provides an optional caching layer for chat models. This is useful for
 It can save you money by reducing the number of API calls you make to the LLM provider, if you're often requesting the same completion multiple times.
 It can speed up your application by reducing the number of API calls you make to the LLM provider.
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 import CodeBlock from "@theme/CodeBlock";
 
 ```typescript

docs/core_docs/docs/modules/model_io/chat/custom_chat.mdx

@@ -15,7 +15,7 @@ You can also implement the following optional method:
 
 - A `_streamResponseChunks` method that returns an `AsyncGenerator` and yields [`ChatGenerationChunks`](https://api.js.langchain.com/classes/langchain_core_outputs.ChatGenerationChunk.html). This allows the LLM to support streaming outputs.
 
-Let’s implement a very simple custom chat model that just echoes back the first `n` characters of the input.
+Let's implement a very simple custom chat model that just echoes back the first `n` characters of the input.
 
 ```typescript
 import {

docs/core_docs/docs/modules/model_io/chat/quick_start.mdx

@@ -14,6 +14,10 @@ import Tabs from "@theme/Tabs";
 import TabItem from "@theme/TabItem";
 import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>
 

docs/core_docs/docs/modules/model_io/chat/streaming.mdx

@@ -22,6 +22,10 @@ import IntegrationInstallTooltip from "@mdx_components/integration_install_toolt
 npm install @langchain/openai
 ```
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <CodeBlock language="typescript">{StreamMethodExample}</CodeBlock>
 
 For models that do not support streaming, the entire response will be returned as a single chunk.

docs/core_docs/docs/modules/model_io/quick_start.mdx

@@ -16,6 +16,10 @@ import TabItem from "@theme/TabItem";
 import CodeBlock from "@theme/CodeBlock";
 import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
 
+import UnifiedModelParamsTooltip from "@mdx_components/unified_model_params_tooltip.mdx";
+
+<UnifiedModelParamsTooltip></UnifiedModelParamsTooltip>
+
 <Tabs groupId="preferredModel">
   <TabItem value="openai" label="OpenAI" default>