oss(py): integrations work

pipeline/preprocessors/link_map.py

@@ -147,17 +147,36 @@ class LinkMap(TypedDict):
             # Integrations
             # langchain-openai
             "langchain-openai": "integrations/langchain_openai",
-            "BaseChatOpenAI": "integrations/langchain_openai/BaseChatOpenAI/",
-            "ChatOpenAI": "integrations/langchain_openai/ChatOpenAI/",
-            "AzureChatOpenAI": "integrations/langchain_openai/AzureChatOpenAI/",
-            "OpenAI": "integrations/langchain_openai/OpenAI/",
-            "AzureOpenAI": "integrations/langchain_openai/AzureOpenAI/",
-            "OpenAIEmbeddings": "integrations/langchain_openai/OpenAIEmbeddings/",
-            "AzureOpenAIEmbeddings": "integrations/langchain_openai/AzureOpenAIEmbeddings/",
+            "BaseChatOpenAI": "integrations/langchain_openai/BaseChatOpenAI",
+            "ChatOpenAI": "integrations/langchain_openai/ChatOpenAI",
+            "AzureChatOpenAI": "integrations/langchain_openai/AzureChatOpenAI",
+            "OpenAI": "integrations/langchain_openai/OpenAI",
+            "AzureOpenAI": "integrations/langchain_openai/AzureOpenAI",
+            "OpenAIEmbeddings": "integrations/langchain_openai/OpenAIEmbeddings",
+            "AzureOpenAIEmbeddings": "integrations/langchain_openai/AzureOpenAIEmbeddings",
             # langchain-anthropic
             "langchain-anthropic": "integrations/langchain_anthropic",
-            "ChatAnthropic": "integrations/langchain_anthropic/ChatAnthropic/",
-            "AnthropicLLM": "integrations/langchain_anthropic/AnthropicLLM/",
+            "ChatAnthropic": "integrations/langchain_anthropic/ChatAnthropic",
+            "AnthropicLLM": "integrations/langchain_anthropic/AnthropicLLM",
+            # langchain-google
+            "langchain-google": "integrations/langchain_google",
+            "langchain-google-genai": "integrations/langchain_google_genai",
+            "ChatGoogleGenerativeAI": "integrations/langchain_google_genai/#langchain_google_genai.ChatGoogleGenerativeAI",
+            "langchain-google-vertexai": "integrations/langchain_google_vertexai",
+            "ChatVertexAI": "integrations/langchain_google_vertexai/#langchain_google_vertexai.ChatVertexAI",
+            "langchain-google-community": "integrations/langchain_google_community/",
+            # langchain-ollama
+            "langchain-ollama": "integrations/langchain_ollama",
+            "ChatOllama": "integrations/langchain_ollama/#langchain_ollama.ChatOllama",
+            # langchain-xai
+            "langchain-xai": "integrations/langchain_xai",
+            "ChatXAI": "integrations/langchain_xai/#langchain_xai.ChatXAI",
+            # langchain-groq
+            "langchain-groq": "integrations/langchain_groq",
+            "ChatGroq": "integrations/langchain_groq/#langchain_groq.ChatGroq",
+            # langchain-deepseek
+            "langchain-deepseek": "integrations/langchain_deepseek",
+            "ChatDeepSeek": "integrations/langchain_deepseek/#langchain_deepseek.ChatDeepSeek",
             # Models
             "init_chat_model": "langchain/models/#langchain.chat_models.init_chat_model",
             "init_chat_model(model)": "langchain/models/#langchain.chat_models.init_chat_model(model)",

src/oss/javascript/integrations/chat/google_generative_ai.mdx

@@ -74,7 +74,7 @@ Now we can instantiate our model object and generate chat completions:
 import { ChatGoogleGenerativeAI } from "@langchain/google-genai"
 
 const llm = new ChatGoogleGenerativeAI({
-    model: "gemini-1.5-pro",
+    model: "gemini-2.5-pro",
     temperature: 0,
     maxRetries: 2,
     // other params...
@@ -168,7 +168,7 @@ import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
 import { HarmBlockThreshold, HarmCategory } from "@google/generative-ai";
 
 const llmWithSafetySettings = new ChatGoogleGenerativeAI({
-  model: "gemini-1.5-pro",
+  model: "gemini-2.5-pro",
   temperature: 0,
   safetySettings: [
     {
@@ -255,7 +255,7 @@ const searchRetrievalTool: GoogleSearchRetrievalTool = {
   }
 };
 const searchRetrievalModel = new ChatGoogleGenerativeAI({
-  model: "gemini-1.5-pro",
+  model: "gemini-2.5-pro",
   temperature: 0,
   maxRetries: 0,
 }).bindTools([searchRetrievalTool]);
@@ -453,7 +453,7 @@ const codeExecutionTool: CodeExecutionTool = {
   codeExecution: {}, // Simply pass an empty object to enable it.
 };
 const codeExecutionModel = new ChatGoogleGenerativeAI({
-  model: "gemini-1.5-pro",
+  model: "gemini-2.5-pro",
   temperature: 0,
   maxRetries: 0,
 }).bindTools([codeExecutionTool]);
@@ -564,7 +564,7 @@ const fileResult = await fileManager.uploadFile(pathToVideoFile, {
 
 // creates cached content AFTER uploading is finished
 const cachedContent = await cacheManager.create({
-    model: "models/gemini-1.5-flash-001",
+    model: "models/gemini-2.5-flash",
     displayName: displayName,
     systemInstruction: "You are an expert video analyzer, and your job is to answer " +
       "the user's query based on the video file you have access to.",
@@ -594,7 +594,6 @@ await model.invoke("Summarize the video");
 
 **Note**
 
-- Context caching supports both Gemini 1.5 Pro and Gemini 1.5 Flash. Context caching is only available for stable models with fixed versions (for example, gemini-1.5-pro-001). You must include the version postfix (for example, the -001 in gemini-1.5-pro-001).
 - The minimum input token count for context caching is 32,768, and the maximum is the same as the maximum for the given model.
 
 ## Gemini Prompting FAQs

src/oss/javascript/integrations/chat/google_vertex_ai.mdx

@@ -172,7 +172,7 @@ const searchRetrievalTool = {
 };
 
 const searchRetrievalModel = new ChatVertexAI({
-  model: "gemini-1.5-pro",
+  model: "gemini-2.5-pro",
   temperature: 0,
   maxRetries: 0,
 }).bindTools([searchRetrievalTool]);
@@ -218,7 +218,7 @@ const searchRetrievalToolWithDataset = {
 };
 
 const searchRetrievalModelWithDataset = new ChatVertexAI({
-  model: "gemini-1.5-pro",
+  model: "gemini-2.5-pro",
   temperature: 0,
   maxRetries: 0,
 }).bindTools([searchRetrievalToolWithDataset]);
@@ -248,7 +248,7 @@ Once you've created a cache, you can pass its id in as a runtime param as follow
 import { ChatVertexAI } from "@langchain/google-vertexai";
 
 const modelWithCachedContent = new ChatVertexAI({
-  model: "gemini-1.5-pro-002",
+  model: "gemini-2.5-pro-002",
   location: "us-east5",
 });
 
@@ -262,7 +262,7 @@ You can also bind this field directly onto the model instance:
 
 ```typescript
 const modelWithBoundCachedContent = new ChatVertexAI({
-  model: "gemini-1.5-pro-002",
+  model: "gemini-2.5-pro-002",
   location: "us-east5",
 }).bind({
   cachedContent:

src/oss/javascript/integrations/chat/index.mdx

@@ -143,7 +143,7 @@ title: Chat models
         import { ChatVertexAI } from "@langchain/google-vertexai";
 
         const model = new ChatVertexAI({
-        model: "gemini-1.5-flash",
+        model: "gemini-2.5-flash",
         temperature: 0
         });
         ```

src/oss/javascript/integrations/llms/google_vertex_ai.mdx

@@ -11,7 +11,7 @@ You may be looking for [this page instead](/oss/integrations/chat/google_vertex_
 </Warning>
 
 
-[Google Vertex](https://cloud.google.com/vertex-ai) is a service that exposes all foundation models available in Google Cloud, like `gemini-1.5-pro`, `gemini-1.5-flash`, etc.
+[Google Vertex](https://cloud.google.com/vertex-ai) is a service that exposes all foundation models available in Google Cloud, like `gemini-2.5-pro`, `gemini-2.5-flash`, etc.
 
 This will help you get started with VertexAI completion models (LLMs) using LangChain. For detailed documentation on `VertexAI` features and configuration options, please refer to the [API reference](https://api.js.langchain.com/classes/langchain_google_vertexai.VertexAI.html).
 

src/oss/javascript/integrations/providers/google.mdx

@@ -9,7 +9,7 @@ and [AI Studio](https://aistudio.google.com/)
 
 ### Gemini Models
 
-Access Gemini models such as `gemini-1.5-pro` and `gemini-2.0-flex` through the [`ChatGoogleGenerativeAI`](/oss/integrations/chat/google_generative_ai),
+Access Gemini models such as `gemini-2.5-pro` and `gemini-2.0-flex` through the [`ChatGoogleGenerativeAI`](/oss/integrations/chat/google_generative_ai),
 or if using VertexAI, via the [`ChatVertexAI`](/oss/integrations/chat/google_vertex_ai) class.
 
 <Tip>
@@ -97,7 +97,7 @@ import { ChatVertexAI } from "@langchain/google-vertexai";
 // import { ChatVertexAI } from "@langchain/google-vertexai-web";
 
 const model = new ChatVertexAI({
-  model: "gemini-1.0-pro",
+  model: "gemini-2.5-pro",
   maxOutputTokens: 2048,
 });
 

src/oss/python/integrations/chat/anthropic.mdx

@@ -1,9 +1,8 @@
 ---
 title: ChatAnthropic
+description: Get started using Anthropic [chat models](/oss/langchain/models) in LangChain.
 ---
 
-This guide provides a quick overview for getting started with Claude [chat models](/oss/langchain/models).
-
 You can find information about Anthropic's latest models, their costs, context windows, and supported input types in the [Claude](https://docs.claude.com/en/docs/about-claude/models/overview) docs.
 
 <Tip>
@@ -49,7 +48,7 @@ To access Anthropic (Claude) models you'll need to install the `langchain-anthro
 
 ### Credentials
 
-Head to [console.anthropic.com/](https://console.anthropic.com) to sign up for Anthropic and generate an API key. Once you've done this set the `ANTHROPIC_API_KEY` environment variable:
+Head to the [Claude console](https://console.anthropic.com) to sign up and generate a Claude API key. Once you've done this set the `ANTHROPIC_API_KEY` environment variable:
 
 ```python
 import getpass
@@ -145,7 +144,7 @@ response.content
   'type': 'tool_use'}]
 ```
 
-Using `content_blocks` will render the content in a standard format that is consistent across other model providers:
+Using `content_blocks` will render the content in a standard format that is consistent across other model providers. Read more about [content blocks](/oss/langchain/messages#standard-content-blocks).
 
 ```python
 response.content_blocks
@@ -306,7 +305,7 @@ print(json.dumps(response.content_blocks, indent=2))
 
 ## Prompt caching
 
-Anthropic supports [caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching) of [elements of your prompts](https://docs.claude.com/en/docs/build-with-claude/prompt-caching#what-can-be-cached), including messages, tool definitions, tool results, images and documents. This allows you to re-use large documents, instructions, [few-shot documents](/langsmith/create-few-shot-evaluators), and other data to reduce latency and costs.
+Anthropic supports [caching](https://docs.claude.com/en/docs/build-with-claude/prompt-caching) of elements of your prompts, including messages, tool definitions, tool results, images and documents. This allows you to re-use large documents, instructions, [few-shot documents](/langsmith/create-few-shot-evaluators), and other data to reduce latency and costs.
 
 To enable caching on an element of a prompt, mark its associated content block using the `cache_control` key. See examples below:
 
@@ -400,7 +399,7 @@ Second:
 
 ### Tools
 
-```python
+```python expandable
 from langchain_anthropic import convert_to_anthropic_tool
 from langchain.tools import tool
 

src/oss/python/integrations/chat/azure_chat_openai.mdx

@@ -1,9 +1,8 @@
 ---
 title: AzureChatOpenAI
+description: Get started using OpenAI [chat models](/oss/langchain/models) via Azure in LangChain.
 ---
 
-This guide provides a quick overview for getting started with OpenAI [chat models](/oss/langchain/models) on Azure.
-
 You can find information about Azure OpenAI's latest models and their costs, context windows, and supported input types in the [Azure docs](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models).
 
 <Info>
@@ -32,6 +31,12 @@ You can find information about Azure OpenAI's latest models and their costs, con
     features, or head to the @[`AzureChatOpenAI`] API reference.
 </Note>
 
+<Tip>
+    **API Reference**
+
+    For detailed documentation of all features and configuration options, head to the @[`AzureChatOpenAI`] API reference.
+</Tip>
+
 ## Overview
 
 ### Integration details

src/oss/python/integrations/chat/deepseek.mdx

@@ -1,12 +1,18 @@
 ---
 title: ChatDeepSeek
+description: Get started using DeepSeek [chat models](/oss/langchain/models) in LangChain.
 ---
 
-This will help you get started with DeepSeek's hosted [chat models](/oss/langchain/models). For detailed documentation of all ChatDeepSeek features and configurations head to the [API reference](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html).
+This will help you get started with DeepSeek's hosted [chat models](/oss/langchain/models).
 
 <Tip>
-**DeepSeek's models are open source and can be run locally (e.g. in [Ollama](./ollama.ipynb)) or on other inference providers (e.g. [Fireworks](./fireworks.ipynb), [Together](./together.ipynb)) as well.**
+    **API Reference**
 
+    For detailed documentation of all features and configuration options, head to the @[`ChatDeepSeek`] API reference.
+</Tip>
+
+<Tip>
+    **DeepSeek's models are open source and can be run locally (e.g. in [Ollama](./ollama.ipynb)) or on other inference providers (e.g. [Fireworks](./fireworks.ipynb), [Together](./together.ipynb)) as well.**
 </Tip>
 
 ## Overview
@@ -15,7 +21,7 @@ This will help you get started with DeepSeek's hosted [chat models](/oss/langcha
 
 | Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/deepseek) | Downloads | Version |
 | :--- | :--- | :---: | :---: |  :---: | :---: | :---: |
-| [ChatDeepSeek](https://python.langchain.com/api_reference/deepseek/chat_models/langchain_deepseek.chat_models.ChatDeepSeek.html) | [langchain-deepseek](https://python.langchain.com/api_reference/deepseek/) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-deepseek?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-deepseek?style=flat-square&label=%20) |
+| @[`ChatDeepSeek`] | @[`langchain-deepseek`] | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-deepseek?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-deepseek?style=flat-square&label=%20) |
 
 ### Model features