langchain-ai · mdrxy · Nov 4, 2025 · Nov 3, 2025 · Nov 3, 2025 · Nov 3, 2025
@@ -23,7 +23,7 @@ title: IBM
 
     [:octicons-arrow-right-24: Reference](./ChatWatsonx.md)
 
-- :material-message-text:{ .lg .middle } __`WatsonxLLM`__
+- :fontawesome-solid-i-cursor:{ .lg .middle } __`WatsonxLLM`__
 
     ---
 
@@ -39,7 +39,7 @@ title: IBM
 
     [:octicons-arrow-right-24: Reference](./WatsonxEmbeddings.md)
 
-- :fontawesome-solid-layer-group:{ .lg .middle } __`WatsonxRerank`__
+- :fontawesome-solid-download:{ .lg .middle } __`WatsonxRerank`__
 
     ---
 

@@ -31,31 +31,31 @@ title: OpenAI
 
     [:octicons-arrow-right-24: Reference](./AzureChatOpenAI.md)
 
-- :material-message-text:{ .lg .middle } __`OpenAI`__
+- :fontawesome-solid-i-cursor:{ .lg .middle } __`OpenAI`__
 
     ---
 
     (Legacy) OpenAI text completion models.
 
     [:octicons-arrow-right-24: Reference](./OpenAI.md)
 
-- :material-message-text:{ .lg .middle } __`AzureOpenAI`__
+- :fontawesome-solid-i-cursor:{ .lg .middle } __`AzureOpenAI`__
 
     ---
 
     Wrapper for (legacy) OpenAI text completion models hosted on Azure.
 
     [:octicons-arrow-right-24: Reference](./AzureChatOpenAI.md)
 
-- :material-message-text:{ .lg .middle } __`OpenAIEmbeddings`__
+- :fontawesome-solid-layer-group:{ .lg .middle } __`OpenAIEmbeddings`__
 
     ---
 
     OpenAI embedding models.
 
     [:octicons-arrow-right-24: Reference](./OpenAIEmbeddings.md)
 
-- :material-message-text:{ .lg .middle } __`OpenAIEmbeddings`__
+- :fontawesome-solid-layer-group:{ .lg .middle } __`AzureOpenAIEmbeddings`__
 
     ---
 

@@ -12,7 +12,7 @@ The aim of these examples is to show how to communicate with `watsonx.ai` models
 
 | Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/ibm/) | Downloads | Version |
 | :--- | :--- | :---: | :---: |  :---: | :---: | :---: |
-| [ChatWatsonx](https://python.langchain.com/api_reference/ibm/chat_models/langchain_ibm.chat_models.ChatWatsonx.html) | [langchain-ibm](https://python.langchain.com/api_reference/ibm/index.html) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
+| [`ChatWatsonx`](https://reference.langchain.com/python/integrations/langchain_ibm/ChatWatsonx/) | [`langchain-ibm`](https://reference.langchain.com/python/integrations/langchain_ibm/) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
 
 ### Model features
 
@@ -307,4 +307,4 @@ ai_msg.tool_calls
 
 ## API reference
 
-For detailed documentation of all `ChatWatsonx` features and configurations head to the [API reference](https://python.langchain.com/api_reference/ibm/chat_models/langchain_ibm.chat_models.ChatWatsonx.html).
+For detailed documentation of all `ChatWatsonx` features and configurations head to the [API reference](https://reference.langchain.com/python/integrations/langchain_ibm/ChatWatsonx/).
@@ -22,6 +22,7 @@ mode: wide
 | [`ChatBedrock`](/oss/integrations/chat/bedrock) | ✅ | ✅ | ❌ | ❌ | ❌ | [`langchain-aws`](https://reference.langchain.com/python/integrations/langchain_aws/) |
 | [`ChatHuggingFace`](/oss/integrations/chat/huggingface) | ✅ | ✅ | ❌ | ✅ | ❌ | [`langchain-huggingface`](https://reference.langchain.com/python/integrations/langchain_huggingface/) |
 | [`ChatOllama`](/oss/integrations/chat/ollama) | ✅ | ✅ | ✅ | ✅ | ❌ | [`langchain-ollama`](https://reference.langchain.com/python/integrations/langchain_ollama/) |
+| [`ChatWatsonx`](/oss/integrations/chat/ibm_watsonx) | ✅ | ✅ | ✅ | ❌ | ✅ | [`langchain-ibm`](https://reference.langchain.com/python/integrations/langchain_ibm/) |
 | [`ChatXAI`](/oss/integrations/chat/xai) | ✅ | ✅ | ❌ | ❌ | ❌ | [`langchain-xai`](https://reference.langchain.com/python/integrations/langchain_xai/) |
 | [`ChatNVIDIA`](/oss/integrations/chat/nvidia_ai_endpoints) | ✅ | ✅ | ✅ | ✅ | ✅ | [`langchain-nvidia-ai-endpoints`](https://reference.langchain.com/python/integrations/langchain_nvidia_ai_endpoints/) |
 | [`ChatCohere`](/oss/integrations/chat/cohere) | ✅ | ✅ | ❌ | ❌ | ❌ | [`langchain-cohere`](https://reference.langchain.com/python/integrations/langchain_cohere/) |

@@ -2,7 +2,7 @@
 title: IBM watsonx.ai
 ---
 
->[WatsonxLLM](https://ibm.github.io/watsonx-ai-python-sdk/fm_extensions.html#langchain) is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
+>[`WatsonxLLM`](https://ibm.github.io/watsonx-ai-python-sdk/fm_extensions.html#langchain) is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
 
 This example shows how to communicate with `watsonx.ai` models using `LangChain`.
 
@@ -12,7 +12,7 @@ This example shows how to communicate with `watsonx.ai` models using `LangChain`
 
 | Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/llms/ibm/) | Downloads | Version |
 | :--- | :--- | :---: | :---: |  :---: | :---: | :---: |
-| [WatsonxLLM](https://python.langchain.com/api_reference/ibm/llms/langchain_ibm.llms.WatsonxLLM.html) | [langchain-ibm](https://python.langchain.com/api_reference/ibm/index.html) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
+| [`WatsonxLLM`](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxLLM/) | [`langchain-ibm`](https://reference.langchain.com/python/integrations/langchain_ibm/) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
 
 ## Setup
 
@@ -211,4 +211,4 @@ llm_chain.invoke(topic)
 
 ## API reference
 
-For detailed documentation of all `WatsonxLLM` features and configurations head to the [API reference](https://python.langchain.com/api_reference/ibm/llms/langchain_ibm.llms.WatsonxLLM.html).
+For detailed documentation of all `WatsonxLLM` features and configurations head to the [API reference](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxLLM/).
@@ -6,6 +6,7 @@ LangChain integrations related to IBM technologies, including the
 [IBM watsonx.ai](https://www.ibm.com/products/watsonx-ai) platform and DB2 database.
 
 ## Watsonx AI
+
 IBM® watsonx.ai™ AI studio is part of the IBM [watsonx](https://www.ibm.com/watsonx)™ AI and data platform, bringing together new generative
 AI capabilities powered by [foundation models](https://www.ibm.com/products/watsonx-ai/foundation-models) and traditional machine learning (ML)
 into a powerful studio spanning the AI lifecycle. Tune and guide models with your enterprise data to meet your needs with easy-to-use tools for
@@ -17,103 +18,52 @@ Watsonx.ai offers:
 - **End-to-end AI governance:** Enterprises can scale and accelerate the impact of AI with trusted data across the business, using data wherever it resides.
 - **Hybrid, multi-cloud deployments:** IBM provides the flexibility to integrate and deploy your AI workloads into your hybrid-cloud stack of choice.
 
+### Model interfaces
 
-### Installation and Setup
-
-Install the integration package with:
-
-<CodeGroup>
-```bash pip
-pip install -qU langchain-ibm
-```
-
-```bash uv
-uv add langchain-ibm
-```
-</CodeGroup>
-
-Get an IBM watsonx.ai api key and set it as an environment variable (`WATSONX_APIKEY`)
-```python
-import os
-
-os.environ["WATSONX_APIKEY"] = "your IBM watsonx.ai api key"
-```
-
-### Chat Model
-
-#### ChatWatsonx
-
-See a [usage example](/oss/integrations/chat/ibm_watsonx).
-
-```python
-from langchain_ibm import ChatWatsonx
-```
-
-### LLMs
-
-#### WatsonxLLM
-
-See a [usage example](/oss/integrations/llms/ibm_watsonx).
-
-```python
-from langchain_ibm import WatsonxLLM
-```
+<Columns cols={2}>
+    <Card title="ChatWatsonx" href="/oss/integrations/chat/ibm_watsonx" cta="Get started" icon="message" arrow>
+        IBM watsonx.ai chat models.
+    </Card>
+    <Card title="WatsonxLLM" href="/oss/integrations/llms/ibm_watsonx" cta="Get started" icon="i-cursor" arrow>
+        (Legacy) IBM watsonx.ai text completion models.
+    </Card>
+    <Card title="WatsonxEmbeddings" href="/oss/integrations/text_embedding/ibm_watsonx" cta="Get started" icon="layer-group" arrow>
+        IBM watsonx.ai embedding models.
+    </Card>
+</Columns>
 
-### Embedding Models
+### Tools and toolkits
 
-#### WatsonxEmbeddings
+<Columns cols={2}>
+    <Card title="WatsonxToolkit" href="/oss/integrations/tools/ibm_watsonx" cta="Get started" icon="screwdriver-wrench" arrow>
+        IBM watsonx.ai toolkit.
+    </Card>
+</Columns>
 
-See a [usage example](/oss/integrations/text_embedding/ibm_watsonx).
+### Retrievers
 
-```python
-from langchain_ibm import WatsonxEmbeddings
-```
+<Columns cols={2}>
+    <Card title="WatsonxRerank" href="/oss/integrations/retrievers/ibm_watsonx_ranker" cta="Get started" icon="download" arrow>
+        IBM watsonx.ai document retriever.
+    </Card>
+</Columns>
 
-### Reranker
-
-#### WatsonxRerank
-
-See a [usage example](/oss/integrations/retrievers/ibm_watsonx_ranker).
-
-```python
-from langchain_ibm import WatsonxRerank
-```
-
-### Toolkit
+## DB2
 
-#### WatsonxToolkit
+The IBM DB2 relational database v12.1.2 and above offers the abilities of vector store
+and vector search. Installation of `langchain-db2` package will give LangChain users
+the support of DB2 vector store and vector search.
 
-See a [usage example](/oss/integrations/tools/ibm_watsonx).
 
-```python
-from langchain_ibm.agent_toolkits.utility import WatsonxToolkit
-```
+<Note>
+`langchain-db2` is a separate package for Vector Store feature only, and can be run without the `langchain-ibm` package.
+</Note>
 
-## DB2
 
 ### Vector stores
 
-#### IBM DB2 Vector Store and Vector Search
-
-The IBM DB2 relational database v12.1.2 and above offers the abilities of vector store
-and vector search. Installation of `langchain-db2` package will give LangChain users
-the support of DB2 vector store and vector search.
-
-See detailed usage examples in the guide [here](/oss/integrations/vectorstores/db2).
-
-Installation: This is a separate package for vector store feature only and can be run
-without the `langchain-ibm` package.
-<CodeGroup>
-```bash pip
-pip install -U langchain-db2
-```
-
-```bash uv
-uv add langchain-db2
-```
-</CodeGroup>
-Usage:
-```python
-from langchain_db2 import db2vs
-from langchain_db2.db2vs import DB2VS
-```
+<Columns cols={2}>
+    <Card title="DB2VS" href="/oss/integrations/vectorstores/db2" cta="Get started" icon="database" arrow>
+        IBM DB2 Vector Store and Vector Search
+    </Card>
+</Columns>
@@ -2,7 +2,7 @@
 title: IBM watsonx.ai
 ---
 
->WatsonxRerank is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
+>`WatsonxRerank` is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
 
 This notebook shows how to use [watsonx's rerank endpoint](https://cloud.ibm.com/apidocs/watsonx-ai#text-rerank) in a retriever.
 
@@ -12,7 +12,7 @@ This notebook shows how to use [watsonx's rerank endpoint](https://cloud.ibm.com
 
 | Class | Package | [JS support](https://js.langchain.com/docs/integrations/document_compressors/ibm/) | Downloads | Version |
 | :--- | :--- | :---: | :---: | :---: |
-| [WatsonxRerank](https://python.langchain.com/api_reference/ibm/rerank/langchain_ibm.rerank.WatsonxRerank.html) | [langchain-ibm](https://python.langchain.com/api_reference/ibm/index.html) | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
+| [`WatsonxRerank`](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxRerank/) | [`langchain-ibm`](https://reference.langchain.com/python/integrations/langchain_ibm/) | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
 
 ## Setup
 
@@ -267,4 +267,4 @@ chain.invoke(query)
 
 ## API reference
 
-For detailed documentation of all `WatsonxRerank` features and configurations head to the [API reference](https://python.langchain.com/api_reference/ibm/chat_models/langchain_ibm.rerank.WatsonxRerank.html).
+For detailed documentation of all `WatsonxRerank` features and configurations head to the [API reference](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxRerank/).
@@ -2,7 +2,7 @@
 title: IBM watsonx.ai
 ---
 
->WatsonxEmbeddings is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
+>`WatsonxEmbeddings` is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.
 
 This example shows how to communicate with `watsonx.ai` models using `LangChain`.
 
@@ -183,4 +183,4 @@ doc_result[0][:5]
 
 ## API reference
 
-For detailed documentation of all `WatsonxEmbeddings` features and configurations head to the [API reference](https://python.langchain.com/api_reference/ibm/embeddings/langchain_ibm.embeddings.WatsonxEmbeddings.html).
+For detailed documentation of all `WatsonxEmbeddings` features and configurations head to the [API reference](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxEmbeddings/).
@@ -2,7 +2,7 @@
 title: IBM watsonx.ai
 ---
 
->WatsonxToolkit is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) Toolkit.
+>`WatsonxToolkit` is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) Toolkit.
 
 This example shows how to use `watsonx.ai` Toolkit using `LangChain`.
 
@@ -12,7 +12,7 @@ This example shows how to use `watsonx.ai` Toolkit using `LangChain`.
 
 | Class | Package | Serializable | [JS support](https://js.langchain.com/docs/integrations/toolkits/ibm/) | Downloads | Version |
 | :--- | :--- | :---: | :---: | :---: | :---: |
-| [WatsonxToolkit](https://python.langchain.com/api_reference/ibm/agent_toolkits/langchain_ibm.agent_toolkits.utility.toolkit.WatsonxToolkit.html) | [langchain-ibm](https://python.langchain.com/api_reference/ibm/index.html) | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
+| [`WatsonxToolkit`](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxToolkit/) | [`langchain-ibm`](https://reference.langchain.com/python/integrations/langchain_ibm/) | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ibm?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ibm?style=flat-square&label=%20) |
 
 ## Setup
 
@@ -302,4 +302,4 @@ The current weather in Boston is -1°C with 0mm of rain, a relative humidity of
 
 ## API reference
 
-For detailed documentation of all `WatsonxToolkit` features and configurations head to the [API reference](https://python.langchain.com/api_reference/ibm/toolkit/langchain_ibm.toolkit.WatsonxToolkit.html).
+For detailed documentation of all `WatsonxToolkit` features and configurations head to the [API reference](https://reference.langchain.com/python/integrations/langchain_ibm/WatsonxToolkit/).