switch to gh code - test

Author: sdgilley

.openpublishing.publish.config.json

@@ -113,7 +113,7 @@
     {
       "path_to_root": "azureai-samples-main",
       "url": "https://github.com/Azure-Samples/azureai-samples",
-      "branch": "main",
+      "branch": "sgilley-doc-updates",
       "branch_mapping": {}
     },
     {

articles/ai-foundry/how-to/develop/langchain.md

@@ -66,7 +66,7 @@ To use LLMs deployed in Azure AI Foundry portal, you need the endpoint and crede
 In this scenario, we placed both the endpoint URL and key in the following environment variables.  
 
 > [!TIP]
-> The endpoint you copied might have extra text after /models.  Delete that and stop ad /models as shown here.
+> The endpoint you copied might have extra text after /models.  Delete that and stop at /models as shown here.
 
 ```bash
 export AZURE_INFERENCE_ENDPOINT="https://<resource>.services.ai.azure.com/models"
@@ -83,6 +83,9 @@ llm = init_chat_model(model="mistral-medium-2505", model_provider="azure_ai")
 
 You can also use the class `AzureAIChatCompletionsModel` directly.
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_client)]
+
+
 ```python
 import os
 from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
@@ -145,6 +148,8 @@ model = AzureAIChatCompletionsModel(
 
 Let's first use the model directly. `ChatModels` are instances of LangChain `Runnable`, which means they expose a standard interface for interacting with them. To call the model, we can pass in a list of messages to the `invoke` method.
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=human_message)] 
+
 ```python
 from langchain_core.messages import HumanMessage, SystemMessage
 
@@ -170,6 +175,8 @@ prompt_template = ChatPromptTemplate.from_messages(
 
 As you can see from the prompt template, this chain has a `language` and `text` input. Now, let's create an output parser:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_output_parser)]
+
 ```python
 from langchain_core.prompts import ChatPromptTemplate
 parser = StrOutputParser()
@@ -195,7 +202,9 @@ chain.invoke({"language": "italian", "text": "hi"})
 
 Models deployed to Azure AI Foundry support the Foundry Models API, which is standard across all the models. Chain multiple LLM operations based on the capabilities of each model so you can optimize for the right model based on capabilities. 
 
-In the following example, we create two model clients. One is a producer and another one is a verifier. To make the distinction clear, we're using a multi-model endpoint like the [Foundry Models API](../../model-inference/overview.md) and hence we're passing the parameter `model` to use a `Mistral-Large` and a `Mistral-Small` model, quoting the fact that **producing content is more complex than verifying it**.
+In the following example, we create two model clients. One is a producer and another one is a verifier. To make the distinction clear, we're using a multi-model endpoint like the [Foundry Models API](../../model-inference/overview.md) and hence we're passing the parameter `model` to use a `Mistral-Medium` and a `Mistral-Small` model, quoting the fact that **producing content is more complex than verifying it**.
+
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_producer_verifier)]
 
 ```python
 from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
@@ -218,6 +227,8 @@ verifier = AzureAIChatCompletionsModel(
 
 The following example generates a poem written by an urban poet:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=generate_poem)]
+
 ```python
 from langchain_core.prompts import PromptTemplate
 
@@ -241,11 +252,16 @@ verifier_template = PromptTemplate(
 
 Now let's chain the pieces:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_chain)]
+
 ```python
 chain = producer_template | producer | parser | verifier_template | verifier | parser
 ```
 
-The previous chain returns the output of the step `verifier` only. Since we want to access the intermediate result generated by the `producer`, in LangChain you need to use a `RunnablePassthrough` object to also output that intermediate step. The following code shows how to do it:
+The previous chain returns the output of the step `verifier` only. Since we want to access the intermediate result generated by the `producer`, in LangChain you need to use a `RunnablePassthrough` object to also output that intermediate step. 
+
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_chain_with_passthrough)]
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_multiple_outputs_chain)]
 
 ```python
 from langchain_core.runnables import RunnablePassthrough, RunnableParallel
@@ -258,16 +274,12 @@ chain = generate_poem | RunnableParallel(poem=RunnablePassthrough(), verificatio
 
 To invoke the chain, identify the inputs required and provide values using the `invoke` method:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=invoke_chain)]
+
 ```python
 chain.invoke({"topic": "living in a foreign country"})
 ```
 
-```output
-{
-  "peom": "...",
-  "verification: "false"
-}
-```
 
 ## Use embeddings models
 
@@ -280,6 +292,9 @@ export AZURE_INFERENCE_CREDENTIAL="<your-key-goes-here>"
 
 Then create the client:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-embeddings.ipynb.ipynb?name=
+create_embed_model_client)]
+
 ```python
 from langchain_azure_ai.embeddings import AzureAIEmbeddingsModel
 
@@ -292,6 +307,8 @@ embed_model = AzureAIEmbeddingsModel(
 
 The following example shows a simple example using a vector store in memory:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-embeddings.ipynb.ipynb?name=create_vector_store)]
+
 ```python
 from langchain_core.vectorstores import InMemoryVectorStore
 
@@ -300,6 +317,8 @@ vector_store = InMemoryVectorStore(embed_model)
 
 Let's add some documents:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-embeddings.ipynb.ipynb?name="add_documents)]
+
 ```python
 from langchain_core.documents import Document
 
@@ -312,6 +331,8 @@ vector_store.add_documents(documents=documents)
 
 Let's search by similarity:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-embeddings.ipynb.ipynb?name=search_similarity)]
+
 ```python
 results = vector_store.similarity_search(query="thud",k=1)
 for doc in results:
@@ -338,6 +359,8 @@ If you need to debug your application and understand the requests sent to the mo
 
 First, configure logging to the level you are interested in:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=configure_logging)]
+
 ```python
 import sys
 import logging
@@ -362,6 +385,8 @@ handler.setFormatter(formatter)
 
 To see the payloads of the requests, when instantiating the client, pass the argument `logging_enable`=`True` to the `client_kwargs`:
 
+[!notebook-python[](~/azureai-samples-main/scenarios/langchain/getting-started-with-langchain-chat-models.ipynb?name=create_client_with_logging)]
+
 ```python
 import os
 from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
@@ -400,7 +425,7 @@ You can configure your application to send telemetry to Azure Application Insigh
         application_insights_connection_string = "instrumentation...."
         ```
 
-2. Using the Azure AI Foundry SDK and the project connection string.
+2. Using the Azure AI Foundry SDK and the project connection string ([!INCLUDE [hub-project-name](../../includes/hub-project-name.md)]s only).
 
     1. Ensure you have the package `azure-ai-projects` installed in your environment.