Merge pull request #79 from STRIDES/langchain_updates_zy

Langchain updates zy

notebooks/GenAI/Azure_Open_AI_README.md

@@ -78,7 +78,7 @@ On the far right, you can modify which model you are deploying, which allows you
 
   ![modify deployment](/docs/images/19_deployment.png)
 
-Finally, you can select the `parameters` tab to modify the model parameters. Review [this presentation](/tutorials/notebooks/GenAI/search_documents/aoai_workshop_content.pdf) to learn more about the parameters.
+Finally, you can select the `parameters` tab to modify the model parameters. Review [this presentation](/notebooks/GenAI/search_documents/aoai_workshop_content.pdf) to learn more about the parameters.
 
   ![modify parameters](/docs/images/20_parameters.png)
 
@@ -357,7 +357,7 @@ Creating embeddings of search documents allows you to use vector search, which i
 ### Environment Setup
 Navigate to your [Azure Machine Learning Studio environment](https://github.com/STRIDES/NIHCloudLabAzure#launch-a-machine-learning-workspace-jupyter-environment-). If you have not created your environment, [create one now](https://learn.microsoft.com/en-us/azure/machine-learning/tutorial-cloud-workstation?view=azureml-api-2). 
 
-Navigate to `Notebooks`, then clone this Git repo into your environment and navigate to the notebook called [AzureOpenAI_embeddings.ipynb](/tutorials/notebooks/GenAI/notebooks/AzureOpenAI_embeddings.ipynb). 
+Navigate to `Notebooks`, then clone this Git repo into your environment and navigate to the notebook called [AzureOpenAI_embeddings.ipynb](/notebooks/GenAI/notebooks/AzureOpenAI_embeddings.ipynb). 
 
 You will need a variety of parameters to authenticate with the API. You can find these within the Chat Playground by clicking **View Code**. Input these parameters into the notebook cell when asked.
 

notebooks/GenAI/example_scripts/example_azureaisearch_openaichat_zeroshot.py

@@ -1,7 +1,7 @@
 from langchain.chains import ConversationalRetrievalChain
 from langchain.prompts import PromptTemplate
-from langchain.chat_models import AzureChatOpenAI
-from langchain.retrievers import AzureCognitiveSearchRetriever
+from langchain_community.retrievers import AzureCognitiveSearchRetriever
+from langchain_openai import AzureChatOpenAI
 import sys
 import json
 import os

notebooks/GenAI/example_scripts/example_langchain_openaichat_zeroshot.py

@@ -1,7 +1,6 @@
 from langchain.retrievers import PubMedRetriever
 from langchain.chains import ConversationalRetrievalChain
 from langchain.prompts import PromptTemplate
-from langchain.llms import VertexAI
 import sys
 import json
 import os

notebooks/GenAI/notebooks/AzureAIStudio_index_structured_notebook.ipynb

@@ -10,6 +10,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "e421b4fd",
    "metadata": {},
    "source": [
     "## Overview\n",
@@ -18,6 +19,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "f3fe0439",
    "metadata": {},
    "source": [
     "## Prerequisites\n",
@@ -26,6 +28,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "6c5376ef",
    "metadata": {},
    "source": [
     "## Learning objectives\n",
@@ -38,6 +41,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "6fd8094c",
    "metadata": {},
    "source": [
     "## Get started"
@@ -61,7 +65,7 @@
    },
    "outputs": [],
    "source": [
-    "pip install -U \"langchain\" \"openai\""
+    "pip install -U \"langchain\" \"openai\" \"langchain-openai\" \"langchain-community\""
    ]
   },
   {
@@ -156,7 +160,18 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"<Your Azure Endpoint>\"\n",
+    "os.environ[\"AZURE_OPENAI_KEY\"] = \"<Your Azure AI Key>\"\n",
+    "\n",
     "#create embeddings functions to apply to a given column\n",
+    "from openai import AzureOpenAI\n",
+    "    \n",
+    "client = AzureOpenAI(\n",
+    "    api_key=os.getenv(\"AZURE_OPENAI_KEY\"),  \n",
+    "    api_version=\"2023-05-15\",\n",
+    "    azure_endpoint = os.getenv(\"AZURE_OPENAI_ENDPOINT\")\n",
+    "    )\n",
+    "\n",
     "def generate_embeddings(text, model=\"text-embedding-ada-002\"):\n",
     "    return client.embeddings.create(input = [text], model=model).data[0].embedding\n",
     "\n",
@@ -770,6 +785,7 @@
   },
   {
    "cell_type": "markdown",
+   "id": "31c915c9",
    "metadata": {},
    "source": [
     "## Conclusion\n",