Merge pull request #84 from STRIDES/updated_tutorials_zy

Updated All Azure tutorials

notebooks/GenAI/example_scripts/example_azureaisearch_openaichat_zeroshot.py

@@ -71,7 +71,7 @@ def build_chain():
 
 def run_chain(chain, prompt: str, history=[]):
     print(prompt)
-    return chain({"question": prompt, "chat_history": history})
+    return chain.invoke({"question": prompt, "chat_history": history})
 
 if __name__ == "__main__":
   chat_history = []

notebooks/GenAI/example_scripts/example_langchain_openaichat_zeroshot.py

@@ -1,6 +1,7 @@
 from langchain.retrievers import PubMedRetriever
 from langchain.chains import ConversationalRetrievalChain
 from langchain.prompts import PromptTemplate
+from langchain_openai import AzureChatOpenAI
 import sys
 import json
 import os
@@ -66,7 +67,7 @@ def build_chain():
 
 def run_chain(chain, prompt: str, history=[]):
     print(prompt)
-    return chain({"question": prompt, "chat_history": history})
+    return chain.invoke({"question": prompt, "chat_history": history})
 
 if __name__ == "__main__":
   chat_history = []

notebooks/GenAI/example_scripts/workshop_embedding.py

@@ -1,5 +1,4 @@
 import openai
-from openai.embeddings_utils import get_embedding, cosine_similarity # must pip install openai[embeddings]
 import pandas as pd
 import numpy as np
 import os
@@ -13,20 +12,31 @@
 
 
 # set keys and configure Azure OpenAI
-openai.api_type = 'azure'
-openai.api_version = os.environ['AZURE_OPENAI_VERSION']
-openai.api_base = os.environ['AZURE_OPENAI_ENDPOINT']
-openai.api_key = os.environ['AZURE_OPENAI_KEY']
+os.environ["AZURE_OPENAI_ENDPOINT"] = "<YOUR OPENAI ENDPOINT>"
+os.environ["AZURE_OPENAI_KEY"] = "<YOUR OPENAI KEY>"
+
+#create embeddings functions to apply to a given column
+
+client = AzureOpenAI(
+    api_key=os.getenv("AZURE_OPENAI_KEY"),  
+    api_version="2023-05-15",
+    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
+    )]
 
 
 # read the data file to be embed 
 df = pd.read_csv('microsoft-earnings.csv')
 print(df)
 
+#embeddings function
+def get_embedding(text, model="text-embedding-ada-002"):
+   text = text.replace("\n", " ")
+   return client.embeddings.create(input = [text], model=model).data[0].embedding
+
 
-# calculate word embeddings 
-df['embedding'] = df['text'].apply(lambda x:get_embedding(x, engine='text-embedding-ada-002'))
-df.to_csv('microsoft-earnings_embeddings.csv')
+# calculate word embeddings
+df['embedding'] = df['text'].apply(lambda x: get_embedding(x))
+df.to_csv('microsoft-earnings_embeddings.csv', index=False)
 time.sleep(3)
 print(df)
 

notebooks/GenAI/example_scripts/workshop_search.py

@@ -1,5 +1,4 @@
 import openai
-from openai.embeddings_utils import get_embedding, cosine_similarity # must pip install openai[embeddings]
 import pandas as pd
 import numpy as np
 import os
@@ -10,14 +9,21 @@
 
 load_dotenv()
 
-
-
-
 # set keys and configure Azure OpenAI
-openai.api_type = 'azure'
-openai.api_version = os.environ['AZURE_OPENAI_VERSION']
-openai.api_base = os.environ['AZURE_OPENAI_ENDPOINT']
-openai.api_key = os.environ['AZURE_OPENAI_KEY']
+os.environ["AZURE_OPENAI_ENDPOINT"] = "<YOUR OPENAI ENDPOINT>"
+os.environ["AZURE_OPENAI_KEY"] = "<YOUR OPENAI KEY>"
+
+#create embeddings functions to apply to a given column
+
+client = AzureOpenAI(
+    api_key=os.getenv("AZURE_OPENAI_KEY"),  
+    api_version="2023-05-15",
+    azure_endpoint = os.getenv("AZURE_OPENAI_ENDPOINT")
+    )
+
+#create cosine function
+def cosine_similarity(a, b):
+    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
 
 # read in the embeddings .csv 
 # convert elements in 'embedding' column back to numpy array

notebooks/GenAI/notebooks/AzureAIStudio_index_structured_notebook.ipynb

@@ -293,7 +293,7 @@
    "id": "19a076aa-d2c1-4709-aec2-9532e6457e48",
    "metadata": {},
    "source": [
-    "Create your Azure AI Search service."
+    "Create your Azure AI Search service. We will be using the free tier that holds 50MB of memory and allows you to create up to 3 indexes."
    ]
   },
   {
@@ -759,9 +759,7 @@
     "        {\"role\": \"user\", \"content\": \"Context: \"+ context + \"\\n\\n Query: \" + query}\n",
     "    ],\n",
     "    #max_tokens=100,\n",
-    "    temperature=1,\n",
-    "    top_p=1,\n",
-    "    n=1\n",
+    "    temperature=0,\n",
     ")"
    ]
   },

notebooks/GenAI/notebooks/AzureAIStudio_index_structured_with_console.ipynb

@@ -346,7 +346,7 @@
    "metadata": {},
    "source": [
     "## Conclusion\n",
-    "And that is it! You successfully created a simple chat bot that runs queries against structured data! This is a complex problem and there are a lot of good blogs out there that describe more complex architectures. We recommend you do some investigation and see if you can come up with an even better solution for your use case! \n",
+    "And that is it! You successfully created a simple chat bot that runs queries against structured data! This is a complex problem and there are a lot of good blogs out there that describe more complex architectures. We recommend you do some investigating and see if you can come up with an even better solution for your use case! \n",
     "\n",
     "Key skills you learned were to: \n",
     "+ Create embeddings and a vector store using Azure AI Search in the console\n",

notebooks/GenAI/notebooks/AzureAIStudio_langchain.ipynb

@@ -84,7 +84,7 @@
    "outputs": [],
    "source": [
     "# pip install other packages as needed\n",
-    "! pip install 'langchain' 'langchain-core' 'langchain-community' 'langchain-openai'"
+    "! pip install 'langchain' 'langchain-core' 'langchain-community' 'langchain-openai' 'bs4'"
    ]
   },
   {
@@ -122,10 +122,28 @@
    "source": [
     "import os\n",
     "from langchain_core.messages import HumanMessage\n",
+    "from langchain.chains.summarize import load_summarize_chain\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
     "from langchain_openai import AzureChatOpenAI\n",
-    "from langchain_openai import AzureOpenAIEmbeddings\n"
+    "from langchain_openai import AzureOpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Tip:** If you receieve an error that bs4 was not loaded you can manually load it using the below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#uncomment if necessary\n",
+    "#from bs4 import BeautifulSoup"
    ]
   },
   {
@@ -161,10 +179,13 @@
    },
    "outputs": [],
    "source": [
+    "import os\n",
+    "os.environ[\"AZURE_OPENAI_ENDPOINT\"] = \"<Your_Azure_Endpoint>\"\n",
+    "os.environ[\"AZURE_OPENAI_API_KEY\"] = \"<Your_OpenAI_API_Key>\"\n",
+    "\n",
     "llm = AzureChatOpenAI(\n",
-    "    openai_api_version=\"<Your_OpenAI_API_Version>\",\n",
-    "    azure_endpoint = \"<Your_Azure_Endpoint>\",\n",
-    "    openai_api_key=\"<Your_OpenAI_API_Key>\",\n",
+    "    openai_api_version=\"<Your_OpenAI_Model_Version>\",\n",
+    "    azure_deployment=\"<Your_OpenAI_API_Name>\",\n",
     ")"
    ]
   },
@@ -310,11 +331,6 @@
     "## Clean up\n",
     "Make sure to shut down your Azure ML compute and if desired you can delete your deployed model on Azure AI Studio."
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
   }
  ],
  "metadata": {

notebooks/GenAI/notebooks/AzureAIStudio_sql_chatbot.ipynb

@@ -56,29 +56,6 @@
     "- Creating a chatbot and utilizing langchains SQL agent to connect the bot to a database"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "3d2aa60a-cf87-4083-80fa-e9dc9179dcc8",
-   "metadata": {},
-   "source": [
-    "## Table of Contents"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3bad1638-6fcd-4299-b714-48c7cfd865ff",
-   "metadata": {},
-   "source": [
-    "- [Summary](#summary)\n",
-    "- [Install Packages](#packages)\n",
-    "- [Create Azure SQL Database](#azure_db)\n",
-    "- [Create Azure SQL Table](#azure_table)\n",
-    "- [Submitting a Query](#query)\n",
-    "- [Setting up a Chatbot](#chatbot)\n",
-    "- [Conclusion](#conclusion)\n",
-    "- [Cleaning up Resources](#cleanup)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "3d98bdb4",
@@ -125,7 +102,76 @@
    "id": "64e959a6-4515-49cd-bdf8-b0da0544c10a",
    "metadata": {},
    "source": [
-    "Follow the instructions [here](https://learn.microsoft.com/en-us/azure/azure-sql/database/single-database-create-quickstart?view=azuresql&tabs=azure-portal) to create a single database in Azure SQL Database. Note that for this tutorials database the field name **Use existing data** was set to **None**."
+    "Follow the instructions [here](https://learn.microsoft.com/en-us/azure/azure-sql/database/single-database-create-quickstart?view=azuresql&tabs=azure-portal) to create a single database in Azure SQL Database. \n",
+    "\n",
+    "**Note:** For this tutorials database the field name **'Use existing data'** was set to **None** and the **location** to **US East 2**."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4fdf2998-f598-4814-a580-62db432c2d61",
+   "metadata": {},
+   "source": [
+    "### Install SQL Driver <a id=\"sql_driver\"></a>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e07ed164-d94a-4cac-bb37-b082b0fa9285",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Download the drivers package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fce56601-fb8d-495f-b0fd-9e58cac7d0c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! curl https://packages.microsoft.com/config/ubuntu/22.04/prod.list | sudo tee /etc/apt/sources.list.d/mssql-release.list"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "32e91b50-d685-4a9a-b593-fcd1f1eb2f74",
+   "metadata": {},
+   "source": [
+    "Run the following in your terminal. If prompted to accept the license terms of installing the driver use your arrow keys to select **'yes'** then press **enter**."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2318532f-b884-4cf2-a7f1-f9a83b2a4aa9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#RUN IN TERMINAL\n",
+    "sudo ACCEPT_EULA=Y apt-get install -y msodbcsql18"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0677acc-d8a1-4683-ba34-d12d517369cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!echo 'export PATH=\"$PATH:/opt/mssql-tools18/bin\"' >> ~/.bashrc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6114fcf3-af53-4a62-b9ac-cd017308ff7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!source ~/.bashrc"
    ]
   },
   {
@@ -144,6 +190,14 @@
     "Now that we have our SQL database we will connect to it using the python package `pyodbc` which will allow us to commit changes to our database and query tables."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b13c9608-32a7-42ba-a2a9-6b249949d7c8",
+   "metadata": {},
+   "source": [
+    "**Tip:** If you run into firewall errors go to **Azure SQL** on the console, click on the your SQL server name, on the left side of the screen go to **Networking** under Security, make sure your IP address is saved under Firewall rules and where is says **'Allow Azure services and resources to access this server'** is checkmarked."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -154,12 +208,12 @@
     "import pyodbc\n",
     "\n",
     "server_name = \"<ENTER_DB_SERVER_NAME>\"\n",
-    "user = \"<ENTER_DB_USERNAME>\"\n",
+    "username = \"<ENTER_DB_USERNAME>\"\n",
     "password = \"<ENTER_DB_PASSWORD>\"\n",
     "database = \"<ENTER_DB_NAME>\"\n",
     "driver= '{ODBC Driver 18 for SQL Server}'\n",
     "\n",
-    "conn = pyodbc.connect('DRIVER='+driver+';PORT=1433;SERVER='+server+'.database.windows.net/;PORT=1443;DATABASE='+database+';UID='+user+';PWD='+ password)"
+    "conn = pyodbc.connect(f'DRIVER={driver};PORT=1433;SERVER={server_name}.database.windows.net;PORT=1443;DATABASE={database};UID={username};PWD={password}')"
    ]
   },
   {
@@ -418,7 +472,7 @@
    },
    "outputs": [],
    "source": [
-    "py_connectionString=f\"mssql+pyodbc://{user}:{password}@{server_name}.database.windows.net/{database}?driver={driver}\"\n",
+    "py_connectionString=f\"mssql+pyodbc://{username}:{password}@{server_name}.database.windows.net/{database}?driver={driver}\"\n",
     "db_engine = create_engine(py_connectionString)"
    ]
   },
@@ -633,14 +687,6 @@
     "subscription_id='<Enter_Subscription_ID>'\n",
     "!az sql server delete --name {server_name} --resource-group {resource_group} --subscription {subscription_id}  -y"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1f91700b-bfe3-452c-b5a0-0b8fed115fd8",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {