[Docs] Rename remaining instances of Cognitive Search to AI Search (#961)

* Rename remaining cognitive instanceS

* oops dont remain cog services

* Apply suggestions from code review

* Apply suggestions from code review

* Update docs/customization.md

* Update docs/customization.md

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* Update docs/customization.md

Author: pamelafox

app/backend/app.py

@@ -221,7 +221,7 @@ async def setup_clients():
     AZURE_SEARCH_QUERY_LANGUAGE = os.getenv("AZURE_SEARCH_QUERY_LANGUAGE", "en-us")
     AZURE_SEARCH_QUERY_SPELLER = os.getenv("AZURE_SEARCH_QUERY_SPELLER", "lexicon")
 
-    # Use the current user identity to authenticate with Azure OpenAI, Cognitive Search and Blob Storage (no secrets needed,
+    # Use the current user identity to authenticate with Azure OpenAI, AI Search and Blob Storage (no secrets needed,
     # just use 'az login' locally, and managed identity when deployed on Azure). If you need to use keys, use separate AzureKeyCredential instances with the
     # keys for each service
     # If you encounter a blocking error during a DefaultAzureCredential resolution, you can exclude the problematic credential by using a parameter (ex. exclude_shared_token_cache_credential=True)
@@ -237,7 +237,7 @@ async def setup_clients():
         token_cache_path=TOKEN_CACHE_PATH,
     )
 
-    # Set up clients for Cognitive Search and Storage
+    # Set up clients for AI Search and Storage
     search_client = SearchClient(
         endpoint=f"https://{AZURE_SEARCH_SERVICE}.search.windows.net",
         index_name=AZURE_SEARCH_INDEX,

app/backend/approaches/chatreadretrieveread.py

@@ -23,9 +23,9 @@ class ChatReadRetrieveReadApproach(Approach):
     NO_RESPONSE = "0"
 
     """
-    Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
-    top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion
-    (answer) with that prompt.
+    A multi-step approach that first uses OpenAI to turn the user's question into a search query,
+    then uses Azure AI Search to retrieve relevant documents, and then sends the conversation history,
+    original user question, and search results to OpenAI to generate a response.
     """
     system_message_chat_conversation = """Assistant helps the company employees with their healthcare plan questions, and questions about the employee handbook. Be brief in your answers.
 Answer ONLY with the facts listed in the list of sources below. If there isn't enough information below, say you don't know. Do not generate answers that don't use the sources below. If asking a clarifying question to the user would help, ask the question.
@@ -43,7 +43,7 @@ class ChatReadRetrieveReadApproach(Approach):
 Make sure the last question ends with ">>"."""
 
     query_prompt_template = """Below is a history of the conversation so far, and a new question asked by the user that needs to be answered by searching in a knowledge base about employee healthcare plans and the employee handbook.
-You have access to Azure Cognitive Search index with 100's of documents.
+You have access to an Azure AI Search index with 100's of documents.
 Generate a search query based on the conversation and the new question.
 Do not include cited source filenames and document names e.g info.txt or doc.pdf in the search query terms.
 Do not include any text inside [] or <<>> in the search query terms.
@@ -102,7 +102,7 @@ async def run_until_final_call(
         functions = [
             {
                 "name": "search_sources",
-                "description": "Retrieve sources from the Azure Cognitive Search index",
+                "description": "Retrieve sources from the Azure AI Search index",
                 "parameters": {
                     "type": "object",
                     "properties": {

app/backend/approaches/retrievethenread.py

@@ -11,7 +11,7 @@
 
 class RetrieveThenReadApproach(Approach):
     """
-    Simple retrieve-then-read implementation, using the Cognitive Search and OpenAI APIs directly. It first retrieves
+    Simple retrieve-then-read implementation, using the AI Search and OpenAI APIs directly. It first retrieves
     top documents from search, then constructs a prompt with them, and then uses OpenAI to generate an completion
     (answer) with that prompt.
     """

app/frontend/src/pages/layout/Layout.tsx

@@ -42,7 +42,7 @@ const Layout = () => {
                             </li>
                         </ul>
                     </nav>
-                    <h4 className={styles.headerRightText}>Azure OpenAI + Cognitive Search</h4>
+                    <h4 className={styles.headerRightText}>Azure OpenAI + AI Search</h4>
                     {useLogin && <LoginButton />}
                 </div>
             </header>

docs/customization.md

@@ -27,18 +27,18 @@ Typically, the primary backend code you'll want to customize is the `app/backend
 
 The chat tab uses the approach programmed in [chatreadretrieveread.py](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/approaches/chatreadretrieveread.py).
 
-1. It uses the ChatGPT API to turn the user question into a good search query.
-2. It queries Azure Cognitive Search for search results for that query (optionally using the vector embeddings for that query).
-3. It then combines the search results and original user question, and asks ChatGPT API to answer the question based on the sources. It includes the last 4K of message history as well (or however many tokens are allowed by the deployed model).
+1. It uses the OpenAI ChatCompletion API to turn the user question into a good search query.
+2. It queries Azure AI Search for search results for that query (optionally using the vector embeddings for that query).
+3. It then combines the search results and original user question, and asks OpenAI ChatCompletion API to answer the question based on the sources. It includes the last 4K of message history as well (or however many tokens are allowed by the deployed model).
 
 The `system_message_chat_conversation` variable is currently tailored to the sample data since it starts with "Assistant helps the company employees with their healthcare plan questions, and questions about the employee handbook." Change that to match your data.
 
 #### Ask approach
 
 The ask tab uses the approach programmed in [retrievethenread.py](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/approaches/retrievethenread.py).
 
-1. It queries Azure Cognitive Search for search results for the user question (optionally using the vector embeddings for that question).
-2. It then combines the search results and user question, and asks ChatGPT API to answer the question based on the sources.
+1. It queries Azure AI Search for search results for the user question (optionally using the vector embeddings for that question).
+2. It then combines the search results and user question, and asks OpenAI ChatCompletion API to answer the question based on the sources.
 
 The `system_chat_template` variable is currently tailored to the sample data since it starts with "You are an intelligent assistant helping Contoso Inc employees with their healthcare plan questions and employee handbook questions." Change that to match your data.
 
@@ -79,24 +79,24 @@ If you notice any answers that aren't as good as you'd like, here's a process fo
 
 The first step is to identify where the problem is occurring. For example, if using the Chat tab, the problem could be:
 
-1. ChatGPT is not generating a good search query based on the user question
-2. Azure Cognitive Search is not returning good search results for the query
-3. ChatGPT is not generating a good answer based on the search results and user question
+1. OpenAI ChatCompletion API is not generating a good search query based on the user question
+2. Azure AI Search is not returning good search results for the query
+3. OpenAI ChatCompletion API is not generating a good answer based on the search results and user question
 
 You can look at the "Thought process" tab in the chat app to see each of those steps,
 and determine which one is the problem.
 
-#### Improving ChatGPT results
+#### Improving OpenAI ChatCompletion results
 
-If the problem is with ChatGPT (steps 1 or 3 above), you can try changing the relevant prompt.
+If the problem is with the ChatCompletion API calls (steps 1 or 3 above), you can try changing the relevant prompt.
 
-Once you've changed the prompt, make sure you ask the same question multiple times to see if the overall quality has improved. ChatGPT can yield different results every time, even for a temperature of 0.0, but especially for a higher temperature than that (like our default of 0.7 for step 3).
+Once you've changed the prompt, make sure you ask the same question multiple times to see if the overall quality has improved. The ChatCompletion API can yield different results every time, even for a temperature of 0.0, but especially for a higher temperature than that (like our default of 0.7 for step 3).
 
-You can also try changing the ChatGPT parameters, like temperature, to see if that improves results for your domain.
+You can also try changing the ChatCompletion parameters, like temperature, to see if that improves results for your domain.
 
-#### Improving Azure Cognitive Search results
+#### Improving Azure AI Search results
 
-If the problem is with Azure Cognitive Search (step 2 above), the first step is to check what search parameters you're using. Generally, the best results are found with hybrid search (text + vectors) plus the additional semantic re-ranking step, and that's what we've enabled by default. There may be some domains where that combination isn't optimal, however.
+If the problem is with Azure AI Search (step 2 above), the first step is to check what search parameters you're using. Generally, the best results are found with hybrid search (text + vectors) plus the additional semantic re-ranking step, and that's what we've enabled by default. There may be some domains where that combination isn't optimal, however.
 
 ##### Configuring parameters in the app
 
@@ -107,7 +107,7 @@ You can change many of the search parameters in the "Developer settings" in the
 #### Configuring parameters in the Azure Portal
 
 You may find it easier to experiment with search options with the index explorer in the Azure Portal.
-Open up the Azure Cognitive Search resource, select the Indexes tab, and select the index there.
+Open up the Azure AI Search resource, select the Indexes tab, and select the index there.
 
 Then use the JSON view of the search explorer, and make sure you specify the same options you're using in the app. For example, this query represents a search with semantic ranker configured:
 

docs/data_ingestion.md

@@ -10,14 +10,14 @@ The `scripts/prepdocs.py` script is responsible for both uploading and indexing
 
 The script uses the following steps to index documents:
 
-1. If it doesn't yet exist, create a new index in Azure Cognitive Search.
+1. If it doesn't yet exist, create a new index in Azure AI Search.
 2. Upload the PDFs to Azure Blob Storage.
 3. Split the PDFs into chunks of text.
-4. Upload the chunks to Azure Cognitive Search. If using vectors (the default), also compute the embeddings and upload those alongside the text.
+4. Upload the chunks to Azure AI Search. If using vectors (the default), also compute the embeddings and upload those alongside the text.
 
 ### Chunking
 
-We're often asked why we need to break up the PDFs into chunks when Azure Cognitive Search supports searching large documents.
+We're often asked why we need to break up the PDFs into chunks when Azure AI Search supports searching large documents.
 
 Chunking allows us to limit the amount of information we send to OpenAI due to token limits. By breaking up the content, it allows us to easily find potential chunks of text that we can inject into OpenAI. The method of chunking we use leverages a sliding window of text such that sentences that end one chunk will start the next. This allows us to reduce the chance of losing the context of the text.
 

docs/productionizing.md

@@ -16,7 +16,7 @@ to production. Here are some things to consider:
 * **Azure Storage**: The default storage account uses the `Standard_LRS` SKU.
   To improve your resiliency, we recommend using `Standard_ZRS` for production deployments,
   which you can specify using the `sku` property under the `storage` module in `infra/main.bicep`.
-* **Azure Cognitive Search**: The default search service uses the `Standard` SKU
+* **Azure AI Search**: The default search service uses the `Standard` SKU
   with the free semantic search option, which gives you 1000 free queries a month.
   Assuming your app will experience more than 1000 questions, you should either change `semanticSearch`
   to "standard" or disable semantic search entirely in the `/app/backend/approaches` files.
@@ -66,7 +66,7 @@ Open the locust UI at http://localhost:8089/, the URI displayed in the terminal.
 
 Start a new test with the URI of your website, e.g. `https://my-chat-app.azurewebsites.net`.
 Do *not* end the URI with a slash. You can start by pointing at your localhost if you're concerned
-more about load on OpenAI/Cognitive Search than the host platform.
+more about load on OpenAI/AI Search than the host platform.
 
 For the number of users and spawn rate, we recommend starting with 20 users and 1 users/second.
 From there, you can keep increasing the number of users to simulate your expected load.

infra/core/search/search-services.bicep

@@ -1,4 +1,4 @@
-metadata description = 'Creates an Azure Cognitive Search instance.'
+metadata description = 'Creates an Azure AI Search instance.'
 param name string
 param location string = resourceGroup().location
 param tags object = {}

scripts/manageacl.py

@@ -174,17 +174,17 @@ async def main(args: Any):
     parser.add_argument(
         "--search-service",
         required=True,
-        help="Name of the Azure Cognitive Search service where content should be indexed (must exist already)",
+        help="Name of the Azure AI Search service where content should be indexed (must exist already)",
     )
     parser.add_argument(
         "--index",
         required=True,
-        help="Name of the Azure Cognitive Search index where content should be indexed (will be created if it doesn't exist)",
+        help="Name of the Azure AI Search index where content should be indexed (will be created if it doesn't exist)",
     )
     parser.add_argument(
         "--search-key",
         required=False,
-        help="Optional. Use this Azure Cognitive Search account key instead of the current user identity to login (use az login to set current user for Azure)",
+        help="Optional. Use this Azure AI Search account key instead of the current user identity to login (use az login to set current user for Azure)",
     )
     parser.add_argument("--acl-type", required=False, choices=["oids", "groups"], help="Optional. Type of ACL")
     parser.add_argument(

scripts/prepdocs.py

@@ -175,22 +175,22 @@ async def main(strategy: Strategy, credential: AsyncTokenCredential, args: Any):
     )
     parser.add_argument(
         "--searchservice",
-        help="Name of the Azure Cognitive Search service where content should be indexed (must exist already)",
+        help="Name of the Azure AI Search service where content should be indexed (must exist already)",
     )
     parser.add_argument(
         "--index",
-        help="Name of the Azure Cognitive Search index where content should be indexed (will be created if it doesn't exist)",
+        help="Name of the Azure AI Search index where content should be indexed (will be created if it doesn't exist)",
     )
     parser.add_argument(
         "--searchkey",
         required=False,
-        help="Optional. Use this Azure Cognitive Search account key instead of the current user identity to login (use az login to set current user for Azure)",
+        help="Optional. Use this Azure AI Search account key instead of the current user identity to login (use az login to set current user for Azure)",
     )
     parser.add_argument(
         "--searchanalyzername",
         required=False,
         default="en.microsoft",
-        help="Optional. Name of the Azure Cognitive Search analyzer to use for the content field in the index",
+        help="Optional. Name of the Azure AI Search analyzer to use for the content field in the index",
     )
     parser.add_argument("--openaihost", help="Host of the API used to compute embeddings ('azure' or 'openai')")
     parser.add_argument("--openaiservice", help="Name of the Azure OpenAI service used to compute embeddings")