general cleanup

Author: lebaro-msft

README.md

@@ -56,7 +56,9 @@ If you intend to develop your own code following this sample, we recommend you u
     ```bash
     cd src
     ```
+
     - Next, install the requirements in your venv. Note: this may take several minutes the first time you install.
+
     ``` bash
     pip install -r requirements.txt
     ```
@@ -65,6 +67,7 @@ If you intend to develop your own code following this sample, we recommend you u
     - Note: if you are running from within a Codespace or the curated VS Code cloud container, you will need to use `az login --use-device-code`
 
 ## Step 2: Provision or reference Azure AI resources
+
 Use the provision script to provision new or reference existing Azure AI resources to use in your application.
 
 We have a process to help you easily provision the resources you need to run this sample. You can either create new resources, or specify existing resources.
@@ -81,19 +84,19 @@ You can find the details you need for existing resources in the top-right projec
     You can also try running our experimental script to check quota in your subscription. You can modify it to fit your requirements.
 
     > [!NOTE]
-    > This script is intended to help understand quota, but it might provide numbers that are not accurate. The Azure AI Studio or the [Azure OpenAI portal](https://oai.azure.com/), and our [docs of quota limits](https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits) would be the source of truth.
+    > This script is intended to help understand quota, but it might provide numbers that are not accurate. The Azure AI Studio or the [Azure OpenAI portal](https://oai.azure.com/), and our [docs of quota limits](https://learn.microsoft.com/azure/ai-services/openai/quotas-limits) would be the source of truth.
 
     ```bash
     python provisioning/check_quota.py --subscription-id <your-subscription-id>
     ```
 
-2. **Open the _provision.yaml_ file** that is located in the `provisioning` directory
+1. **Open the *provision.yaml* file** that is located in the `provisioning` directory
     1. There are notes in the file to help you.
-3. **Input all your desired fields**
+1. **Input all your desired fields**
     1. Note that you can either specify existing resources, or your desired names for new resources. If you are specifying existing resources, you can find the details you need in the Azure AI Studio project view.
     1. Make sure you select a location and deployments you have quota for.
-1. **Run the _provision.py_ script**
-    1. If you want to see the provisioning plan (what _would_ be provisioned given your `provision.yaml` specifications, without actually provisioning anything), run the below script with the `--show-only` flag.
+1. **Run the *provision.py* script**
+    1. If you want to see the provisioning plan (what *would* be provisioned given your `provision.yaml` specifications, without actually provisioning anything), run the below script with the `--show-only` flag.
     1. This script will output a .env in your src/ directory with all of your specified resources, which will be referenced by the rest of the sample code.
 
     ``` bash
@@ -103,7 +106,6 @@ You can find the details you need for existing resources in the top-right projec
 
     The script will check whether the resources you specified exist, otherwise it will create them. It will then construct a .env for you that references the provisioned or referenced resources, including your keys. Once the provisioning is complete, you'll be ready to move to step 3.
 
-
 ## Step 3: Explore prompts
 
 This sample repository contains a sample chat prompty file you can explore. This will let you verify your environment is set up to call your model deployments.
@@ -145,24 +147,24 @@ AZUREAI_SEARCH_INDEX_NAME=<index-name>
 
 ## Step 5: Develop custom code
 
-This sample includes custom code to add retrieval augmented generation (RAG) to our application.
+This sample includes custom code to add retrieval augmented generation (RAG) capabilities to a basic chat application.
 
-The code follows the following general logic:
+The code implements the following general logic:
 
-1. Generates a search query based on user query intent and any chat history
-1. Uses an embedding model to embed the query
-1. Retrieves relevant documents from the search index, given the query
-1. Passes the relevant context to the Azure Open AI chat completion model
-1. Returns the response from the Azure Open AI model
+1. Generate a search query based on user query intent and any chat history
+1. Use an embedding model to embed the query
+1. Retrieve relevant documents from the search index, given the query
+1. Pass the relevant context to the Azure Open AI chat completion model
+1. Return the response from the Azure Open AI model
 
 You can modify this logic as appropriate to fit your use case.
 
 ## Step 6: Use prompt flow to test copilot code
 
-Use the built-in prompt flow front end to locally serve your application, and validate your copilot performs as expected on sample inputs.
+Use prompt flow's testing capability to validate how your copilot performs as expected on sample inputs.
 
 ``` bash
-pf flow test --flow ./copilot_flow --inputs chat_input="how much for the Trailwalker shoes cost?"
+pf flow test --flow ./copilot_flow --inputs chat_input="how much do the Trailwalker shoes cost?"
 ```
 
 You can use the `--ui` flag to test interactively with a sample chat experience. Prompt flow locally serves a front end integrated with your code.

src/copilot_flow/chat.prompty

@@ -1,6 +1,6 @@
 ---
 name: Chat Prompt
-description: A prompty that uses the chat API to respond to queries
+description: A prompty that uses the chat API to respond to queries grounded in relevant documents
 model:
     api: chat
     configuration:

src/copilot_flow/copilot.py

@@ -1,31 +1,29 @@
 # ---------------------------------------------------------
 # Copyright (c) Microsoft Corporation. All rights reserved.
 # ---------------------------------------------------------
-from typing import TypedDict
-
-from openai import AzureOpenAI
-
 import os
+# set environment variables before importing any other code
+from dotenv import load_dotenv
+load_dotenv()
+
 from pathlib import Path
 
-from promptflow.tracing import trace
+from typing import TypedDict
+
+from openai import AzureOpenAI
 
 from azure.core.credentials import AzureKeyCredential
 from azure.search.documents import SearchClient
 from azure.search.documents.models import VectorizedQuery
 
-import os
-# set environment variables before importing any other code
-from dotenv import load_dotenv
-load_dotenv()
+from promptflow.tracing import trace
+from promptflow.core import Prompty, AzureOpenAIModelConfiguration
 
 class ChatResponse(TypedDict):
     context: dict
     reply: str
 
-from promptflow.core import tool, Prompty, AzureOpenAIModelConfiguration
-
-@tool
+@trace
 def get_chat_response(chat_input: str, chat_history: list = []) -> ChatResponse:
 
     model_config = AzureOpenAIModelConfiguration(
@@ -75,7 +73,7 @@ def get_documents(search_query: str, num_docs=3):
 
     index_name = os.environ["AZUREAI_SEARCH_INDEX_NAME"]
 
-    #  retrieve documents relevant to the user's question from Cognitive Search
+    #  retrieve documents relevant to the user's query from Azure AI Search index
     search_client = SearchClient(
         endpoint=os.environ["AZURE_SEARCH_ENDPOINT"],
         credential=AzureKeyCredential(os.environ["AZURE_SEARCH_KEY"]),

src/deployment/deploy.py

@@ -57,7 +57,7 @@ def deploy_flow(endpoint_name, deployment_name):
         ),
         # instance type comes with associated cost.
         # make sure you have quota for the specified instance type
-        # See more details here: https://learn.microsoft.com/en-us/azure/machine-learning/reference-managed-online-endpoints-vm-sku-list?view=azureml-api-2
+        # See more details here: https://learn.microsoft.com/azure/machine-learning/reference-managed-online-endpoints-vm-sku-list
         instance_type="Standard_DS3_v2",
         instance_count=1,
         environment_variables={
@@ -77,26 +77,24 @@ def deploy_flow(endpoint_name, deployment_name):
     )
 
     # 1. create endpoint
-    created_endpoint = client.begin_create_or_update(endpoint).result() # result() means we wait on this to complete
+    client.begin_create_or_update(endpoint).result() # result() means we wait on this to complete
 
     # 2. create deployment
-    created_deployment = client.begin_create_or_update(deployment).result()
+    client.begin_create_or_update(deployment).result()
 
     # 3. update endpoint traffic for the deployment
     endpoint.traffic = {deployment_name: 100} # 100% of traffic
     client.begin_create_or_update(endpoint).result()
 
     output_deployment_details(client, endpoint_name, deployment_name)
 
-    return created_endpoint, created_deployment
-
 def output_deployment_details(client, endpoint_name, deployment_name) -> str:
     print("\n ~~~Deployment details~~~")
     print(f"Your online endpoint name is: {endpoint_name}")
     print(f"Your deployment name is: {deployment_name}")
 
     print("\n ~~~Test in the Azure AI Studio~~~")
-    print(f"Follow this link to your deployment in the Azure AI Studio:")
+    print("\n Follow this link to your deployment in the Azure AI Studio:")
     print(get_ai_studio_url_for_deploy(client=client, endpoint_name=endpoint_name, deployment_name=deployment_name))
 
 if __name__ == "__main__":

src/evaluation/evaluate.py

@@ -19,7 +19,7 @@ def load_jsonl(path):
     with open(path, "r") as f:
         return [json.loads(line) for line in f.readlines()]
 
-def copilot_qna(*, chat_input, **kwargs):
+def copilot_wrapper(*, chat_input, **kwargs):
     from copilot_flow.copilot import get_chat_response
 
     result = get_chat_response(chat_input)
@@ -48,7 +48,7 @@ def run_evaluation(name, dataset_path):
     output_path = "./evaluation/eval_results/eval_results.jsonl"
 
     result = evaluate(
-        target=copilot_qna,
+        target=copilot_wrapper,
         evaluation_name=name,
         data=data_path,
         evaluators={

src/evaluation/evaluation_dataset.jsonl

@@ -2,12 +2,12 @@
 {"chat_input": "Which camping table holds the most weight?", "truth": "The Adventure Dining Table has a higher weight capacity than all of the other camping tables mentioned"}
 {"chat_input": "How much do the TrailWalker Hiking Shoes cost? ", "truth": "The Trailewalker Hiking Shoes are priced at $110"}
 {"chat_input": "What is the proper care for trailwalker hiking shoes? ", "truth": "After each use, remove any dirt or debris by brushing or wiping the shoes with a damp cloth."}
-{"chat_input": "What brand is for TrailMaster tent? ", "truth": "OutdoorLiving"}
+{"chat_input": "What brand is TrailMaster tent? ", "truth": "OutdoorLiving"}
 {"chat_input": "How do I carry the TrailMaster tent around? ", "truth": " Carry bag included for convenient storage and transportation"}
 {"chat_input": "What is the floor area for Floor Area? ", "truth": "80 square feet"}
 {"chat_input": "What is the material for TrailBlaze Hiking Pants?", "truth": "Made of high-quality nylon fabric"}
 {"chat_input": "What color does TrailBlaze Hiking Pants come in?", "truth": "Khaki"}
-{"chat_input": "Cant he warrenty for TrailBlaze pants be transfered? ", "truth": "The warranty is non-transferable and applies only to the original purchaser of the TrailBlaze Hiking Pants. It is valid only when the product is purchased from an authorized retailer."}
-{"chat_input": "How long are the TrailBlaze pants under warrenty for? ", "truth": " The TrailBlaze Hiking Pants are backed by a 1-year limited warranty from the date of purchase."}
+{"chat_input": "Can the warrenty for TrailBlaze pants be transfered? ", "truth": "The warranty is non-transferable and applies only to the original purchaser of the TrailBlaze Hiking Pants. It is valid only when the product is purchased from an authorized retailer."}
+{"chat_input": "How long are the TrailBlaze pants under warranty for? ", "truth": " The TrailBlaze Hiking Pants are backed by a 1-year limited warranty from the date of purchase."}
 {"chat_input": "What is the material for PowerBurner Camping Stove? ", "truth": "Stainless Steel"}
 {"chat_input": "Is France in Europe?", "truth": "Sorry, I can only queries related to outdoor/camping gear and equipment"}

src/indexing/build_index.py

@@ -44,7 +44,7 @@ def build_aisearch_index(index_name, path_to_data):
       token_overlap_across_chunks = 0, # Optional field - Number of tokens to overlap between chunks
   )
 
-  # register the index so that it shows up in the project
+  # register the index so that it shows up in the cloud project
   client.indexes.create_or_update(Index(name=index_name, path=index_path))
 
   print(f"Local Path: {index_path}")