chore: import upstream snapshot with attribution

examples/flows/standard/conditional-flow-for-switch/README.md

@@ -0,0 +1,78 @@
+# Conditional flow for switch scenario
+
+This example is a conditional flow for switch scenario.
+
+By following this example, you will learn how to create a conditional flow using the `activate config`.
+
+## Flow description
+
+In this flow, we set the background to the search function of a certain mall, use `activate config` to implement switch logic and determine user intent based on the input queries to achieve dynamic processing and generate user-oriented output.
+
+- The `classify_with_llm` node analyzes user intent based on input query and provides one of the following results: "product_recommendation," "order_search," or "product_info".
+- The `class_check` node generates the correctly formatted user intent.
+- The `product_recommendation`, `order_search`, and `product_info` nodes are configured with activate config and are only executed when the output from `class_check` meets the specified conditions.
+- The `generate_response` node generates user-facing output.
+
+For example, as the shown below, the input query is "When will my order be shipped" and the LLM node classifies the user intent as "order_search", resulting in both the `product_info` and `product_recommendation` nodes being bypassed and only the `order_search` node being executed, and then generating the outputs.
+
+![conditional_flow_for_switch](conditional_flow_for_switch.png)
+
+## Prerequisites
+
+Install promptflow sdk and other dependencies:
+```bash
+pip install -r requirements.txt
+```
+
+## Setup connection
+
+Prepare your Azure OpenAI resource follow this [instruction](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal) and get your `api_key` if you don't have one.
+
+Note in this example, we are using [chat api](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/chatgpt?pivots=programming-language-chat-completions), please use `gpt-35-turbo` or `gpt-4` model deployment.
+
+Create connection if you haven't done that. Ensure you have put your azure OpenAI endpoint key in [azure_openai.yml](../../../connections/azure_openai.yml) file.
+```bash
+# Override keys with --set to avoid yaml file changes
+pf connection create -f ../../../connections/azure_openai.yml --name open_ai_connection --set api_key=<your_api_key> api_base=<your_api_base>
+```
+
+Note in [flow.dag.yaml](flow.dag.yaml) we are using connection named `open_ai_connection`.
+```bash
+# show registered connection
+pf connection show --name open_ai_connection
+```
+
+## Run flow
+
+- Test flow
+```bash
+# test with default input value in flow.dag.yaml
+pf flow test --flow .
+
+# test with flow inputs
+pf flow test --flow . --inputs query="When will my order be shipped?"
+```
+
+- Create run with multiple lines of data
+```bash
+# create a random run name
+run_name="conditional_flow_for_switch_"$(openssl rand -hex 12)
+
+# create run
+pf run create --flow . --data ./data.jsonl --column-mapping query='${data.query}' --stream --name $run_name
+```
+
+- List and show run metadata
+```bash
+# list created run
+pf run list
+
+# show specific run detail
+pf run show --name $run_name
+
+# show output
+pf run show-details --name $run_name
+
+# visualize run in browser
+pf run visualize --name $run_name
+```

examples/flows/standard/conditional-flow-for-switch/class_check.py

@@ -0,0 +1,8 @@
+from promptflow.core import tool
+
+
+@tool
+def class_check(llm_result: str) -> str:
+    intentions_list = ["order_search", "product_info", "product_recommendation"]
+    matches = [intention for intention in intentions_list if intention in llm_result.lower()]
+    return matches[0] if matches else "unknown"

examples/flows/standard/conditional-flow-for-switch/classify_with_llm.jinja2

@@ -0,0 +1,11 @@
+# system:
+There is a search bar in the mall APP and users can enter any query in the search bar.
+
+The user may want to search for orders, view product information, or seek recommended products.
+
+Therefore, please classify user intentions into the following three types according to the query: product_recommendation, order_search, product_info
+
+Please note that only the above three situations can be returned, and try not to include other return values.
+
+# user:
+The user's query is {{query}}

examples/flows/standard/conditional-flow-for-switch/data.jsonl

@@ -0,0 +1,3 @@
+{"query": "When will my order be shipped?"}
+{"query": "Can you help me find information about this T-shirt?"}
+{"query": "Can you recommend me a useful prompt tool?"}

examples/flows/standard/conditional-flow-for-switch/flow.dag.yaml

@@ -0,0 +1,69 @@
+$schema: https://azuremlschemas.azureedge.net/promptflow/latest/Flow.schema.json
+inputs:
+  query:
+    type: string
+    default: When will my order be shipped?
+outputs:
+  response:
+    type: string
+    reference: ${generate_response.output}
+nodes:
+- name: classify_with_llm
+  type: llm
+  source:
+    type: code
+    path: classify_with_llm.jinja2
+  inputs:
+    deployment_name: gpt-35-turbo
+    max_tokens: 128
+    query: ${inputs.query}
+  connection: open_ai_connection
+  api: chat
+- name: class_check
+  type: python
+  source:
+    type: code
+    path: class_check.py
+  inputs:
+    llm_result: ${classify_with_llm.output}
+- name: order_search
+  type: python
+  source:
+    type: code
+    path: order_search.py
+  inputs:
+    query: ${inputs.query}
+  activate:
+    when: ${class_check.output}
+    is: order_search
+- name: product_info
+  type: python
+  source:
+    type: code
+    path: product_info.py
+  inputs:
+    query: ${inputs.query}
+  activate:
+    when: ${class_check.output}
+    is: product_info
+- name: product_recommendation
+  type: python
+  source:
+    type: code
+    path: product_recommendation.py
+  inputs:
+    query: ${inputs.query}
+  activate:
+    when: ${class_check.output}
+    is: product_recommendation
+- name: generate_response
+  type: python
+  source:
+    type: code
+    path: generate_response.py
+  inputs:
+    order_search: ${order_search.output}
+    product_info: ${product_info.output}
+    product_recommendation: ${product_recommendation.output}
+environment:
+    python_requirements_txt: requirements.txt

examples/flows/standard/conditional-flow-for-switch/generate_response.py

@@ -0,0 +1,8 @@
+from promptflow.core import tool
+
+
+@tool
+def generate_response(order_search="", product_info="", product_recommendation="") -> str:
+    default_response = "Sorry, no results matching your search were found."
+    responses = [order_search, product_info, product_recommendation]
+    return next((response for response in responses if response), default_response)

examples/flows/standard/conditional-flow-for-switch/order_search.py

@@ -0,0 +1,7 @@
+from promptflow.core import tool
+
+
+@tool
+def order_search(query: str) -> str:
+    print(f"Your query is {query}.\nSearching for order...")
+    return "Your order is being mailed, please wait patiently."

examples/flows/standard/conditional-flow-for-switch/product_info.py

@@ -0,0 +1,7 @@
+from promptflow.core import tool
+
+
+@tool
+def product_info(query: str) -> str:
+    print(f"Your query is {query}.\nLooking for product information...")
+    return "This product is produced by Microsoft."

examples/flows/standard/conditional-flow-for-switch/product_recommendation.py

@@ -0,0 +1,7 @@
+from promptflow.core import tool
+
+
+@tool
+def product_recommendation(query: str) -> str:
+    print(f"Your query is {query}.\nRecommending products...")
+    return "I recommend promptflow to you, which can solve your problem very well."

examples/flows/standard/conditional-flow-for-switch/requirements.txt

@@ -0,0 +1,2 @@
+promptflow
+promptflow-tools