update doc

examples/flows/chat/use_tools_with_chat_models/README.md

@@ -3,22 +3,22 @@
 This flow covers how to use the LLM tool chat API in combination with external functions to extend the 
 capabilities of GPT models. 
 
-`tools` is an optional parameter in the <a href='https://platform.openai.com/docs/api-reference/chat/create' target='_blank'>Chat Completion API</a> which can be used to provide function 
+`tools` is an optional parameter in the <a href='https://platform.openai.com/docs/api-reference/chat/create' target='_blank'>Chat Completion API</a> which can be used to provide tool 
 specifications. The purpose of this is to enable models to generate function arguments which adhere to the provided 
-specifications. Note that the API will not actually execute any function calls. It is up to developers to execute 
-function calls using model outputs. 
+specifications. Note that the API will not actually execute any tool calls. It is up to developers to execute 
+tool calls using model outputs. 
 
 If the `tools` parameter is provided then by default the model will decide when it is appropriate to use one of the 
-tools. The API can be forced to use a specific function by setting the `tool_choice` parameter to 
-`{"name": "<insert-function-name>"}`. The API can also be forced to not use any function by setting the `tool_choice` 
-parameter to `"none"`. If a function is used, the output will contain `"finish_reason": "tool_choice"` in the 
-response, as well as a `tool_choice` object that has the name of the function and the generated function arguments. 
+tools. The API can be forced to use a specific tool by setting the `tool_choice` parameter to 
+`{"type": "function", "function": {"name": "<insert-function-name>"}}`. The API can also be forced to not use any tool by setting the `tool_choice` 
+parameter to `"none"`. If a tool is used, the output will contain `"finish_reason": "tool_choice"` in the 
+response, as well as a `tool_choice` object that has the name of the tool and the generated function arguments. 
 You can refer to <a href='https://github.com/openai/openai-cookbook/blob/main/examples/How_to_call_functions_with_chat_models.ipynb' target='_blank'>openai sample</a> for more details.
 
 
 ## What you will learn
 
-In this flow, you will learn how to use tools with LLM chat models and how to compose function role message in prompt template.
+In this flow, you will learn how to use tools with LLM chat models and how to compose tool role message in prompt template.
 
 ## Tools used in this flow
 - LLM tool
@@ -55,7 +55,7 @@ pf connection show --name open_ai_connection
 pf flow test --flow . 
 
 # run chat flow with new question
-pf flow test --flow . --inputs question="How about London next week?"
+pf flow test --flow . --inputs question="What's the current weather like in San Francisco, Tokyo and Paris in Fahrenheit?"
 
 # start a interactive chat session in CLI
 pf flow test --flow . --interactive
@@ -67,5 +67,5 @@ pf flow test --flow . --interactive --verbose
 ## References
 - <a href='https://github.com/openai/openai-cookbook/blob/main/examples/How_to_call_functions_with_chat_models.ipynb' target='_blank'>OpenAI cookbook example</a>
 - <a href='https://openai.com/blog/function-calling-and-other-api-updates?ref=upstract.com' target='_blank'>OpenAI function calling announcement</a> 
-- <a href='https://platform.openai.com/docs/guides/gpt/function-calling' target='_blank'>OpenAI function calling doc</a>
-- <a href='https://platform.openai.com/docs/api-reference/chat/create' target='_blank'>OpenAI function calling API</a>
+- <a href='https://platform.openai.com/docs/guides/function-calling' target='_blank'>OpenAI function calling doc</a>
+- <a href='https://platform.openai.com/docs/api-reference/chat/create' target='_blank'>OpenAI tools API</a>

examples/flows/chat/use_tools_with_chat_models/flow.dag.yaml

@@ -51,7 +51,7 @@ nodes:
  tool: promptflow.tools.llm.llm
  path: use_tools_with_chat_models.jinja2
  inputs:
- connection: azure_open_ai_connection
+ connection: open_ai_connection
  api: chat
  deployment_name: gpt-35-turbo-1106
  temperature: 0.7