(test) tool/function calling + streaming

litellm/tests/test_function_calling.py

@@ -108,4 +108,87 @@ def test_parallel_function_call():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-test_parallel_function_call()
+# test_parallel_function_call()
+
+
+
+
+def test_parallel_function_call_stream():
+    try:
+        # Step 1: send the conversation and available functions to the model
+        messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
+        tools = [
+            {
+                "type": "function",
+                "function": {
+                    "name": "get_current_weather",
+                    "description": "Get the current weather in a given location",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+                        },
+                        "required": ["location"],
+                    },
+                },
+            }
+        ]
+        response = litellm.completion(
+            model="gpt-3.5-turbo-1106",
+            messages=messages,
+            tools=tools,
+            stream=True,
+            tool_choice="auto",  # auto is default, but we'll be explicit
+        )
+        print("Response\n", response)
+        for chunk in response:
+            print(chunk)
+        # response_message = response.choices[0].message
+        # tool_calls = response_message.tool_calls
+
+        # print("length of tool calls", len(tool_calls))
+        # print("Expecting there to be 3 tool calls")
+        # assert len(tool_calls) > 1 # this has to call the function for SF, Tokyo and parise
+
+        # # Step 2: check if the model wanted to call a function
+        # if tool_calls:
+        #     # Step 3: call the function
+        #     # Note: the JSON response may not always be valid; be sure to handle errors
+        #     available_functions = {
+        #         "get_current_weather": get_current_weather,
+        #     }  # only one function in this example, but you can have multiple
+        #     messages.append(response_message)  # extend conversation with assistant's reply
+        #     print("Response message\n", response_message)
+        #     # Step 4: send the info for each function call and function response to the model
+        #     for tool_call in tool_calls:
+        #         function_name = tool_call.function.name
+        #         function_to_call = available_functions[function_name]
+        #         function_args = json.loads(tool_call.function.arguments)
+        #         function_response = function_to_call(
+        #             location=function_args.get("location"),
+        #             unit=function_args.get("unit"),
+        #         )
+        #         messages.append(
+        #             {
+        #                 "tool_call_id": tool_call.id,
+        #                 "role": "tool",
+        #                 "name": function_name,
+        #                 "content": function_response,
+        #             }
+        #         )  # extend conversation with function response
+        #     second_response = litellm.completion(
+        #         model="gpt-3.5-turbo-1106",
+        #         messages=messages,
+        #         temperature=0.2,
+        #         seed=22
+        #     )  # get a new response from the model where it can see the function response
+        #     print("second response\n", second_response)
+        #     return second_response
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+test_parallel_function_call_stream()