chore: add back openai tool choice arg (#245)

* chore: add back openai tool choice arg

* style: fix formating

Author: darshit-s3

src/examples/openai_example/chat_completion_tool_choice.py

@@ -0,0 +1,73 @@
+# Example taken from https://platform.openai.com/docs/guides/function-calling
+import json
+
+from dotenv import find_dotenv, load_dotenv
+from openai import OpenAI
+
+from langtrace_python_sdk import langtrace
+
+client = OpenAI()
+
+_ = load_dotenv(find_dotenv())
+
+langtrace.init(
+    write_spans_to_console=True,
+)
+
+
+# Example dummy function hard coded to return the same weather
+# In production, this could be your backend API or an external API
+def get_current_weather(location, unit="fahrenheit"):
+    """Get the current weather in a given location"""
+    if "tokyo" in location.lower():
+        return json.dumps({"location": "Tokyo", "temperature": "10", "unit": unit})
+    elif "san francisco" in location.lower():
+        return json.dumps(
+            {"location": "San Francisco", "temperature": "72", "unit": unit}
+        )
+    elif "paris" in location.lower():
+        return json.dumps({"location": "Paris", "temperature": "22", "unit": unit})
+    else:
+        return json.dumps({"location": location, "temperature": "unknown"})
+
+
+def run_conversation():
+    # 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 = client.chat.completions.create(
+        model="gpt-4o",
+        messages=messages,
+        tools=tools,
+        tool_choice="required",  # auto is default, but we'll be explicit
+    )
+    response_message = response.choices[0].message
+    tool_calls = response_message.tool_calls
+    print(tool_calls)
+
+
+print(run_conversation())

src/langtrace_python_sdk/instrumentation/anthropic/patch.py

@@ -48,7 +48,9 @@ def traced_method(wrapped, instance, args, kwargs):
         prompts = kwargs.get("messages", [])
         system = kwargs.get("system")
         if system:
-            prompts = [{"role": "system", "content": system}] + kwargs.get("messages", [])
+            prompts = [{"role": "system", "content": system}] + kwargs.get(
+                "messages", []
+            )
 
         span_attributes = {
             **get_langtrace_attributes(version, service_provider),

src/langtrace_python_sdk/instrumentation/gemini/patch.py

@@ -110,7 +110,10 @@ def get_llm_model(instance):
 
 def serialize_prompts(args, kwargs, instance):
     prompts = []
-    if hasattr(instance, "_system_instruction") and instance._system_instruction is not None:
+    if (
+        hasattr(instance, "_system_instruction")
+        and instance._system_instruction is not None
+    ):
         system_prompt = {
             "role": "system",
             "content": instance._system_instruction.__dict__["_pb"].parts[0].text,

src/langtrace_python_sdk/utils/llm.py

@@ -123,6 +123,7 @@ def get_llm_request_attributes(kwargs, prompts=None, model=None):
         SpanAttributes.LLM_FREQUENCY_PENALTY: kwargs.get("frequency_penalty"),
         SpanAttributes.LLM_REQUEST_SEED: kwargs.get("seed"),
         SpanAttributes.LLM_TOOLS: json.dumps(tools) if tools else None,
+        SpanAttributes.LLM_TOOL_CHOICE: kwargs.get("tool_choice"),
         SpanAttributes.LLM_REQUEST_LOGPROPS: kwargs.get("logprobs"),
         SpanAttributes.LLM_REQUEST_LOGITBIAS: kwargs.get("logit_bias"),
         SpanAttributes.LLM_REQUEST_TOP_LOGPROPS: kwargs.get("top_logprobs"),