langtrace-python-sdk 2.0.3__py3-none-any.whl → 2.0.5__py3-none-any.whl

examples/anthropic_example/completion.py

@@ -7,7 +7,7 @@ from langtrace_python_sdk import langtrace, with_langtrace_root_span
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 
 @with_langtrace_root_span("messages_create")

examples/chroma_example/basic.py

@@ -7,7 +7,7 @@ from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 
 @with_langtrace_root_span()

examples/cohere_example/chat.py

@@ -7,7 +7,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 co = cohere.Client()
 
@@ -17,11 +18,14 @@ def chat_comp():
     response = co.chat(
         chat_history=[
             {"role": "USER", "message": "Who discovered gravity?"},
-            {"role": "CHATBOT", "message": "The man who is widely credited with discovering gravity is Sir Isaac Newton"}
+            {
+                "role": "CHATBOT",
+                "message": "The man who is widely credited with discovering gravity is Sir Isaac Newton",
+            },
         ],
         message="Tell me a story in 3 sentences or less?",
         preamble="answer like a pirate",
         # perform web search before answering the question. You can also use your own custom connector.
-        connectors=[{"id": "web-search"}]
+        connectors=[{"id": "web-search"}],
     )
     print(response)

examples/cohere_example/chat_stream.py

@@ -5,7 +5,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 co = cohere.Client()
 
@@ -13,7 +14,11 @@ co = cohere.Client()
 # @with_langtrace_root_span("chat_stream")
 def chat_stream():
     result = []
-    for event in co.chat_stream(message="Tell me a short story in 2 lines", preamble="Respond like a pirate", max_tokens=100):
+    for event in co.chat_stream(
+        message="Tell me a short story in 2 lines",
+        preamble="Respond like a pirate",
+        max_tokens=100,
+    ):
         if event.event_type == "text-generation":
             result.append(event.text)
         elif event.event_type == "stream-end":

examples/cohere_example/embed.py

@@ -7,7 +7,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 co = cohere.Client()
 

examples/cohere_example/rerank.py

@@ -7,7 +7,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 co = cohere.Client()
 

examples/cohere_example/tools.py

@@ -7,7 +7,7 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 co = cohere.Client()
 
@@ -17,10 +17,26 @@ student_custom_functions = [
         "name": "extract_student_info",
         "description": "Get the student information from the body of the input text",
         "parameter_definitions": {
-            "name": {"type": "string", "description": "Name of the person", "required": True},
-            "major": {"type": "string", "description": "Major subject.", "required": True},
-            "school": {"type": "string", "description": "The university name.", "required": True},
-            "grades": {"type": "integer", "description": "GPA of the student.", "required": True},
+            "name": {
+                "type": "string",
+                "description": "Name of the person",
+                "required": True,
+            },
+            "major": {
+                "type": "string",
+                "description": "Major subject.",
+                "required": True,
+            },
+            "school": {
+                "type": "string",
+                "description": "The university name.",
+                "required": True,
+            },
+            "grades": {
+                "type": "integer",
+                "description": "GPA of the student.",
+                "required": True,
+            },
             "club": {
                 "type": "string",
                 "description": "School club for extracurricular activities. ",

examples/fastapi_example/basic_route.py

@@ -8,7 +8,7 @@ from openai import OpenAI
 
 from langtrace_python_sdk import langtrace
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 app = FastAPI()
 client = OpenAI()
 

examples/hiveagent_example/basic.py

@@ -6,7 +6,7 @@ from openai import OpenAI
 load_dotenv()
 
 langtrace.init(
-    write_to_langtrace_cloud=False,
+    write_spans_to_console=True,
     api_host="http://localhost:3000",
 )
 

examples/langchain_example/groq_example.py

@@ -22,7 +22,9 @@ def groq_example():
     prompt = ChatPromptTemplate.from_messages([("system", system), ("human", human)])
 
     chain = prompt | chat
-    result = chain.invoke({"text": "Explain the importance of low latency LLMs in 2 sentences or less."})
+    result = chain.invoke(
+        {"text": "Explain the importance of low latency LLMs in 2 sentences or less."}
+    )
     # print(result)
     return result
 

examples/langchain_example/langgraph_example.py

@@ -48,17 +48,12 @@ def invoke_tool(state):
     if multiply_call is None:
         raise Exception("No adder input found.")
 
-    res = multiply.invoke(
-        json.loads(multiply_call.get("function").get("arguments"))
-    )
+    res = multiply.invoke(json.loads(multiply_call.get("function").get("arguments")))
 
-    return ToolMessage(
-        tool_call_id=multiply_call.get("id"),
-        content=res
-    )
+    return ToolMessage(tool_call_id=multiply_call.get("id"), content=res)
 
 
-@with_langtrace_root_span('langgraph_example')
+@with_langtrace_root_span("langgraph_example")
 def basic():
 
     graph = MessageGraph()
@@ -67,10 +62,14 @@ def basic():
 
     graph.add_node("multiply", invoke_tool)
 
-    graph.add_conditional_edges("oracle", router, {
-        "multiply": "multiply",
-        "end": END,
-    })
+    graph.add_conditional_edges(
+        "oracle",
+        router,
+        {
+            "multiply": "multiply",
+            "end": END,
+        },
+    )
 
     graph.add_edge("multiply", END)
 

examples/llamaindex_example/agent.py

@@ -12,7 +12,7 @@ import nest_asyncio
 
 nest_asyncio.apply()
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 
 def multiply(a: int, b: int) -> int:

examples/llamaindex_example/basic.py

@@ -7,7 +7,7 @@ from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
 _ = load_dotenv(find_dotenv())
 
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 
 @with_langtrace_root_span()

examples/openai_example/async_tool_calling_nonstreaming.py

@@ -9,10 +9,11 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 client = AsyncOpenAI()
 
+
 # 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"):
@@ -20,7 +21,9 @@ def get_current_weather(location, unit="fahrenheit"):
     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})
+        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:
@@ -29,7 +32,12 @@ def get_current_weather(location, unit="fahrenheit"):
 
 async 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?"}]
+    messages = [
+        {
+            "role": "user",
+            "content": "What's the weather like in San Francisco, Tokyo, and Paris?",
+        }
+    ]
     tools = [
         {
             "type": "function",
@@ -90,4 +98,3 @@ async def run_conversation():
         )  # get a new response from the model where it can see the function response
         # print(second_response)
         return second_response
-

examples/openai_example/async_tool_calling_streaming.py

@@ -9,7 +9,7 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 client = AsyncOpenAI()
 
@@ -21,7 +21,9 @@ def get_current_weather(location, unit="fahrenheit"):
     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})
+        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:
@@ -42,7 +44,12 @@ def get_current_time(location):
 
 async 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?"}]
+    messages = [
+        {
+            "role": "user",
+            "content": "What's the weather like in San Francisco, Tokyo, and Paris?",
+        }
+    ]
     tools = [
         {
             "type": "function",
@@ -78,7 +85,7 @@ async def run_conversation():
                     "required": ["location"],
                 },
             },
-        }
+        },
     ]
     response = await client.chat.completions.create(
         model="gpt-4",
@@ -95,29 +102,34 @@ async def run_conversation():
     name = ""
     arguments = ""
     async for chunk in response:
-        if chunk.choices[0].delta is not None and chunk.choices[0].delta.tool_calls is not None:
+        if (
+            chunk.choices[0].delta is not None
+            and chunk.choices[0].delta.tool_calls is not None
+        ):
             for choice in chunk.choices:
                 for tool_call in choice.delta.tool_calls:
                     if tool_call.id and id != tool_call.id:
                         id = tool_call.id if tool_call.id else ""
-                        name = tool_call.function.name if tool_call.function and tool_call.function.name else ""
+                        name = (
+                            tool_call.function.name
+                            if tool_call.function and tool_call.function.name
+                            else ""
+                        )
                         tool_call_dict[name] = {
                             "id": id,
-                            "function": {
-                                "name": name,
-                                "arguments": arguments
-                            },
-                            "type": "function"
+                            "function": {"name": name, "arguments": arguments},
+                            "type": "function",
                         }
-                    arguments += tool_call.function.arguments if tool_call.function and tool_call.function.arguments else ""
+                    arguments += (
+                        tool_call.function.arguments
+                        if tool_call.function and tool_call.function.arguments
+                        else ""
+                    )
                 if name != "":
                     tool_call_dict[name] = {
                         "id": id,
-                        "function": {
-                            "name": name,
-                            "arguments": arguments
-                        },
-                        "type": "function"
+                        "function": {"name": name, "arguments": arguments},
+                        "type": "function",
                     }
     for key, value in tool_call_dict.items():
         tool_calls.append(value)
@@ -133,9 +145,9 @@ async def run_conversation():
         # messages.append(response_message)  # extend conversation with assistant's reply
         # 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_name = tool_call["function"]["name"]
             function_to_call = available_functions[function_name]
-            function_args = json.loads(tool_call['function']['arguments'])
+            function_args = json.loads(tool_call["function"]["arguments"])
             function_response = function_to_call(
                 location=function_args.get("location"),
                 unit=function_args.get("unit"),
@@ -143,10 +155,7 @@ async def run_conversation():
             func_res = json.loads(function_response)
             content = f"Use the below information to answer the user's question: The current weather in {func_res['location']} is {func_res['temperature']} degrees {func_res['unit']}"
             messages.append(
-                {
-                    "role": "system",
-                    "content": content
-                }
+                {"role": "system", "content": content}
             )  # extend conversation with function response
         print(messages)
         second_response = await client.chat.completions.create(
@@ -158,10 +167,13 @@ async def run_conversation():
         async for chunk in second_response:
             if chunk.choices[0].delta.content is not None:
                 content = [
-                    choice.delta.content if choice.delta and
-                    choice.delta.content else ""
-                    for choice in chunk.choices]
-                result.append(
-                    content[0] if len(content) > 0 else "")
+                    (
+                        choice.delta.content
+                        if choice.delta and choice.delta.content
+                        else ""
+                    )
+                    for choice in chunk.choices
+                ]
+                result.append(content[0] if len(content) > 0 else "")
         print("".join(result))
-        # return second_response
+        # return second_response

examples/openai_example/chat_completion.py

@@ -3,11 +3,13 @@ from openai import OpenAI
 
 from langtrace_python_sdk import langtrace
 from langtrace_python_sdk.utils.with_root_span import (
-    with_additional_attributes, with_langtrace_root_span)
+    with_additional_attributes,
+    with_langtrace_root_span,
+)
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 client = OpenAI()
 
 
@@ -15,7 +17,10 @@ client = OpenAI()
 def api():
     response = client.chat.completions.create(
         model="gpt-4",
-        messages=[{"role": "system", "content": "Talk like a pirate"}, {"role": "user", "content": "Tell me a story in 3 sentences or less."}],
+        messages=[
+            {"role": "system", "content": "Talk like a pirate"},
+            {"role": "user", "content": "Tell me a story in 3 sentences or less."},
+        ],
         stream=True,
         # stream=False,
     )
@@ -31,11 +36,10 @@ def chat_completion():
     for chunk in response:
         if chunk.choices[0].delta.content is not None:
             content = [
-                choice.delta.content if choice.delta and
-                choice.delta.content else ""
-                for choice in chunk.choices]
-            result.append(
-                content[0] if len(content) > 0 else "")
+                choice.delta.content if choice.delta and choice.delta.content else ""
+                for choice in chunk.choices
+            ]
+            result.append(content[0] if len(content) > 0 else "")
 
     print("".join(result))
     return response

examples/openai_example/embeddings_create.py

@@ -6,7 +6,8 @@ from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 client = OpenAI()
 
 

examples/openai_example/function_calling.py

@@ -7,7 +7,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 client = OpenAI()
 
@@ -51,11 +52,15 @@ def function_calling():
     for chunk in response:
         if chunk.choices[0].delta.function_call is not None:
             content = [
-                choice.delta.function_call.arguments if choice.delta.function_call and
-                choice.delta.function_call.arguments else ""
-                for choice in chunk.choices]
-            result.append(
-                content[0] if len(content) > 0 else "")
+                (
+                    choice.delta.function_call.arguments
+                    if choice.delta.function_call
+                    and choice.delta.function_call.arguments
+                    else ""
+                )
+                for choice in chunk.choices
+            ]
+            result.append(content[0] if len(content) > 0 else "")
 
     print("".join(result))
 

examples/openai_example/images_generate.py

@@ -6,7 +6,8 @@ from langtrace_python_sdk.utils.with_root_span import with_langtrace_root_span
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 client = OpenAI()
 

examples/openai_example/tool_calling.py

@@ -7,7 +7,7 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
 
 client = OpenAI()
 

examples/openai_example/tool_calling_nonstreaming.py

@@ -9,7 +9,8 @@ from langtrace_python_sdk import langtrace
 
 _ = load_dotenv(find_dotenv())
 
-langtrace.init(write_to_langtrace_cloud=False)
+langtrace.init(write_spans_to_console=True)
+
 
 client = OpenAI()
 
@@ -21,7 +22,9 @@ def get_current_weather(location, unit="fahrenheit"):
     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})
+        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:
@@ -30,7 +33,12 @@ def get_current_weather(location, unit="fahrenheit"):
 
 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?"}]
+    messages = [
+        {
+            "role": "user",
+            "content": "What's the weather like in San Francisco, Tokyo, and Paris?",
+        }
+    ]
     tools = [
         {
             "type": "function",