How to Retrieve Phoenix Trace Links in Your Code Implementation

# managing tracer objects in cache
session = px.launch_app(use_temp_dir=False)
tracers = {}


@extend_schema(
    tags=['Main'],
    operation_id='query',
    summary='Chained Query',
    description='API for Changed Queries',
    parameters=[
        OpenApiParameter(name='app_id', description='App ID', required=True, type=OpenApiTypes.UUID,
                         location=OpenApiParameter.PATH),
        OpenApiParameter(name='thread_id', description='Thread ID', required=True, type=OpenApiTypes.UUID,
                         location=OpenApiParameter.PATH),
    ],
    responses={200: OpenApiResponse(description='Success')}
)
@api_view(['POST'])
def query(request, app_id, thread_id):
    if thread_id not in tracers.keys():
        tracer = tracing.setup_tracing(thread_id)
        tracers[thread_id] = tracer
    else:
        tracer = tracers[thread_id]

    logging.info("New conversation started for app id : %s holding the thread id : %s", app_id, thread_id)

    if request.method == 'POST':

        # receiving json payload
        payload = request.data
        query = payload['query']
        type = payload['type']
        image_file_path = ""

        # handle language
        language = True
        if 'language' in payload:
            language_str = payload['language']
            if language_str == 'true':
                language = True
            elif language_str == 'false':
                language = False

        # handle voice
        voice = False
        if 'voice' in payload:
            voice = eval(payload['voice'].capitalize())

        memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True,
                                          input_key="question", output_key="answer")

        # Answer Generation
        with tracer.start_as_current_span(name="completions") as span:
            try:
                span.set_attribute("input.value", f"Query : {query}, Language : {str(language)}")
                if type == 'Agent':
                    span.set_attribute("openinference.span.kind", "AGENT")
                    answer, current_memory = conversational_agent.get_result(
                        query, language, voice, memory, app_id, thread_id, tracer)
                elif type == 'Chain':
                    span.set_attribute("openinference.span.kind", "CHAIN")
                    answer, current_memory = conversational_chain.get_result(
                        query, language, voice, image_file_path, memory, app_id, thread_id, tracer)
                span.set_status(Status(StatusCode.OK))
                span.set_attribute("output.value", answer["answer"])
                return Response(answer, status=status.HTTP_200_OK)
            except Exception as e:
                logging.info("Exception occured while trying to call get result method : %s", e)
                answer = {
                    "answer": "Query overload in LLM. Please try again shortly",
                    "type": "doc",
                    "documents": ['']
                }
                span.set_status(Status(StatusCode.ERROR))
                return Response(answer, status=status.HTTP_200_OK)