Setup Sessions

How to track sessions across multiple traces

Sessions UI is available in Phoenix 7.0 and requires a db migration if you’re coming from an older version of Phoenix.

If you are using LangChain, you can use LangChain’s native threads to track sessions! See https://docs.smith.langchain.com/old/monitoring/faq/threads

Evals in the Phoenix UI

A Session is a sequence of traces representing a single session (e.g. a session or a thread). Each response is represented as its own trace, but these traces are linked together by being part of the same session.

To associate traces together, you need to pass in a special metadata key where the value is the unique identifier for that thread.

Example Notebooks

Use Case	Language	Links
OpenAI tracing with Sessions	Python
LlamaIndex tracing with Sessions	Python
OpenAI tracing with Sessions	TS/JS

Logging Conversations

Below is an example of logging conversations:

Python

First make sure you have the required dependancies installed

pip install openinference-instrumentation

Below is an example of how to use openinference.instrumentation to the traces created.

import uuid

import openai
from openinference.instrumentation import using_session
from openinference.semconv.trace import SpanAttributes
from opentelemetry import trace

client = openai.Client()
session_id = str(uuid.uuid4())

tracer = trace.get_tracer(__name__)

@tracer.start_as_current_span(name="agent", attributes={SpanAttributes.OPENINFERENCE_SPAN_KIND: "agent"})
def assistant(
  messages: list[dict],
  session_id: str = str,
):
  current_span = trace.get_current_span()
  current_span.set_attribute(SpanAttributes.SESSION_ID, session_id)
  current_span.set_attribute(SpanAttributes.INPUT_VALUE, messages[-1].get('content'))

  # Propagate the session_id down to spans crated by the OpenAI instrumentation
  # This is not strictly necessary, but it helps to correlate the spans to the same session
  with using_session(session_id):
  response = client.chat.completions.create(
      model="gpt-3.5-turbo",
      messages=[{"role": "system", "content": "You are a helpful assistant."}] + messages,
  ).choices[0].message

  current_span.set_attribute(SpanAttributes.OUTPUT_VALUE, response.content)
  return response

messages = [
  {"role": "user", "content": "hi! im bob"}
]
response = assistant(
  messages,
  session_id=session_id,
)
messages = messages + [
  response,
  {"role": "user", "content": "what's my name?"}
]
response = assistant(
  messages,
  session_id=session_id,
)

Viewing Sessions

You can view the sessions for a given project by clicking on the “Sessions” tab in the project. You will see a list of all the recent sessions as well as some analytics. You can search the content of the messages to narrow down the list.

View all the sessions under a project

You can then click into a given session. This will open the history of a particular session. If the sessions contain input / output, you will see a chatbot-like UI where you can see the a history of inputs and outputs.

Session details view

How to track sessions with LangChain

For LangChain, in order to log runs as part of the same thread you need to pass a special metadata key to the run. The key value is the unique identifier for that conversation. The key name should be one of:

• session_id

• thread_id

• conversation_id.