User Tracking

Set a session identifier as user_id tag for every request, e.g. in a request handler. This will set a Python contextvar and will be picked up by all traces of the current context. You can additionally set user_name and user_email tags.

graphsignal.set_context_tag('user_id', my_user_id)

You can also set tags directly, when tracing manually:

with graphsignal.trace('generate', tags=dict(user_id=my_user_id)):
    ...

Set a user_id tag in request, call or run context. You can additionally set user_name and user_email tags.

graphsignal.set_context_tag('user_id', my_user_id)

Alternatively, a more reliable way to set user_id and other tags is passing tags in extra_headers argument as comma-separated key-value pairs.

client = OpenAI()
response = client.chat.completions.create(
    model="gpt-3.5-turbo", 
    messages=[{'role': 'user', 'content': 'Tell me a joke'}],
    extra_headers: {
        'Graphsignal-Tags': f'user_id={my_user_id}'
    })

In case of automatic integration, set a user_id tag in request, call or run context. You can additionally set user_name and user_email tags.

graphsignal.set_context_tag('user_id', my_user_id)

Alternatively, a more reliable way to set user_id and other tags is passing tags dictionary to callback constructor.

from graphsignal.callbacks.langchain import GraphsignalCallbackHandler, GraphsignalAsyncCallbackHandler

chat = ChatOpenAI(
    callbacks=[GraphsignalCallbackHandler(tags=dict(user_id=my_user_id))])

If you are running a single process per session and added Graphsignal at command line, you can set the user_id tag in an environment variable. You can additionally set user_name and user_email tags.

env GRAPHSIGNAL_TAGS="user_id=123" python -m graphsignal <script>