Tracing
Rasa Pro License
You'll need a license to get started with Rasa Pro. Talk with Sales
Tracing
Distributed tracing tracks requests as they flow through a distributed system (in this case: a Rasa assistant), sending data about the requests to a tracing backend which collects all trace data and enables inspecting it. Trace data helps you understand the flow of requests through both the components of a single service (Rasa itself), and across different distributed services, for example, your action server.
Supported Tracing Backends/Collectors
To trace requests in Rasa Pro, you can either use Jaeger as a backend, or use the OTEL Collector (OpenTelemetry Collector). to collect traces and then send them to the backend of your choice. See Configuring a Tracing Backend or Collector for instructions.
Enabling / Disabling
Tracing is automatically enabled in Rasa Pro by configuring a supported tracing backend. No further action is required to enable tracing.
You can disable tracing by leaving the tracing:
configuration key empty
in your endpoints file.
Action Server
The trace context is sent along with requests to the custom action server using the W3C Trace Context Specification. You can use this trace context to continue tracing the request through your custom action code. See traced events for details on what attributes are made available as part of the trace context.
Configuring a Tracing Backend or Collector
To configure a tracing backend or collector, add a tracing
entry to your endpoints
i.e. in your endpoints.yml
file, or in the relevant section of your Helm values in a deployment.
Jaeger
To configure a Jaeger tracing backend, specify the type
as jaeger
.
OTEL Collector
Collectors are components that collect traces in a vendor-agnostic way and then forward them to various backends. For example, the OpenTelemetry Collector (OTEL) can collect traces from multiple different components and instrumentation libraries, and then export them to multiple different backends e.g. jaeger.
To configure an OTEL Collector, specify the type
as otlp
.
Traced Events
The Rasa service areas that are traceable cover the actions required to:
- train a model (i.e., the training of each graph component)
- handle a message
Model Training
Tracing is enabled for model training by instrumenting Rasa GraphTrainer
and GraphNode
classes.
GraphTrainer
Attributes
The following attributes can be inspected during training of GraphTrainer
:
training_type
of model configuration:"NLU"
"CORE"
"BOTH"
"END-TO-END"
language
of model configurationrecipe_name
used in theconfig.yml
fileoutput_filename
: the location where the packaged model is savedis_finetuning
: boolean argument, ifTrue
enables incremental training
GraphNode
Attributes
The following attributes are captured during the training (as well as prediction during message handling) of every graph node:
node_name
component_class
fn_name
: method of component class that gets called
Message Handling
The following Rasa classes are instrumented to enable tracing during message handling:
Namely, these operations are now traceable:
- receiving a message
- parsing the message
- predicting the next action
- running the action
- retrieving and saving the tracker
- locking the conversation
- publishing to the event broker
- passing the trace context to the action server
Agent
Attributes
Tracing the Agent
instance handling a message captures the following attributes:
input_channel
: the name of the channel connectorsender_id
: the conversation idmodel_id
: a unique identifier for the modelmodel_name
: the model name
MessageProcessor
Attributes
The following MessageProcessor
attributes are extracted during the tracing:
number_of_events
: number of events in trackeraction_name
: the name of the predicted and executed actionsender_id
: the conversation id of theDialogueStateTracker
objectmessage_id
: the unique message id
The latter three attributes are also injected in the trace context that gets passed to the requests made to the custom action server.
TrackerStore
& LockStore
Attributes
Observable TrackerStore
and LockStore
attributes include:
number_of_streamed_events
: number of new events to streambroker_class
: theEventBroker
on which the new events are publishedlock_store_class
: Name of lock store used to lock conversations while messages are actively processed