Skip to content


Apps in trulens derive from two classes, AppDefinition and App. The first contains only serialized or serializable components in a JSON-like format while the latter contains the executable apps that may or may not be serializable.


Bases: WithClassInfo, SerialModel

Serialized fields of an app here whereas App contains non-serialized fields.


feedback_definitions class-attribute instance-attribute

feedback_definitions: Sequence[FeedbackDefinition] = []

Feedback functions to evaluate on each record.

feedback_mode class-attribute instance-attribute

feedback_mode: FeedbackMode = WITH_APP_THREAD

How to evaluate feedback functions upon producing a record.

root_class instance-attribute

root_class: Class

Class of the main instrumented object.

Ideally this would be a ClassVar but since we want to check this without instantiating the subclass of AppDefinition that would define it, we cannot use ClassVar.

root_callable class-attribute

root_callable: FunctionOrMethod

App's main method.

This is to be filled in by subclass.

app instance-attribute

Wrapped app in jsonized form.

initial_app_loader_dump class-attribute instance-attribute

initial_app_loader_dump: Optional[SerialBytes] = None

Serialization of a function that loads an app.

Dump is of the initial app state before any invocations. This can be used to create a new session.


Experimental work in progress.

app_extra_json instance-attribute

app_extra_json: JSON

Info to store about the app and to display in dashboard.

This can be used even if app itself cannot be serialized. app_extra_json, then, can stand in place for whatever data the user might want to keep track of about the app.

app_id instance-attribute

app_id: AppID = app_id

Unique identifier for this app.

tags instance-attribute

tags: Tags = tags

Tags for the app.

metadata instance-attribute

metadata: Metadata = metadata

Metadata for the app.


continue_session staticmethod

continue_session(app_definition_json: JSON, app: Any) -> AppDefinition

Instantiate the given app with the given state app_definition_json.


This is an experimental feature with ongoing work.


The json serialized app.



The app to continue the session with.



A new AppDefinition instance with the given app and the given app_definition_json state.

new_session staticmethod

new_session(app_definition_json: JSON, initial_app_loader: Optional[Callable] = None) -> AppDefinition

Create an app instance at the start of a session.


This is an experimental feature with ongoing work.

Create a copy of the json serialized app with the enclosed app being initialized to its initial state before any records are produced (i.e. blank memory).

get_loadable_apps staticmethod


Gets a list of all of the loadable apps.


This is an experimental feature with ongoing work.

This is those that have initial_app_loader_dump set.

select_inputs classmethod

select_inputs() -> Lens

Get the path to the main app's call inputs.

select_outputs classmethod

select_outputs() -> Lens

Get the path to the main app's call outputs.

Bases: AppDefinition, WithInstrumentCallbacks, Hashable

Base app recorder type.

Non-serialized fields here while the serialized ones are defined in AppDefinition.

This class is abstract. Use one of these concrete subclasses as appropriate: - TruLlama for LlamaIndex apps. - TruChain for LangChain apps. - TruRails for NeMo Guardrails apps. - TruVirtual for recording information about invocations of apps without access to those apps. - TruCustomApp for custom apps. These need to be decorated to have appropriate data recorded. - TruBasicApp for apps defined solely by a string-to-string method.


feedbacks class-attribute instance-attribute

feedbacks: List[Feedback] = Field(exclude=True, default_factory=list)

Feedback functions to evaluate on each record.

tru class-attribute instance-attribute

tru: Optional[Tru] = Field(default=None, exclude=True)

Workspace manager.

If this is not povided, a singleton Tru will be made (if not already) and used.

db class-attribute instance-attribute

db: Optional[DB] = Field(default=None, exclude=True)

Database interface.

If this is not provided, a singleton SQLAlchemyDB will be made (if not already) and used.

instrument class-attribute instance-attribute

instrument: Optional[Instrument] = Field(None, exclude=True)

Instrumentation class.

This is needed for serialization as it tells us which objects we want to be included in the json representation of this app.

recording_contexts class-attribute instance-attribute

recording_contexts: ContextVar[RecordingContext] = Field(None, exclude=True)

Sequnces of records produced by the this class used as a context manager are stored in a RecordingContext.

Using a context var so that context managers can be nested.

instrumented_methods class-attribute instance-attribute

instrumented_methods: Dict[int, Dict[Callable, Lens]] = Field(exclude=True, default_factory=dict)

Mapping of instrumented methods (by id(.) of owner object and the function) to their path in this app.

records_with_pending_feedback_results class-attribute instance-attribute

records_with_pending_feedback_results: Queue[Record] = Field(exclude=True, default_factory=lambda: Queue(maxsize=1024))

Records produced by this app which might have yet to finish feedback runs.

manage_pending_feedback_results_thread class-attribute instance-attribute

manage_pending_feedback_results_thread: Optional[Thread] = Field(exclude=True, default=None)

Thread for manager of pending feedback results queue.

See _manage_pending_feedback_results.

selector_check_warning class-attribute instance-attribute

selector_check_warning: bool = False

Issue warnings when selectors are not found in the app with a placeholder record.

If False, constructor will raise an error instead.

selector_nocheck class-attribute instance-attribute

selector_nocheck: bool = False

Ignore selector checks entirely.

This may be necessary if the expected record content cannot be determined before it is produced.

app class-attribute instance-attribute

app: Any = app

The app to be recorded.



wait_for_feedback_results() -> None

Wait for all feedbacks functions to complete.

This applies to all feedbacks on all records produced by this app. This call will block until finished and if new records are produced while this is running, it will include them.

select_context classmethod

select_context(app: Optional[Any] = None) -> Lens

Try to find retriever components in the given app and return a lens to access the retrieved contexts that would appear in a record were these components to execute.


main_call(human: str) -> str

If available, a single text to a single text invocation of this app.

main_acall async

main_acall(human: str) -> str

If available, a single text to a single text invocation of this app.


main_input(func: Callable, sig: Signature, bindings: BoundArguments) -> JSON

Determine the main input string for the given function func with signature sig if it is to be called with the given bindings bindings.


main_output(func: Callable, sig: Signature, bindings: BoundArguments, ret: Any) -> JSON

Determine the main out string for the given function func with signature sig after it is called with the given bindings and has returned ret.


on_method_instrumented(obj: object, func: Callable, path: Lens)

Called by instrumentation system for every function requested to be instrumented by this app.


get_methods_for_func(func: Callable) -> Iterable[Tuple[int, Callable, Lens]]

Get the methods (rather the inner functions) matching the given func and the path of each.

See WithInstrumentCallbacks.get_methods_for_func.


get_method_path(obj: object, func: Callable) -> Lens

Get the path of the instrumented function method relative to this app.


json(*args, **kwargs)

Create a json string representation of this app.


on_new_record(func) -> Iterable[RecordingContext]

Called at the start of record creation.

See WithInstrumentCallbacks.on_new_record.


on_add_record(ctx: RecordingContext, func: Callable, sig: Signature, bindings: BoundArguments, ret: Any, error: Any, perf: Perf, cost: Cost, existing_record: Optional[Record] = None) -> Record

Called by instrumented methods if they use _new_record to construct a record call list.

See WithInstrumentCallbacks.on_add_record.

awith_ async

awith_(func: CallableMaybeAwaitable[A, T], *args, **kwargs) -> T

Call the given async func with the given *args and **kwargs while recording, producing func results. The record of the computation is available through other means like the database or dashboard. If you need a record of this execution immediately, you can use awith_record or the App as a context mananger instead.

with_ async

with_(func: Callable[[A], T], *args, **kwargs) -> T

Call the given async func with the given *args and **kwargs while recording, producing func results. The record of the computation is available through other means like the database or dashboard. If you need a record of this execution immediately, you can use awith_record or the App as a context mananger instead.


with_record(func: Callable[[A], T], *args, record_metadata: JSON = None, **kwargs) -> Tuple[T, Record]

Call the given func with the given *args and **kwargs, producing its results as well as a record of the execution.

awith_record async

awith_record(func: Callable[[A], Awaitable[T]], *args, record_metadata: JSON = None, **kwargs) -> Tuple[T, Record]

Call the given func with the given *args and **kwargs, producing its results as well as a record of the execution.


dummy_record(cost: Cost = mod_schema.Cost(), perf: Perf =, ts: datetime =, main_input: str = 'main_input are strings.', main_output: str = 'main_output are strings.', main_error: str = 'main_error are strings.', meta: Dict = {'metakey': 'meta are dicts'}, tags: str = 'tags are strings') -> Record

Create a dummy record with some of the expected structure without actually invoking the app.

The record is a guess of what an actual record might look like but will be missing information that can only be determined after a call is made.

All args are Record fields except these:

- `record_id` is generated using the default id naming schema.
- `app_id` is taken from this recorder.
- `calls` field is constructed based on instrumented methods.


instrumented() -> Iterable[Tuple[Lens, ComponentView]]

Iteration over instrumented components and their categories.


print_instrumented() -> None

Print the instrumented components and methods.


format_instrumented_methods() -> str

Build a string containing a listing of instrumented methods.


print_instrumented_methods() -> None

Print instrumented methods.


print_instrumented_components() -> None

Print instrumented components and their categories.

Manager of the creation of records from record calls.

An instance of this class is produced when using an App as a context mananger, i.e.:

app = ...  # your app
truapp: TruChain = TruChain(app, ...) # recorder for LangChain apps

with truapp as recorder:
    app.invoke(...) # use your app

recorder: RecordingContext

Each instance of this class produces a record for every "root" instrumented method called. Root method here means the first instrumented method in a call stack. Note that there may be more than one of these contexts in play at the same time due to:

  • More than one wrapper of the same app.
  • More than one context manager ("with" statement) surrounding calls to the same app.
  • Calls to "with_record" on methods that themselves contain recording.
  • Calls to apps that use trulens internally to track records in any of the supported ways.
  • Combinations of the above.


calls instance-attribute

calls: List[RecordAppCall] = []

A record (in terms of its RecordAppCall) in process of being created.

records instance-attribute

records: List[Record] = []

Completed records.

lock instance-attribute

lock: Lock = Lock()

Lock blocking access to calls and records when adding calls or finishing a record.

token instance-attribute

token: Optional[Token] = None

Token for context management.

app instance-attribute

App for which we are recording.

record_metadata instance-attribute

record_metadata = record_metadata

Metadata to attach to all records produced in this context.



get() -> Record

Get the single record only if there was exactly one. Otherwise throw an error.


add_call(call: RecordAppCall)

Add the given call to the currently tracked call list.


finish_record(calls_to_record: Callable[[List[RecordAppCall], JSON], Record], existing_record: Optional[Record] = None)

Run the given function to build a record from the tracked calls and any pre-specified metadata.