π¦ Tru Llama¶
Bases: App
Recorder for LlamaIndex applications.
This recorder is designed for LlamaIndex apps, providing a way to instrument, log, and evaluate their behavior.
Creating a LlamaIndex application
Consider an example LlamaIndex application. For the complete code example, see LlamaIndex Quickstart.
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
documents = SimpleDirectoryReader("data").load_data()
index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
Feedback functions can utilize the specific context produced by the
application's retriever. This is achieved using the select_context method,
which then can be used by a feedback selector, such as on(context).
Defining a feedback function
from trulens_eval.feedback.provider import OpenAI
from trulens_eval import Feedback
import numpy as np
# Select context to be used in feedback.
from trulens_eval.app import App
context = App.select_context(rag_chain)
# Use feedback
f_context_relevance = (
Feedback(provider.context_relevance_with_context_reasons)
.on_input()
.on(context) # Refers to context defined from `select_context`
.aggregate(np.mean)
)
The application can be wrapped in a TruLlama recorder to provide logging
and evaluation upon the application's use.
Using the TruLlama recorder
from trulens_eval import TruLlama
# f_lang_match, f_qa_relevance, f_qs_relevance are feedback functions
tru_recorder = TruLlama(query_engine,
app_id='LlamaIndex_App1',
feedbacks=[f_lang_match, f_qa_relevance, f_qs_relevance])
with tru_recorder as recording:
query_engine.query("What is llama index?")
Feedback functions can utilize the specific context produced by the
application's query engine. This is achieved using the select_context
method, which then can be used by a feedback selector, such as
on(context).
Further information about LlamaIndex apps can be found on the π¦ LlamaIndex Documentation page.
| PARAMETER | DESCRIPTION |
|---|---|
app |
A LlamaIndex application.
TYPE:
|
**kwargs |
Additional arguments to pass to App and AppDefinition.
TYPE:
|
Attributes¶
class-attribute
instance-attribute
¶
feedback_definitions: Sequence[FeedbackDefinition] = []
Feedback functions to evaluate on each record.
class-attribute
instance-attribute
¶
feedback_mode: FeedbackMode = WITH_APP_THREAD
How to evaluate feedback functions upon producing a record.
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.
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.
Warning
Experimental work in progress.
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.
class-attribute
instance-attribute
¶
Feedback functions to evaluate on each record.
class-attribute
instance-attribute
¶
Workspace manager.
If this is not povided, a singleton Tru will be made (if not already) and used.
class-attribute
instance-attribute
¶
Database interface.
If this is not provided, a singleton SQLAlchemyDB will be made (if not already) and used.
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.
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.
class-attribute
instance-attribute
¶
Mapping of instrumented methods (by id(.) of owner object and the function) to their path in this app.
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.
class-attribute
instance-attribute
¶
Thread for manager of pending feedback results queue.
See _manage_pending_feedback_results.
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.
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.
Functions¶
Called by instrumentation system for every function requested to be instrumented by this app.
Get the path of the instrumented function method relative to this app.
Get the methods (rather the inner functions) matching the given func
and the path of each.
on_new_record(func) -> Iterable[RecordingContext]
Called at the start of record creation.
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.
staticmethod
¶
load(obj, *args, **kwargs)
Deserialize/load this object using the class information in tru_class_info to lookup the actual class that will do the deserialization.
classmethod
¶
model_validate(*args, **kwargs) -> Any
Deserialized a jsonized version of the app into the instance of the class it was serialized from.
Note
This process uses extra information stored in the jsonized object and handled by WithClassInfo.
staticmethod
¶
continue_session(app_definition_json: JSON, app: Any) -> AppDefinition
Instantiate the given app with the given state
app_definition_json.
Warning
This is an experimental feature with ongoing work.
| PARAMETER | DESCRIPTION |
|---|---|
app_definition_json |
The json serialized app.
TYPE:
|
app |
The app to continue the session with.
TYPE:
|
| RETURNS | DESCRIPTION |
|---|---|
AppDefinition
|
A new |
staticmethod
¶
new_session(app_definition_json: JSON, initial_app_loader: Optional[Callable] = None) -> AppDefinition
Create an app instance at the start of a session.
Warning
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).
staticmethod
¶
get_loadable_apps()
Gets a list of all of the loadable apps.
Warning
This is an experimental feature with ongoing work.
This is those that have initial_app_loader_dump set.
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.
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.
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.
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_base_schema.Cost(), perf: Perf = mod_base_schema.Perf.now(), ts: datetime = datetime.datetime.now(), 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.
Iteration over instrumented components and their categories.
format_instrumented_methods() -> str
Build a string containing a listing of instrumented methods.
print_instrumented_components() -> None
Print instrumented components and their categories.
classmethod
¶
select_source_nodes() -> Lens
Get the path to the source nodes in the query output.
classmethod
¶
Get the path to the context in the query output.
main_input(func: Callable, sig: Signature, bindings: BoundArguments) -> str
Determine the main input string for the given function func with
signature sig if it is to be called with the given bindings
bindings.