_get_standardized_inputs() — langchain Function Reference
Architecture documentation for the _get_standardized_inputs() function in log_stream.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD 999c00c5_f6b7_32ae_2290_ef3266811aab["_get_standardized_inputs()"] bd3b753a_7a64_0c77_8d7a_afcce4658003["log_stream.py"] 999c00c5_f6b7_32ae_2290_ef3266811aab -->|defined in| bd3b753a_7a64_0c77_8d7a_afcce4658003 79906bae_a315_8c6a_0f74_2bca8c58615c["_on_run_create()"] 79906bae_a315_8c6a_0f74_2bca8c58615c -->|calls| 999c00c5_f6b7_32ae_2290_ef3266811aab dd086141_42ce_3053_f911_051099488c1c["_on_run_update()"] dd086141_42ce_3053_f911_051099488c1c -->|calls| 999c00c5_f6b7_32ae_2290_ef3266811aab style 999c00c5_f6b7_32ae_2290_ef3266811aab fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/core/langchain_core/tracers/log_stream.py lines 564–602
def _get_standardized_inputs(
run: Run, schema_format: Literal["original", "streaming_events"]
) -> Any:
"""Extract standardized inputs from a `Run`.
Standardizes the inputs based on the type of the runnable used.
Args:
run: `Run` object
schema_format: The schema format to use.
Returns:
Valid inputs are only dict. By conventions, inputs always represented invocation
using named arguments. `None` means that the input is not yet known!
"""
if schema_format == "original":
msg = (
"Do not assign inputs with original schema drop the key for now."
"When inputs are added to astream_log they should be added with "
"standardized schema for streaming events."
)
raise NotImplementedError(msg)
inputs = load(run.inputs, allowed_objects="all")
if run.run_type in {"retriever", "llm", "chat_model"}:
return inputs
# new style chains
# These nest an additional 'input' key inside the 'inputs' to make sure
# the input is always a dict. We need to unpack and use the inner value.
inputs = inputs["input"]
# We should try to fix this in Runnables and callbacks/tracers
# Runnables should be using a None type here not a placeholder
# dict.
if inputs == {"input": ""}: # Workaround for Runnables not using None
# The input is not known, so we don't assign data['input']
return None
return inputs
Domain
Subdomains
Called By
Source
Frequently Asked Questions
What does _get_standardized_inputs() do?
_get_standardized_inputs() is a function in the langchain codebase, defined in libs/core/langchain_core/tracers/log_stream.py.
Where is _get_standardized_inputs() defined?
_get_standardized_inputs() is defined in libs/core/langchain_core/tracers/log_stream.py at line 564.
What calls _get_standardized_inputs()?
_get_standardized_inputs() is called by 2 function(s): _on_run_create, _on_run_update.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free