Results
results
Result
dataclass
Result(responses, total_requests=None, clients=1, n_requests=None, total_test_time=None, model_id=None, output_path=None, endpoint_name=None, provider=None, run_name=None, run_description=None, start_time=None, first_request_time=None, last_request_time=None, end_time=None)
Results of a test run.
stats
property
stats
Run metrics and aggregated statistics over the individual requests.
Returns a flat dictionary combining:
- Basic run information (from
to_dict()). - Aggregated statistics (
average,p50,p90,p99) fortime_to_last_token,time_to_first_token,num_tokens_output, andnum_tokens_input. Keys use the format"{metric}-{aggregation}". - Run-level throughput metrics (
requests_per_minute,total_input_tokens, etc.). - Any additional stats contributed by callbacks via
:meth:
_update_contributed_stats.
During a live run, stats are computed incrementally by
:class:~llmeter.utils.RunningStats and stored in _preloaded_stats.
When loading from disk with load_responses=False, pre-computed stats
from stats.json are used. As a fallback (e.g. manually constructed
Result), stats are computed on the fly from self.responses.
Returns:
| Type | Description |
|---|---|
dict
|
A new shallow copy of the stats dictionary on each access. |
Example::
result = await runner.run(payload=my_payload, clients=5)
result.stats["time_to_first_token-p50"] # 0.312
result.stats["requests_per_minute"] # 141.2
result.stats["failed_requests"] # 0
__post_init__
__post_init__()
Initialize the Result instance.
Source code in llmeter/results.py
55 56 57 58 59 | |
get_dimension
get_dimension(dimension, filter_dimension=None, filter_value=None)
Get the values of a specific dimension from the responses.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
dimension
|
str
|
The name of the dimension to retrieve. |
required |
filter_dimension
|
str
|
Name of dimension to filter on. Defaults to None. |
None
|
filter_value
|
any
|
Value to match for the filter dimension. Defaults to None. |
None
|
Returns:
| Name | Type | Description |
|---|---|---|
list |
list
|
A list of values for the specified dimension across all responses. |
Raises:
| Type | Description |
|---|---|
ValueError
|
If the specified dimension is not found in any response. |
Source code in llmeter/results.py
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 | |
load
classmethod
load(result_path, load_responses=True)
Load run results from disk or cloud storage.
Reads previously saved run results from the specified path. Handles
both complete runs (with summary.json) and interrupted runs where
only responses.jsonl, run_config.json, or stats.json are
available.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
result_path
|
UPath | str
|
The path to the directory containing the result files. Can be a string or a UPath object. |
required |
load_responses
|
bool
|
Whether to load individual invocation responses
from 'responses.jsonl'. Defaults to True. When False, only the
summary and pre-computed stats are loaded, which is significantly
faster for large result sets. Use |
True
|
Returns:
| Name | Type | Description |
|---|---|---|
Result |
Result
|
An instance of the Result class containing the loaded |
Result
|
responses and summary data. |
Raises:
| Type | Description |
|---|---|
FileNotFoundError
|
If the directory does not exist or contains no
recognizable result files ( |
JSONDecodeError
|
If |
Source code in llmeter/results.py
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | |
load_responses
load_responses()
Load individual invocation responses from disk or cloud storage.
Reads the 'responses.jsonl' file from the result's output_path directory.
This is useful when the Result was loaded with load_responses=False and
you need to access the individual responses on demand.
Returns:
| Type | Description |
|---|---|
list[InvocationResponse]
|
list[InvocationResponse]: The loaded responses. Also updates |
list[InvocationResponse]
|
in place. |
Raises:
| Type | Description |
|---|---|
ValueError
|
If no output_path is set on this Result. |
FileNotFoundError
|
If 'responses.jsonl' is not found at the output_path. |
Source code in llmeter/results.py
184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | |
save
save(output_path=None)
Save the results to disk or cloud storage.
Saves the run results to the specified output path or the instance's default output path. It creates three files: 1. 'summary.json': Contains the overall summary of the results. 2. 'stats.json': Contains detailed statistics of the run. 3. 'responses.jsonl': Contains individual invocation responses - Only if the responses are not already saved at the indicated path.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
output_path
|
UPath | str | None
|
The path where the result files will be saved. If None, the instance's default output_path will be used. Defaults to None. |
None
|
Raises:
| Type | Description |
|---|---|
ValueError
|
If no output path is provided and the instance doesn't have a default output_path set. |
TypeError
|
If the provided output_path is not a valid type. |
IOError
|
If there's an error writing to the output files. |
Note
The method uses the Universal Path (UPath) library for file operations, which provides a unified interface for working with different file systems.
Source code in llmeter/results.py
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | |
to_dict
to_dict(include_responses=False)
Return a dictionary representation of this result.
Returns a plain dict produced by :func:dataclasses.asdict,
preserving native Python types (datetime, UPath, etc.).
This is suitable for programmatic access and internal data
processing.
For JSON output, use :meth:to_json which delegates to
:func:~llmeter.json_utils.llmeter_default_serializer for
non-serializable types, or pass the dict through
json.dumps(result.to_dict(), default=llmeter_default_serializer).
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
include_responses
|
bool
|
If |
False
|
Returns:
| Name | Type | Description |
|---|---|---|
dict |
dict
|
A dictionary of result fields with native Python types. |
Source code in llmeter/results.py
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 | |
to_json
to_json(default=llmeter_default_serializer, **kwargs)
Return the results as a JSON string.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
default
|
Fallback serializer. Defaults to
:func: |
llmeter_default_serializer
|
|
**kwargs
|
Extra keyword arguments passed to :func: |
{}
|
Source code in llmeter/results.py
145 146 147 148 149 150 151 152 153 154 155 156 | |