List experiments
List out all experiments. The experiments are sorted by creation date, with the most recently-created experiments coming first
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Query Parameters
limit
integer | null
Limit the number of objects to return
Minimum:0
starting_after
string
Pagination cursor id.
For example, if the final item in the last page you fetched had an id of foo
, pass starting_after=foo
to fetch the next page. Note: you may only pass one of starting_after
and ending_before
"uuid"
ending_before
string
Pagination cursor id.
For example, if the initial item in the last page you fetched had an id of foo
, pass ending_before=foo
to fetch the previous page. Note: you may only pass one of starting_after
and ending_before
"uuid"
ids
Any properties in string, array<string>
Filter search results to a particular set of object IDs. To specify a list of IDs, include the query param multiple times
experiment_name
string
Name of the experiment to search for
project_name
string
Name of the project to search for
project_id
string
Project id
Format:"uuid"
org_name
string
Filter search results to within a particular organization
Status code | Description |
---|---|
200 | Returns a list of experiment objects |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
Create experiment
Create a new experiment. If there is an existing experiment in the project with the same name as the one specified in the request, will return the existing experiment unmodified
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Request Body (Optional)
Any desired information about the new experiment object
project_id
Requiredstring
Unique identifier for the project that the experiment belongs under
Format:"uuid"
name
string | null
Name of the experiment. Within a project, experiment names are unique
Minimum length:1
description
string | null
Textual description of the experiment
repo_info
object | null
Metadata about the state of the repo when the experiment was created
base_exp_id
string | null
Id of default base experiment to compare against when viewing this experiment
Format:"uuid"
dataset_id
string | null
Identifier of the linked dataset, or null if the experiment is not linked to a dataset
Format:"uuid"
dataset_version
string | null
Version number of the linked dataset the experiment was run against. This can be used to reproduce the experiment after the dataset has been modified.
public
boolean | null
Whether or not the experiment is public. Public experiments can be viewed by anybody inside or outside the organization
metadata
object | null
User-controlled metadata about the experiment
ensure_new
boolean | null
Normally, creating an experiment with the same name as an existing experiment will return the existing one un-modified. But if ensure_new
is true, registration will generate a new experiment with a unique name in case of a conflict.
Status code | Description |
---|---|
200 | Returns the new experiment object |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
Get experiment
Get an experiment object by its id
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns the experiment object |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
Partially update experiment
Partially update an experiment object. Specify the fields to update in the payload. Any object-type fields will be deep-merged with existing content. Currently we do not support removing fields or setting them to null.
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Request Body (Optional)
Fields to update
name
string | null
Name of the experiment. Within a project, experiment names are unique
description
string | null
Textual description of the experiment
repo_info
object | null
Metadata about the state of the repo when the experiment was created
base_exp_id
string | null
Id of default base experiment to compare against when viewing this experiment
Format:"uuid"
dataset_id
string | null
Identifier of the linked dataset, or null if the experiment is not linked to a dataset
Format:"uuid"
dataset_version
string | null
Version number of the linked dataset the experiment was run against. This can be used to reproduce the experiment after the dataset has been modified.
public
boolean | null
Whether or not the experiment is public. Public experiments can be viewed by anybody inside or outside the organization
metadata
object | null
User-controlled metadata about the experiment
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns the experiment object |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
Delete experiment
Delete an experiment object by its id
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns the deleted experiment object |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
/insertInsert experiment events
Insert a set of events into the experiment
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Request Body (Optional)
An array of experiment events to insert
events
Requiredarray<Any properties in object, object>
A list of experiment events to insert
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns the inserted row ids |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
/fetchFetch experiment (GET form)
Fetch the events in an experiment. Equivalent to the POST form of the same path, but with the parameters in the URL query rather than in the request body
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Query Parameters
limit
integer | null
limit the number of traces fetched
Fetch queries may be paginated if the total result size is expected to be large (e.g. project_logs which accumulate over a long time). Note that fetch queries only support pagination in descending time order (from latest to earliest _xact_id
. Furthermore, later pages may return rows which showed up in earlier pages, except with an earlier _xact_id
. This happens because pagination occurs over the whole version history of the event log. You will most likely want to exclude any such duplicate, outdated rows (by id
) from your combined result set.
The limit
parameter controls the number of full traces to return. So you may end up with more individual rows than the specified limit if you are fetching events containing traces.
0
max_xact_id
string
DEPRECATION NOTICE: The manually-constructed pagination cursor is deprecated in favor of the explicit 'cursor' returned by object fetch requests. Please prefer the 'cursor' argument going forwards.
Together, max_xact_id
and max_root_span_id
form a pagination cursor
Since a paginated fetch query returns results in order from latest to earliest, the cursor for the next page can be found as the row with the minimum (earliest) value of the tuple (_xact_id, root_span_id)
. See the documentation of limit
for an overview of paginating fetch queries.
max_root_span_id
string
DEPRECATION NOTICE: The manually-constructed pagination cursor is deprecated in favor of the explicit 'cursor' returned by object fetch requests. Please prefer the 'cursor' argument going forwards.
Together, max_xact_id
and max_root_span_id
form a pagination cursor
Since a paginated fetch query returns results in order from latest to earliest, the cursor for the next page can be found as the row with the minimum (earliest) value of the tuple (_xact_id, root_span_id)
. See the documentation of limit
for an overview of paginating fetch queries.
version
string
Retrieve a snapshot of events from a past time
The version id is essentially a filter on the latest event transaction id. You can use the max_xact_id
returned by a past fetch as the version to reproduce that exact fetch.
Status code | Description |
---|---|
200 | Returns the fetched rows |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
/fetchFetch experiment (POST form)
Fetch the events in an experiment. Equivalent to the GET form of the same path, but with the parameters in the request body rather than in the URL query
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Request Body (Optional)
Filters for the fetch query
limit
integer | null
limit the number of traces fetched
Fetch queries may be paginated if the total result size is expected to be large (e.g. project_logs which accumulate over a long time). Note that fetch queries only support pagination in descending time order (from latest to earliest _xact_id
. Furthermore, later pages may return rows which showed up in earlier pages, except with an earlier _xact_id
. This happens because pagination occurs over the whole version history of the event log. You will most likely want to exclude any such duplicate, outdated rows (by id
) from your combined result set.
The limit
parameter controls the number of full traces to return. So you may end up with more individual rows than the specified limit if you are fetching events containing traces.
0
cursor
string | null
An opaque string to be used as a cursor for the next page of results, in order from latest to earliest.
The string can be obtained directly from the cursor
property of the previous fetch query
max_xact_id
string & null
max_root_span_id
string & null
filters
array<object> | null
NOTE: This parameter is deprecated and will be removed in a future revision. Consider using the /btql
endpoint (https://www.braintrust.dev/docs/reference/btql) for more advanced filtering.
A list of filters on the events to fetch. Currently, only path-lookup type filters are supported.
version
string & null
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns the fetched rows |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
/feedbackFeedback for experiment events
Log feedback for a set of experiment events
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Request Body (Optional)
An array of feedback objects
feedback
Requiredarray<object>
A list of experiment feedback items
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Status code | Description |
---|---|
200 | Returns a success status |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
{experiment_id}
/summarizeSummarize experiment
Summarize experiment
Authorization
Authorization
RequiredBearer <token>
Most Braintrust endpoints are authenticated by providing your API key as a header Authorization: Bearer [api_key]
to your HTTP request. You can create an API key in the Braintrust organization settings page.
In: header
Path Parameters
experiment_id
Requiredstring
Experiment id
Format:"uuid"
Query Parameters
summarize_scores
boolean | null
Whether to summarize the scores and metrics. If false (or omitted), only the metadata will be returned.
comparison_experiment_id
string
The experiment to compare against, if summarizing scores and metrics. If omitted, will fall back to the base_exp_id
stored in the experiment metadata, and then to the most recent experiment run in the same project. Must pass summarize_scores=true
for this id to be used
"uuid"
Status code | Description |
---|---|
200 | Experiment summary |
400 | The request was unacceptable, often due to missing a required parameter |
401 | No valid API key provided |
403 | The API key doesn’t have permissions to perform the request |
429 | Too many requests hit the API too quickly. We recommend an exponential backoff of your requests |
500 | Something went wrong on Braintrust's end. (These are rare.) |
Summary of an experiment