/
GE
getplumai
/
Plum API
Search skmtc…
⌘K
Docs
Sign in
Sign in
APIs
Generators
Stacks
Projects
Docs
History
Schema
Checked 44m ago · Updated 2mo ago
Details
Filter operations
get
List all seed datasets
get
Retrieve a specific seed dataset by ID
post
Insert or overwrite seed data by ID
post
Add a single pair to a dataset (creates new dataset if the system_prompt_template that's provided doesn't correspond to an existing dataset)
post
Add a single pair to an existing seed dataset by ID
post
Upload a new seed dataset
get
List all synthetic datasets
get
Retrieve synthetic data by ID
put
Insert or overwrite synthetic data by ID
post
Upload new synthetic data
get
Retrieve synthetic data formatted for OpenAI by ID
get
Get a specific metric definition by ID
get
Get a specific evaluation result by ID
put
Update evaluation result with human feedback
post
Generate evaluation metrics
get
List all available evaluation metrics
get
List all available evaluation results
post
Create custom metric definitions
post
Evaluate datasets with specified metrics
post
Augment seed data to generate synthetic data
get
Gather high-scoring and positively critiqued pairs from evaluation results
get
Gather high-scoring and positively critiqued pairs formatted for OpenAI fine-tuning
post
Compare multiple prompts against a dataset
post
Generate an improved prompt based on comparison results
Get a specific evaluation result by ID
get
/evaluation/{id}
Path parameters
id
string
required
Response
Successfully retrieved evaluation result
object
required
results_id
string
created_at
string
dataset_id
string
metrics_id
string
metrics_definitions
string[]
pair_count
integer
system_prompt
string
score_means
number[]
score_medians
number[]
score_mins
number[]
score_maxes
number[]
score_std_devs
number[]
score_confidence_intervals
object[]
min_scoring_pairs
array[]
human_critique
object[]
Changes