1---
2id: post-eval
3title: "Run Eval"
4description: "Evaluate a model against a eval spice specification"
5sidebar_label: "Run Eval"
6hide_title: true
7hide_table_of_contents: true
8api: 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
9sidebar_class_name: "post api-method"
10info_path: docs/api/HTTP/runtime
11custom_edit_url: null
12proxy: http://localhost:8090
13---
14
15import MethodEndpoint from "@theme/ApiExplorer/MethodEndpoint";
16import ParamsDetails from "@theme/ParamsDetails";
17import RequestSchema from "@theme/RequestSchema";
18import StatusCodes from "@theme/StatusCodes";
19import OperationTabs from "@theme/OperationTabs";
20import TabItem from "@theme/TabItem";
21import Heading from "@theme/Heading";
22
23<Heading
24 as={"h1"}
25 className={"openapi__heading"}
26 children={"Run Eval"}
27>
28</Heading>
29
30<MethodEndpoint
31 method={"post"}
32 path={"/v1/evals/{name}"}
33 context={"endpoint"}
34>
35
36</MethodEndpoint>
37
38
39
40Evaluate a model against a eval spice specification
41
42<Heading
43 id={"request"}
44 as={"h2"}
45 className={"openapi-tabs__heading"}
46 children={"Request"}
47>
48</Heading>
49
50<ParamsDetails
51 parameters={[{"name":"name","in":"path","description":"Name of the evaluation to run","required":true,"schema":{"type":"string"}}]}
52>
53
54</ParamsDetails>
55
56<RequestSchema
57 title={"Body"}
58 body={{"description":"Parameters to run the evaluation","content":{"application/json":{"schema":{"type":"object","description":"Input parameters to start an evaluation run for a given model.","required":["model"],"properties":{"model":{"type":"string"}},"title":"RunEval"},"example":{"model":"example_model"}}},"required":true}}
59>
60
61</RequestSchema>
62
63<StatusCodes
64 id={undefined}
65 label={undefined}
66 responses={{"200":{"description":"Evaluation run successfully","content":{"application/json":{"schema":{"type":"object","description":"Represents the response for an evaluation run","required":["primary_key","time_column","dataset","model","status","scorers","metrics"],"properties":{"dataset":{"type":"string","description":"The name of the dataset used for the evaluation"},"error_message":{"type":["string","null"],"description":"The error message if the evaluation failed, otherwise `None`"},"metrics":{"type":"object","description":"A map of metric names to their corresponding values","additionalProperties":{"type":"number","format":"double"},"propertyNames":{"type":"string"}},"model":{"type":"string","description":"The model used for the evaluation"},"primary_key":{"type":"string","description":"Unique identifier for the evaluation run"},"scorers":{"type":"array","items":{"type":"string"},"description":"List of scorers used in the evaluation"},"status":{"type":"string","description":"The status of the evaluation (e.g., \"completed\", \"failed\", etc.)"},"time_column":{"type":"string","description":"Timestamp indicating when the evaluation was created or run"}},"title":"EvalRunResponse"},"example":{"primary_key":"eval_12345","time_column":"2024-12-19T12:34:56Z","dataset":"my_dataset","model":"example_model","status":"completed","error_message":null,"scorers":["scorer1","scorer2"],"metrics":{"scorer1/accuracy":0.95,"scorer2/accuracy":0.93}}},"text/csv":{"example":"primary_key,time_column,dataset,model,status,error_message,scorers,metrics\neval_12345,2024-12-19T12:34:56Z,my_dataset,example_model,completed,,\"[\"\"scorer1\"\", \"\"scorer2\"\"]\",\"{\"\"scorer1/accuracy\"\":0.95, \"\"scorer2/accuracy\"\":0.93}\""},"text/plain":{"example":"+-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+\n | primary_key | time_column | dataset | model | status | error_message | scorers | metrics |\n +-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+\n | eval_12345 | 2024-12-19T12:34:56Z| my_dataset| example_model | completed | | scorer1, scorer2 | {\"accuracy\": 0.95, \"precision\": 0.93} |\n +-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+"}}}}}
67>
68
69</StatusCodes>
70
71
72
1---
2id: post-eval
3title: "Run Eval"
4description: "Evaluate a model against a eval spice specification"
5sidebar_label: "Run Eval"
6hide_title: true
7hide_table_of_contents: true
8api: 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
9sidebar_class_name: "post api-method"
10info_path: docs/api/HTTP/runtime
11custom_edit_url: null
12proxy: http://localhost:8090
13---
14
15import MethodEndpoint from "@theme/ApiExplorer/MethodEndpoint";
16import ParamsDetails from "@theme/ParamsDetails";
17import RequestSchema from "@theme/RequestSchema";
18import StatusCodes from "@theme/StatusCodes";
19import OperationTabs from "@theme/OperationTabs";
20import TabItem from "@theme/TabItem";
21import Heading from "@theme/Heading";
22
23<Heading
24 as={"h1"}
25 className={"openapi__heading"}
26 children={"Run Eval"}
27>
28</Heading>
29
30<MethodEndpoint
31 method={"post"}
32 path={"/v1/evals/{name}"}
33 context={"endpoint"}
34>
35
36</MethodEndpoint>
37
38
39
40Evaluate a model against a eval spice specification
41
42<Heading
43 id={"request"}
44 as={"h2"}
45 className={"openapi-tabs__heading"}
46 children={"Request"}
47>
48</Heading>
49
50<ParamsDetails
51 parameters={[{"name":"name","in":"path","description":"Name of the evaluation to run","required":true,"schema":{"type":"string"}}]}
52>
53
54</ParamsDetails>
55
56<RequestSchema
57 title={"Body"}
58 body={{"description":"Parameters to run the evaluation","content":{"application/json":{"schema":{"type":"object","description":"Input parameters to start an evaluation run for a given model.","required":["model"],"properties":{"model":{"type":"string"}},"title":"RunEval"},"example":{"model":"example_model"}}},"required":true}}
59>
60
61</RequestSchema>
62
63<StatusCodes
64 id={undefined}
65 label={undefined}
66 responses={{"200":{"description":"Evaluation run successfully","content":{"application/json":{"schema":{"type":"object","description":"Represents the response for an evaluation run","required":["primary_key","time_column","dataset","model","status","scorers","metrics"],"properties":{"dataset":{"type":"string","description":"The name of the dataset used for the evaluation"},"error_message":{"type":["string","null"],"description":"The error message if the evaluation failed, otherwise `None`"},"metrics":{"type":"object","description":"A map of metric names to their corresponding values","additionalProperties":{"type":"number","format":"double"},"propertyNames":{"type":"string"}},"model":{"type":"string","description":"The model used for the evaluation"},"primary_key":{"type":"string","description":"Unique identifier for the evaluation run"},"scorers":{"type":"array","items":{"type":"string"},"description":"List of scorers used in the evaluation"},"status":{"type":"string","description":"The status of the evaluation (e.g., \"completed\", \"failed\", etc.)"},"time_column":{"type":"string","description":"Timestamp indicating when the evaluation was created or run"}},"title":"EvalRunResponse"},"example":{"primary_key":"eval_12345","time_column":"2024-12-19T12:34:56Z","dataset":"my_dataset","model":"example_model","status":"completed","error_message":null,"scorers":["scorer1","scorer2"],"metrics":{"scorer1/accuracy":0.95,"scorer2/accuracy":0.93}}},"text/csv":{"example":"primary_key,time_column,dataset,model,status,error_message,scorers,metrics\neval_12345,2024-12-19T12:34:56Z,my_dataset,example_model,completed,,\"[\"\"scorer1\"\", \"\"scorer2\"\"]\",\"{\"\"scorer1/accuracy\"\":0.95, \"\"scorer2/accuracy\"\":0.93}\""},"text/plain":{"example":"+-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+\n | primary_key | time_column | dataset | model | status | error_message | scorers | metrics |\n +-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+\n | eval_12345 | 2024-12-19T12:34:56Z| my_dataset| example_model | completed | | scorer1, scorer2 | {\"accuracy\": 0.95, \"precision\": 0.93} |\n +-------------+---------------------+-----------+---------------+-----------+----------------+------------------+---------------------------------------+"}}}}}
67>
68
69</StatusCodes>
70
71
72