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