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