Skip to content

Add OpenAPI documentation for LLM Observability eval config CRUD endpoints #3928

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
api-clients-generation-pipeline wants to merge 1 commit into
base: v2
Choose a base branch
from
Open

Add OpenAPI documentation for LLM Observability eval config CRUD endpoints #3928

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
613 changes: 613 additions & 0 deletions .generator/schemas/v2/openapi.yaml
View file
Open in desktop

Large diffs are not rendered by default.

84 changes: 84 additions & 0 deletions features/v2/llm_observability.feature
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,6 +175,42 @@ Feature: LLM Observability
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: Create or update a custom evaluator configuration returns "Bad Request" response
Given operation "UpdateLLMObsCustomEvalConfig" enabled
And new "UpdateLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
And body with value {"data": {"attributes": {"category": "Custom", "eval_name": "my-custom-evaluator", "llm_judge_config": {"assessment_criteria": {"max_threshold": 1.0, "min_threshold": 0.7, "pass_values": ["pass", "yes"], "pass_when": true}, "inference_params": {"frequency_penalty": 0.0, "max_tokens": 1024, "presence_penalty": 0.0, "temperature": 0.7, "top_k": 50, "top_p": 1.0}, "last_used_library_prompt_template_name": "sentiment-analysis-v1", "modified_library_prompt_template": false, "output_schema": null, "parsing_type": "structured_output", "prompt_template": [{"content": "Rate the quality of the following response:", "contents": [{"type": "text", "value": {"text": "What is the sentiment of this review?", "tool_call": {"arguments": "{\"location\": \"San Francisco\"}", "id": "call_abc123", "name": "get_weather", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "sunny, 72F", "tool_id": "call_abc123", "type": "function"}}}], "role": "user"}]}, "llm_provider": {"bedrock": {"region": "us-east-1"}, "integration_account_id": "my-account-id", "integration_provider": "openai", "model_name": "gpt-4o", "vertex_ai": {"location": "us-central1", "project": "my-gcp-project"}}, "target": {"application_name": "my-llm-app", "enabled": true, "eval_scope": "span", "filter": "@service:my-service", "root_spans_only": true, "sampling_percentage": 50.0}}, "id": "my-custom-evaluator", "type": "evaluator_config"}}
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: Create or update a custom evaluator configuration returns "Not Found" response
Given operation "UpdateLLMObsCustomEvalConfig" enabled
And new "UpdateLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
And body with value {"data": {"attributes": {"category": "Custom", "eval_name": "my-custom-evaluator", "llm_judge_config": {"assessment_criteria": {"max_threshold": 1.0, "min_threshold": 0.7, "pass_values": ["pass", "yes"], "pass_when": true}, "inference_params": {"frequency_penalty": 0.0, "max_tokens": 1024, "presence_penalty": 0.0, "temperature": 0.7, "top_k": 50, "top_p": 1.0}, "last_used_library_prompt_template_name": "sentiment-analysis-v1", "modified_library_prompt_template": false, "output_schema": null, "parsing_type": "structured_output", "prompt_template": [{"content": "Rate the quality of the following response:", "contents": [{"type": "text", "value": {"text": "What is the sentiment of this review?", "tool_call": {"arguments": "{\"location\": \"San Francisco\"}", "id": "call_abc123", "name": "get_weather", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "sunny, 72F", "tool_id": "call_abc123", "type": "function"}}}], "role": "user"}]}, "llm_provider": {"bedrock": {"region": "us-east-1"}, "integration_account_id": "my-account-id", "integration_provider": "openai", "model_name": "gpt-4o", "vertex_ai": {"location": "us-central1", "project": "my-gcp-project"}}, "target": {"application_name": "my-llm-app", "enabled": true, "eval_scope": "span", "filter": "@service:my-service", "root_spans_only": true, "sampling_percentage": 50.0}}, "id": "my-custom-evaluator", "type": "evaluator_config"}}
When the request is sent
Then the response status is 404 Not Found

@generated @skip @team:DataDog/ml-observability
Scenario: Create or update a custom evaluator configuration returns "OK" response
Given operation "UpdateLLMObsCustomEvalConfig" enabled
And new "UpdateLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
And body with value {"data": {"attributes": {"category": "Custom", "eval_name": "my-custom-evaluator", "llm_judge_config": {"assessment_criteria": {"max_threshold": 1.0, "min_threshold": 0.7, "pass_values": ["pass", "yes"], "pass_when": true}, "inference_params": {"frequency_penalty": 0.0, "max_tokens": 1024, "presence_penalty": 0.0, "temperature": 0.7, "top_k": 50, "top_p": 1.0}, "last_used_library_prompt_template_name": "sentiment-analysis-v1", "modified_library_prompt_template": false, "output_schema": null, "parsing_type": "structured_output", "prompt_template": [{"content": "Rate the quality of the following response:", "contents": [{"type": "text", "value": {"text": "What is the sentiment of this review?", "tool_call": {"arguments": "{\"location\": \"San Francisco\"}", "id": "call_abc123", "name": "get_weather", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "sunny, 72F", "tool_id": "call_abc123", "type": "function"}}}], "role": "user"}]}, "llm_provider": {"bedrock": {"region": "us-east-1"}, "integration_account_id": "my-account-id", "integration_provider": "openai", "model_name": "gpt-4o", "vertex_ai": {"location": "us-central1", "project": "my-gcp-project"}}, "target": {"application_name": "my-llm-app", "enabled": true, "eval_scope": "span", "filter": "@service:my-service", "root_spans_only": true, "sampling_percentage": 50.0}}, "id": "my-custom-evaluator", "type": "evaluator_config"}}
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: Create or update a custom evaluator configuration returns "Unprocessable Entity" response
Given operation "UpdateLLMObsCustomEvalConfig" enabled
And new "UpdateLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
And body with value {"data": {"attributes": {"category": "Custom", "eval_name": "my-custom-evaluator", "llm_judge_config": {"assessment_criteria": {"max_threshold": 1.0, "min_threshold": 0.7, "pass_values": ["pass", "yes"], "pass_when": true}, "inference_params": {"frequency_penalty": 0.0, "max_tokens": 1024, "presence_penalty": 0.0, "temperature": 0.7, "top_k": 50, "top_p": 1.0}, "last_used_library_prompt_template_name": "sentiment-analysis-v1", "modified_library_prompt_template": false, "output_schema": null, "parsing_type": "structured_output", "prompt_template": [{"content": "Rate the quality of the following response:", "contents": [{"type": "text", "value": {"text": "What is the sentiment of this review?", "tool_call": {"arguments": "{\"location\": \"San Francisco\"}", "id": "call_abc123", "name": "get_weather", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "sunny, 72F", "tool_id": "call_abc123", "type": "function"}}}], "role": "user"}]}, "llm_provider": {"bedrock": {"region": "us-east-1"}, "integration_account_id": "my-account-id", "integration_provider": "openai", "model_name": "gpt-4o", "vertex_ai": {"location": "us-central1", "project": "my-gcp-project"}}, "target": {"application_name": "my-llm-app", "enabled": true, "eval_scope": "span", "filter": "@service:my-service", "root_spans_only": true, "sampling_percentage": 50.0}}, "id": "my-custom-evaluator", "type": "evaluator_config"}}
When the request is sent
Then the response status is 422 Unprocessable Entity

@generated @skip @team:DataDog/ml-observability
Scenario: Delete LLM Observability dataset records returns "Bad Request" response
Given operation "DeleteLLMObsDatasetRecords" enabled
Expand Down Expand Up @@ -264,6 +300,30 @@ Feature: LLM Observability
When the request is sent
Then the response status is 204 No Content

@generated @skip @team:DataDog/ml-observability
Scenario: Delete a custom evaluator configuration returns "Bad Request" response
Given operation "DeleteLLMObsCustomEvalConfig" enabled
And new "DeleteLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: Delete a custom evaluator configuration returns "No Content" response
Given operation "DeleteLLMObsCustomEvalConfig" enabled
And new "DeleteLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 204 No Content

@generated @skip @team:DataDog/ml-observability
Scenario: Delete a custom evaluator configuration returns "Not Found" response
Given operation "DeleteLLMObsCustomEvalConfig" enabled
And new "DeleteLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 404 Not Found

@generated @skip @team:DataDog/ml-observability
Scenario: Delete an LLM Observability annotation queue returns "No Content" response
Given operation "DeleteLLMObsAnnotationQueue" enabled
Expand Down Expand Up @@ -307,6 +367,30 @@ Feature: LLM Observability
When the request is sent
Then the response status is 404 Not Found

@generated @skip @team:DataDog/ml-observability
Scenario: Get a custom evaluator configuration returns "Bad Request" response
Given operation "GetLLMObsCustomEvalConfig" enabled
And new "GetLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: Get a custom evaluator configuration returns "Not Found" response
Given operation "GetLLMObsCustomEvalConfig" enabled
And new "GetLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 404 Not Found

@generated @skip @team:DataDog/ml-observability
Scenario: Get a custom evaluator configuration returns "OK" response
Given operation "GetLLMObsCustomEvalConfig" enabled
And new "GetLLMObsCustomEvalConfig" request
And request contains "eval_name" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: Get annotated queue interactions returns "Bad Request" response
Given operation "GetLLMObsAnnotatedInteractions" enabled
Expand Down
25 changes: 25 additions & 0 deletions features/v2/undo.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,31 @@
"type": "unsafe"
}
},
"DeleteLLMObsCustomEvalConfig": {
"tag": "LLM Observability",
"undo": {
"operationId": "UpdateLLMObsCustomEvalConfig",
"parameters": [
{
"name": "eval_name",
"source": "path"
}
],
"type": "unsafe"
}
},
"GetLLMObsCustomEvalConfig": {
"tag": "LLM Observability",
"undo": {
"type": "safe"
}
},
"UpdateLLMObsCustomEvalConfig": {
"tag": "LLM Observability",
"undo": {
"type": "idempotent"
}
},
"ListDatastores": {
"tag": "Actions Datastores",
"undo": {
Expand Down
Loading
Loading