judgeval 0.1.0__py3-none-any.whl → 0.23.0__py3-none-any.whl

judgeval/data/judgment_types.py

@@ -1,206 +1,456 @@
 # generated by datamodel-codegen:
-#   filename:  openapi_new.json
-#   timestamp: 2025-07-17T03:14:16+00:00
+#   filename:  .openapi.json
+#   timestamp: 2025-11-18T18:52:09+00:00
 
 from __future__ import annotations
-
 from typing import Annotated, Any, Dict, List, Optional, Union
+from pydantic import AwareDatetime, BaseModel, ConfigDict, Field, RootModel
+from enum import Enum
 
-from pydantic import BaseModel, Field
 
+class TraceAndSpanId(RootModel[List]):
+    root: Annotated[List, Field(max_length=2, min_length=2)]
 
-class ValidationErrorJudgmentType(BaseModel):
-    loc: Annotated[List[Union[str, int]], Field(title="Location")]
-    msg: Annotated[str, Field(title="Message")]
-    type: Annotated[str, Field(title="Error Type")]
+
+class LogEvalResultsResponse(BaseModel):
+    ui_results_url: Annotated[str, Field(title="Ui Results Url")]
+
+
+class EvalResultsFetch(BaseModel):
+    experiment_run_id: Annotated[str, Field(title="Experiment Run Id")]
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class FetchExperimentRunResponse(BaseModel):
+    results: Annotated[Optional[List], Field(title="Results")] = None
+    ui_results_url: Annotated[Optional[str], Field(title="Ui Results Url")] = None
+
+
+class DatasetFetch(BaseModel):
+    dataset_name: Annotated[str, Field(title="Dataset Name")]
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class DatasetsFetch(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ProjectAdd(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ProjectAddResponse(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+
+
+class ProjectDeleteFromJudgevalResponse(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ProjectDeleteResponse(BaseModel):
+    message: Annotated[str, Field(title="Message")]
+
+
+class ScorerExistsRequest(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+
+
+class ScorerExistsResponse(BaseModel):
+    exists: Annotated[bool, Field(title="Exists")]
 
 
-class ScorerDataJudgmentType(BaseModel):
+class SavePromptScorerRequest(BaseModel):
     name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
     threshold: Annotated[float, Field(title="Threshold")]
-    success: Annotated[bool, Field(title="Success")]
+    model: Annotated[Optional[str], Field(title="Model")] = "gpt-5-mini"
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    description: Annotated[Optional[str], Field(title="Description")] = None
+
+
+class FetchPromptScorersRequest(BaseModel):
+    names: Annotated[Optional[List[str]], Field(title="Names")] = None
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = None
+
+
+class CustomScorerUploadPayload(BaseModel):
+    scorer_name: Annotated[str, Field(title="Scorer Name")]
+    scorer_code: Annotated[str, Field(title="Scorer Code")]
+    requirements_text: Annotated[str, Field(title="Requirements Text")]
+    overwrite: Annotated[Optional[bool], Field(title="Overwrite")] = False
+
+
+class CustomScorerTemplateResponse(BaseModel):
+    scorer_name: Annotated[str, Field(title="Scorer Name")]
+    status: Annotated[str, Field(title="Status")]
+    message: Annotated[str, Field(title="Message")]
+
+
+class PromptInsertRequest(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+    name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
+    tags: Annotated[List[str], Field(title="Tags")]
+
+
+class PromptInsertResponse(BaseModel):
+    commit_id: Annotated[str, Field(title="Commit Id")]
+    parent_commit_id: Annotated[Optional[str], Field(title="Parent Commit Id")] = None
+    created_at: Annotated[str, Field(title="Created At")]
+
+
+class PromptTagRequest(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+    name: Annotated[str, Field(title="Name")]
+    commit_id: Annotated[str, Field(title="Commit Id")]
+    tags: Annotated[List[str], Field(title="Tags")]
+
+
+class PromptTagResponse(BaseModel):
+    commit_id: Annotated[str, Field(title="Commit Id")]
+
+
+class PromptUntagRequest(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+    name: Annotated[str, Field(title="Name")]
+    tags: Annotated[List[str], Field(title="Tags")]
+
+
+class PromptUntagResponse(BaseModel):
+    commit_ids: Annotated[List[str], Field(title="Commit Ids")]
+
+
+class ResolveProjectNameRequest(BaseModel):
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class ResolveProjectNameResponse(BaseModel):
+    project_id: Annotated[str, Field(title="Project Id")]
+
+
+class TraceIdRequest(BaseModel):
+    trace_id: Annotated[str, Field(title="Trace Id")]
+
+
+class SpanScoreRequest(BaseModel):
+    span_id: Annotated[str, Field(title="Span Id")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+
+
+class BaseScorer(BaseModel):
+    score_type: Annotated[str, Field(title="Score Type")]
+    threshold: Annotated[Optional[float], Field(title="Threshold")] = 0.5
+    name: Annotated[Optional[str], Field(title="Name")] = None
+    class_name: Annotated[Optional[str], Field(title="Class Name")] = None
     score: Annotated[Optional[float], Field(title="Score")] = None
-    reason: Annotated[Optional[str], Field(title="Reason")] = None
-    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = None
-    evaluation_model: Annotated[
-        Optional[Union[List[str], str]], Field(title="Evaluation Model")
+    score_breakdown: Annotated[
+        Optional[Dict[str, Any]], Field(title="Score Breakdown")
     ] = None
+    reason: Annotated[Optional[str], Field(title="Reason")] = ""
+    using_native_model: Annotated[Optional[bool], Field(title="Using Native Model")] = (
+        None
+    )
+    success: Annotated[Optional[bool], Field(title="Success")] = None
+    model: Annotated[Optional[str], Field(title="Model")] = None
+    model_client: Annotated[Any, Field(title="Model Client")] = None
+    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = False
     error: Annotated[Optional[str], Field(title="Error")] = None
     additional_metadata: Annotated[
         Optional[Dict[str, Any]], Field(title="Additional Metadata")
     ] = None
+    user: Annotated[Optional[str], Field(title="User")] = None
+    server_hosted: Annotated[Optional[bool], Field(title="Server Hosted")] = False
 
 
-class ScorerConfigJudgmentType(BaseModel):
+class ScorerConfig(BaseModel):
     score_type: Annotated[str, Field(title="Score Type")]
     name: Annotated[Optional[str], Field(title="Name")] = None
     threshold: Annotated[Optional[float], Field(title="Threshold")] = 0.5
     strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = False
-    required_params: Annotated[Optional[List[str]], Field(title="Required Params")] = (
-        Field(default_factory=list)
-    )
+    required_params: Annotated[Optional[List[str]], Field(title="Required Params")] = []
     kwargs: Annotated[Optional[Dict[str, Any]], Field(title="Kwargs")] = None
 
 
-class TraceUsageJudgmentType(BaseModel):
-    prompt_tokens: Annotated[Optional[int], Field(title="Prompt Tokens")] = None
-    completion_tokens: Annotated[Optional[int], Field(title="Completion Tokens")] = None
-    cache_creation_input_tokens: Annotated[
-        Optional[int], Field(title="Cache Creation Input Tokens")
-    ] = None
-    cache_read_input_tokens: Annotated[
-        Optional[int], Field(title="Cache Read Input Tokens")
-    ] = None
-    total_tokens: Annotated[Optional[int], Field(title="Total Tokens")] = None
-    prompt_tokens_cost_usd: Annotated[
-        Optional[float], Field(title="Prompt Tokens Cost Usd")
-    ] = None
-    completion_tokens_cost_usd: Annotated[
-        Optional[float], Field(title="Completion Tokens Cost Usd")
-    ] = None
-    total_cost_usd: Annotated[Optional[float], Field(title="Total Cost Usd")] = None
-    model_name: Annotated[Optional[str], Field(title="Model Name")] = None
+class Example(BaseModel):
+    model_config = ConfigDict(
+        extra="allow",
+    )
+    example_id: Annotated[Optional[str], Field(title="Example Id")] = None
+    created_at: Annotated[Optional[str], Field(title="Created At")] = None
+    name: Annotated[Optional[str], Field(title="Name")] = None
 
 
-class ToolJudgmentType(BaseModel):
-    tool_name: Annotated[str, Field(title="Tool Name")]
-    parameters: Annotated[Optional[Dict[str, Any]], Field(title="Parameters")] = None
-    agent_name: Annotated[Optional[str], Field(title="Agent Name")] = None
-    result_dependencies: Annotated[
-        Optional[List[Dict[str, Any]]], Field(title="Result Dependencies")
-    ] = None
-    action_dependencies: Annotated[
-        Optional[List[Dict[str, Any]]], Field(title="Action Dependencies")
-    ] = None
-    require_all: Annotated[Optional[bool], Field(title="Require All")] = None
+class ValidationError(BaseModel):
+    loc: Annotated[List[Union[str, int]], Field(title="Location")]
+    msg: Annotated[str, Field(title="Message")]
+    type: Annotated[str, Field(title="Error Type")]
 
 
-class HTTPValidationErrorJudgmentType(BaseModel):
-    detail: Annotated[
-        Optional[List[ValidationErrorJudgmentType]], Field(title="Detail")
-    ] = None
+class UsageInfo(BaseModel):
+    total_judgees: Annotated[int, Field(title="Total Judgees")]
+    regular_use: Annotated[int, Field(title="Regular Use")]
+    pay_as_you_go_use: Annotated[int, Field(title="Pay As You Go Use")]
+    remaining_regular: Annotated[int, Field(title="Remaining Regular")]
+    remaining_after: Annotated[int, Field(title="Remaining After")]
 
 
-class TraceSpanJudgmentType(BaseModel):
-    span_id: Annotated[str, Field(title="Span Id")]
-    trace_id: Annotated[str, Field(title="Trace Id")]
-    function: Annotated[str, Field(title="Function")]
-    depth: Annotated[int, Field(title="Depth")]
-    created_at: Annotated[Any, Field(title="Created At")] = None
-    parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
-    span_type: Annotated[Optional[str], Field(title="Span Type")] = "span"
-    inputs: Annotated[Optional[Dict[str, Any]], Field(title="Inputs")] = None
-    error: Annotated[Optional[Dict[str, Any]], Field(title="Error")] = None
-    output: Annotated[Any, Field(title="Output")] = None
-    usage: Optional[TraceUsageJudgmentType] = None
-    duration: Annotated[Optional[float], Field(title="Duration")] = None
-    expected_tools: Annotated[
-        Optional[List[ToolJudgmentType]], Field(title="Expected Tools")
-    ] = None
+class DatasetKind(Enum):
+    trace = "trace"
+    example = "example"
+
+
+class PromptScorer(BaseModel):
+    id: Annotated[str, Field(title="Id")]
+    user_id: Annotated[str, Field(title="User Id")]
+    organization_id: Annotated[str, Field(title="Organization Id")]
+    name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
+    threshold: Annotated[float, Field(title="Threshold")]
+    model: Annotated[Optional[str], Field(title="Model")] = "gpt-5-mini"
+    options: Annotated[Optional[Dict[str, float]], Field(title="Options")] = None
+    description: Annotated[Optional[str], Field(title="Description")] = None
+    created_at: Annotated[Optional[AwareDatetime], Field(title="Created At")] = None
+    updated_at: Annotated[Optional[AwareDatetime], Field(title="Updated At")] = None
+    is_trace: Annotated[Optional[bool], Field(title="Is Trace")] = False
+    is_bucket_rubric: Annotated[Optional[bool], Field(title="Is Bucket Rubric")] = None
+
+
+class PromptCommitInfo(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    prompt: Annotated[str, Field(title="Prompt")]
+    tags: Annotated[List[str], Field(title="Tags")]
+    commit_id: Annotated[str, Field(title="Commit Id")]
+    parent_commit_id: Annotated[Optional[str], Field(title="Parent Commit Id")] = None
+    created_at: Annotated[str, Field(title="Created At")]
+    first_name: Annotated[str, Field(title="First Name")]
+    last_name: Annotated[str, Field(title="Last Name")]
+    user_email: Annotated[str, Field(title="User Email")]
+
+
+class ScorerData(BaseModel):
+    id: Annotated[Optional[str], Field(title="Id")] = None
+    name: Annotated[str, Field(title="Name")]
+    threshold: Annotated[float, Field(title="Threshold")]
+    success: Annotated[bool, Field(title="Success")]
+    score: Annotated[Optional[float], Field(title="Score")] = None
+    reason: Annotated[Optional[str], Field(title="Reason")] = None
+    strict_mode: Annotated[Optional[bool], Field(title="Strict Mode")] = None
+    evaluation_model: Annotated[Optional[str], Field(title="Evaluation Model")] = None
+    error: Annotated[Optional[str], Field(title="Error")] = None
     additional_metadata: Annotated[
         Optional[Dict[str, Any]], Field(title="Additional Metadata")
     ] = None
-    has_evaluation: Annotated[Optional[bool], Field(title="Has Evaluation")] = False
-    agent_name: Annotated[Optional[str], Field(title="Agent Name")] = None
-    state_before: Annotated[Optional[Dict[str, Any]], Field(title="State Before")] = (
-        None
-    )
-    state_after: Annotated[Optional[Dict[str, Any]], Field(title="State After")] = None
-    update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
 
 
-class ExampleJudgmentType(BaseModel):
-    input: Annotated[Optional[Union[str, Dict[str, Any]]], Field(title="Input")] = None
-    actual_output: Annotated[
-        Optional[Union[str, List[str]]], Field(title="Actual Output")
-    ] = None
-    expected_output: Annotated[
-        Optional[Union[str, List[str]]], Field(title="Expected Output")
-    ] = None
-    context: Annotated[Optional[List[str]], Field(title="Context")] = None
-    retrieval_context: Annotated[
-        Optional[List[str]], Field(title="Retrieval Context")
+class OtelTraceSpan(BaseModel):
+    organization_id: Annotated[str, Field(title="Organization Id")]
+    project_id: Annotated[Optional[str], Field(title="Project Id")] = None
+    user_id: Annotated[str, Field(title="User Id")]
+    timestamp: Annotated[str, Field(title="Timestamp")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+    span_id: Annotated[str, Field(title="Span Id")]
+    parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
+    trace_state: Annotated[Optional[str], Field(title="Trace State")] = None
+    span_name: Annotated[Optional[str], Field(title="Span Name")] = None
+    span_kind: Annotated[Optional[str], Field(title="Span Kind")] = None
+    service_name: Annotated[Optional[str], Field(title="Service Name")] = None
+    resource_attributes: Annotated[
+        Optional[Dict[str, Any]], Field(title="Resource Attributes")
     ] = None
-    additional_metadata: Annotated[
-        Optional[Dict[str, Any]], Field(title="Additional Metadata")
+    span_attributes: Annotated[
+        Optional[Dict[str, Any]], Field(title="Span Attributes")
     ] = None
-    tools_called: Annotated[Optional[List[str]], Field(title="Tools Called")] = Field(
-        default_factory=list
-    )
-    expected_tools: Annotated[
-        Optional[List[ToolJudgmentType]], Field(title="Expected Tools")
-    ] = Field(default_factory=list)
-    name: Annotated[Optional[str], Field(title="Name")] = None
-    example_id: Annotated[str, Field(title="Example Id")]
-    example_index: Annotated[Optional[int], Field(title="Example Index")] = None
+    duration: Annotated[Optional[int], Field(title="Duration")] = None
+    status_code: Annotated[Optional[int], Field(title="Status Code")] = None
+    status_message: Annotated[Optional[str], Field(title="Status Message")] = None
+    events: Annotated[Optional[List[Dict[str, Any]]], Field(title="Events")] = None
+    links: Annotated[Optional[List[Dict[str, Any]]], Field(title="Links")] = None
+
+
+class OtelSpanListItemScores(BaseModel):
+    success: Annotated[bool, Field(title="Success")]
+    score: Annotated[float, Field(title="Score")]
+    reason: Annotated[Optional[str], Field(title="Reason")] = None
+    name: Annotated[str, Field(title="Name")]
+
+
+class OtelSpanDetailScores(BaseModel):
+    success: Annotated[bool, Field(title="Success")]
+    score: Annotated[float, Field(title="Score")]
+    reason: Annotated[Optional[str], Field(title="Reason")] = None
+    name: Annotated[str, Field(title="Name")]
+    example_id: Annotated[Optional[str], Field(title="Example Id")] = None
+
+
+class ExampleEvaluationRun(BaseModel):
+    id: Annotated[Optional[str], Field(title="Id")] = None
+    project_name: Annotated[str, Field(title="Project Name")]
+    eval_name: Annotated[str, Field(title="Eval Name")]
+    custom_scorers: Annotated[
+        Optional[List[BaseScorer]], Field(title="Custom Scorers")
+    ] = []
+    judgment_scorers: Annotated[
+        Optional[List[ScorerConfig]], Field(title="Judgment Scorers")
+    ] = []
     created_at: Annotated[Optional[str], Field(title="Created At")] = None
-    trace_id: Annotated[Optional[str], Field(title="Trace Id")] = None
+    examples: Annotated[List[Example], Field(title="Examples")]
     trace_span_id: Annotated[Optional[str], Field(title="Trace Span Id")] = None
-    dataset_id: Annotated[Optional[str], Field(title="Dataset Id")] = None
+    trace_id: Annotated[Optional[str], Field(title="Trace Id")] = None
 
 
-class TraceJudgmentType(BaseModel):
-    trace_id: Annotated[str, Field(title="Trace Id")]
+class HTTPValidationError(BaseModel):
+    detail: Annotated[Optional[List[ValidationError]], Field(title="Detail")] = None
+
+
+class TraceEvaluationRun(BaseModel):
+    id: Annotated[Optional[str], Field(title="Id")] = None
+    project_name: Annotated[str, Field(title="Project Name")]
+    eval_name: Annotated[str, Field(title="Eval Name")]
+    custom_scorers: Annotated[
+        Optional[List[BaseScorer]], Field(title="Custom Scorers")
+    ] = []
+    judgment_scorers: Annotated[
+        Optional[List[ScorerConfig]], Field(title="Judgment Scorers")
+    ] = []
+    created_at: Annotated[Optional[str], Field(title="Created At")] = None
+    trace_and_span_ids: Annotated[
+        List[TraceAndSpanId], Field(title="Trace And Span Ids")
+    ]
+    is_offline: Annotated[Optional[bool], Field(title="Is Offline")] = False
+    is_bucket_run: Annotated[Optional[bool], Field(title="Is Bucket Run")] = False
+
+
+class DatasetInsertExamples(BaseModel):
+    dataset_name: Annotated[str, Field(title="Dataset Name")]
+    examples: Annotated[List[Example], Field(title="Examples")]
+    project_name: Annotated[str, Field(title="Project Name")]
+
+
+class DatasetInfo(BaseModel):
+    dataset_id: Annotated[str, Field(title="Dataset Id")]
     name: Annotated[str, Field(title="Name")]
     created_at: Annotated[str, Field(title="Created At")]
-    duration: Annotated[float, Field(title="Duration")]
-    trace_spans: Annotated[List[TraceSpanJudgmentType], Field(title="Trace Spans")]
-    overwrite: Annotated[Optional[bool], Field(title="Overwrite")] = False
-    offline_mode: Annotated[Optional[bool], Field(title="Offline Mode")] = False
-    rules: Annotated[Optional[Dict[str, Any]], Field(title="Rules")] = Field(
-        default_factory=dict
-    )
-    has_notification: Annotated[Optional[bool], Field(title="Has Notification")] = False
-    customer_id: Annotated[Optional[str], Field(title="Customer Id")] = None
-    tags: Annotated[Optional[List[str]], Field(title="Tags")] = Field(
-        default_factory=list
-    )
-    metadata: Annotated[Optional[Dict[str, Any]], Field(title="Metadata")] = Field(
-        default_factory=dict
-    )
-    update_id: Annotated[Optional[int], Field(title="Update Id")] = 1
+    kind: DatasetKind
+    entries: Annotated[int, Field(title="Entries")]
+    creator: Annotated[str, Field(title="Creator")]
+
+
+class DatasetCreate(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    dataset_kind: DatasetKind
+    project_name: Annotated[str, Field(title="Project Name")]
+    examples: Annotated[List[Example], Field(title="Examples")]
+    overwrite: Annotated[bool, Field(title="Overwrite")]
 
 
-class ScoringResultJudgmentType(BaseModel):
+class SavePromptScorerResponse(BaseModel):
+    scorer_response: PromptScorer
+
+
+class FetchPromptScorersResponse(BaseModel):
+    scorers: Annotated[List[PromptScorer], Field(title="Scorers")]
+
+
+class PromptFetchResponse(BaseModel):
+    commit: Optional[PromptCommitInfo] = None
+
+
+class PromptVersionsResponse(BaseModel):
+    versions: Annotated[List[PromptCommitInfo], Field(title="Versions")]
+
+
+class ScoringResult(BaseModel):
     success: Annotated[bool, Field(title="Success")]
-    scorers_data: Annotated[
-        Optional[List[ScorerDataJudgmentType]], Field(title="Scorers Data")
-    ]
+    scorers_data: Annotated[List[ScorerData], Field(title="Scorers Data")]
     name: Annotated[Optional[str], Field(title="Name")] = None
     data_object: Annotated[
-        Optional[Union[TraceSpanJudgmentType, ExampleJudgmentType]],
-        Field(title="Data Object"),
+        Optional[Union[OtelTraceSpan, Example]], Field(title="Data Object")
     ] = None
     trace_id: Annotated[Optional[str], Field(title="Trace Id")] = None
     run_duration: Annotated[Optional[float], Field(title="Run Duration")] = None
     evaluation_cost: Annotated[Optional[float], Field(title="Evaluation Cost")] = None
 
 
-class TraceRunJudgmentType(BaseModel):
-    project_name: Annotated[Optional[str], Field(title="Project Name")] = None
-    eval_name: Annotated[Optional[str], Field(title="Eval Name")] = None
-    traces: Annotated[List[TraceJudgmentType], Field(title="Traces")]
-    scorers: Annotated[List[ScorerConfigJudgmentType], Field(title="Scorers")]
-    model: Annotated[str, Field(title="Model")]
-    append: Annotated[Optional[bool], Field(title="Append")] = False
-    override: Annotated[Optional[bool], Field(title="Override")] = False
-    trace_span_id: Annotated[Optional[str], Field(title="Trace Span Id")] = None
-    tools: Annotated[Optional[List[Dict[str, Any]]], Field(title="Tools")] = None
+class OtelTraceListItem(BaseModel):
+    organization_id: Annotated[str, Field(title="Organization Id")]
+    project_id: Annotated[str, Field(title="Project Id")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+    created_at: Annotated[AwareDatetime, Field(title="Created At")]
+    duration: Annotated[Optional[int], Field(title="Duration")] = None
+    tags: Annotated[Optional[List[str]], Field(title="Tags")] = None
+    experiment_run_id: Annotated[Optional[str], Field(title="Experiment Run Id")] = None
+    span_name: Annotated[Optional[str], Field(title="Span Name")] = None
+    llm_cost: Annotated[Optional[float], Field(title="Llm Cost")] = None
+    error: Annotated[Optional[str], Field(title="Error")] = ""
+    scores: Annotated[
+        Optional[List[OtelSpanListItemScores]], Field(title="Scores")
+    ] = []
+    rules_invoked: Annotated[Optional[List[str]], Field(title="Rules Invoked")] = []
+    customer_id: Annotated[Optional[str], Field(title="Customer Id")] = None
+    input: Annotated[Optional[str], Field(title="Input")] = None
+    output: Annotated[Optional[str], Field(title="Output")] = None
+    input_preview: Annotated[Optional[str], Field(title="Input Preview")] = None
+    output_preview: Annotated[Optional[str], Field(title="Output Preview")] = None
+    annotation_count: Annotated[Optional[int], Field(title="Annotation Count")] = 0
+    span_id: Annotated[str, Field(title="Span Id")]
+    rule_id: Annotated[Optional[str], Field(title="Rule Id")] = None
 
 
-class JudgmentEvalJudgmentType(BaseModel):
-    project_name: Annotated[Optional[str], Field(title="Project Name")] = None
-    eval_name: Annotated[Optional[str], Field(title="Eval Name")] = None
-    examples: Annotated[List[ExampleJudgmentType], Field(title="Examples")]
-    scorers: Annotated[List[ScorerConfigJudgmentType], Field(title="Scorers")]
-    model: Annotated[str, Field(title="Model")]
-    append: Annotated[Optional[bool], Field(title="Append")] = False
-    override: Annotated[Optional[bool], Field(title="Override")] = False
-    trace_span_id: Annotated[Optional[str], Field(title="Trace Span Id")] = None
+class OtelSpanDetail(BaseModel):
+    organization_id: Annotated[str, Field(title="Organization Id")]
+    project_id: Annotated[str, Field(title="Project Id")]
+    timestamp: Annotated[AwareDatetime, Field(title="Timestamp")]
+    trace_id: Annotated[str, Field(title="Trace Id")]
+    span_id: Annotated[str, Field(title="Span Id")]
+    parent_span_id: Annotated[Optional[str], Field(title="Parent Span Id")] = None
+    trace_state: Annotated[Optional[str], Field(title="Trace State")] = None
+    span_name: Annotated[Optional[str], Field(title="Span Name")] = None
+    span_kind: Annotated[Optional[str], Field(title="Span Kind")] = None
+    service_name: Annotated[Optional[str], Field(title="Service Name")] = None
+    resource_attributes: Annotated[
+        Optional[Dict[str, Any]], Field(title="Resource Attributes")
+    ] = None
+    span_attributes: Annotated[
+        Optional[Dict[str, Any]], Field(title="Span Attributes")
+    ] = None
+    duration: Annotated[Optional[int], Field(title="Duration")] = None
+    status_code: Annotated[Optional[int], Field(title="Status Code")] = None
+    status_message: Annotated[Optional[str], Field(title="Status Message")] = None
+    events: Annotated[Optional[List[Dict[str, Any]]], Field(title="Events")] = None
+    links: Annotated[
+        Optional[Union[List[Dict[str, Any]], Dict[str, Any]]], Field(title="Links")
+    ] = None
+    llm_cost: Annotated[Optional[float], Field(title="Llm Cost")] = None
+    prompt_tokens: Annotated[Optional[int], Field(title="Prompt Tokens")] = None
+    completion_tokens: Annotated[Optional[int], Field(title="Completion Tokens")] = None
+    scores: Annotated[Optional[List[OtelSpanDetailScores]], Field(title="Scores")] = (
+        None
+    )
 
 
-class EvalResultsJudgmentType(BaseModel):
-    results: Annotated[List[ScoringResultJudgmentType], Field(title="Results")]
-    run: Annotated[
-        Union[TraceRunJudgmentType, JudgmentEvalJudgmentType], Field(title="Run")
-    ]
+class EvaluateResponse(BaseModel):
+    status: Annotated[str, Field(title="Status")]
+    results: Annotated[List[ScoringResult], Field(title="Results")]
+    resource_usage: Optional[UsageInfo] = None
+
+
+class EvalResults(BaseModel):
+    results: Annotated[List[ScoringResult], Field(title="Results")]
+    run: Annotated[Union[ExampleEvaluationRun, TraceEvaluationRun], Field(title="Run")]
+
+
+class DatasetTraceWithSpans(BaseModel):
+    dataset_id: Annotated[str, Field(title="Dataset Id")]
+    trace_detail: OtelTraceListItem
+    spans: Annotated[List[OtelSpanDetail], Field(title="Spans")]
+
+
+class DatasetReturn(BaseModel):
+    name: Annotated[str, Field(title="Name")]
+    project_name: Annotated[str, Field(title="Project Name")]
+    dataset_kind: DatasetKind
+    examples: Annotated[Optional[List[Example]], Field(title="Examples")] = None
+    traces: Annotated[Optional[List[DatasetTraceWithSpans]], Field(title="Traces")] = (
+        None
+    )