> ## Documentation Index > Fetch the complete documentation index at: https://docs.decimal.ai/llms.txt > Use this file to discover all available pages before exploring further. # Push external evaluation scores > Push evaluation scores from an external system (DeepEval, LangSmith, etc.). Scores are stored as quality scores (category="quality") and combined with built-in compatibility scores in the unified decision engine. If a score with the same (trace_id, name, source) already exists, it is updated (upsert behavior). ## OpenAPI ````yaml /openapi.json post /api/v1/traces/{trace_id}/eval-scores openapi: 3.1.0 info: title: DecimalAI Platform description: Agent Dataset Lifecycle Platform — Backend API version: 0.1.0 servers: [] security: - BearerAuth: [] tags: - name: traces description: >- Ingest, search, and inspect agent execution traces. A trace is the atomic unit of the platform — every other feature (evaluation, compatibility scoring, dataset building) operates on traces. Each trace is auto-tagged with the manifest hash of the agent that produced it. - name: eval-scores description: >- Push, fetch, and aggregate per-trace evaluation scores. Scores carry source provenance (built-in, DeepEval, LangSmith, custom) and feed the unified decision engine, which produces a keep / repair / replay / drop verdict per trace. - name: skills description: >- Manage reusable instruction blocks (SKILL.md files) that modify agent behavior. Skills are first-class manifest components — changes to a skill appear in your regression-check impact reports. Use these endpoints to create, version, fork, and sync skills with your local SKILL.md files. - name: manifests description: >- Register and inspect manifest versions. A manifest is a snapshot of your agent's structural identity (tools, prompts, models, skills) at a point in time. The SDK registers manifests automatically; these endpoints expose the underlying records. - name: datasets description: >- Build versioned SFT/DPO training datasets from manifest-classified, eval-scored traces. Datasets are reproducible — each version locks the manifest and filter set used to build it. Export as JSONL, Parquet, or push to HuggingFace Hub. - name: replay description: >- Re-execute historical traces against a new manifest version. Replay is the deferred-future capability for behavioral verification of agent changes. The SDK creates a replay batch, your worker executes each task, then submits results back here for eval scoring. - name: registry description: >- Browse and install community skills from the public skills registry. Each registry skill carries a SkillScore — an evidence-tiered quality composite computed from real-world evals, benchmarks, and ratings across organizations. Installing creates a fork in your org — edits don't affect the public version. - name: agents description: >- List and inspect agents, plus their multi-agent topology (orchestrator → sub-agent edges discovered from traces). Agents are identified by a stable agent_name string set in your SDK init() call. - name: import description: >- Bulk-import historical traces from another observability platform or a JSONL backup. Useful for migrating from LangSmith / Braintrust / Langfuse. Duplicate trace IDs are silently skipped — re-running an import is safe. paths: /api/v1/traces/{trace_id}/eval-scores: post: tags: - eval-scores summary: Push external evaluation scores description: >- Push evaluation scores from an external system (DeepEval, LangSmith, etc.). Scores are stored as quality scores (category="quality") and combined with built-in compatibility scores in the unified decision engine. If a score with the same (trace_id, name, source) already exists, it is updated (upsert behavior). operationId: push_eval_scores_api_v1_traces__trace_id__eval_scores_post parameters: - name: trace_id in: path required: true schema: type: string title: Trace Id - name: Authorization in: header required: false schema: type: string title: Authorization - name: decimal_session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Decimal Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PushScoresRequest' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PushScoresResponse' example: trace_id: trc_abc123 source: deepeval scores_stored: 2 scores: - id: es_001 name: correctness score: 0.9 passed: true source: deepeval category: quality - id: es_002 name: faithfulness score: 0.85 passed: true source: deepeval category: quality '404': description: Trace not found. '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: Python label: Python SDK source: >- # For DeepEval / LangSmith integrations, prefer the dedicated helpers: # decimalai.push_deepeval_results(trace_id=..., results=...) # decimalai.push_langsmith_scores(trace_id=..., feedback=...) # Generic custom scores: import decimalai decimalai.push_custom_scores( api_key="dai_sk_...", trace_id="trc_abc123", source="my-pipeline", scores=[ {"name": "correctness", "score": 0.9}, {"name": "faithfulness", "score": 0.85}, ], ) components: schemas: PushScoresRequest: properties: source: type: string title: Source description: >- Source system: 'custom', 'my-pipeline', etc. (reserved external-tool names like 'deepeval' require the webhook path) scores: items: $ref: '#/components/schemas/ScoreInput' type: array minItems: 1 title: Scores description: List of scores to push metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata description: Source-specific metadata (run_id, metric version, etc.) type: object required: - source - scores title: PushScoresRequest description: Request body for pushing external eval scores. PushScoresResponse: properties: trace_id: type: string title: Trace Id source: type: string title: Source scores_stored: type: integer title: Scores Stored scores: items: $ref: '#/components/schemas/ScoreResponse' type: array title: Scores type: object required: - trace_id - source - scores_stored - scores title: PushScoresResponse description: Response after pushing scores. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ScoreInput: properties: name: type: string maxLength: 255 title: Name description: Metric name, e.g. 'correctness', 'faithfulness' score: type: number maximum: 1 minimum: 0 title: Score description: Score value 0.0–1.0 passed: anyOf: - type: boolean - type: 'null' title: Passed description: Binary pass/fail. Auto-derived from score >= 0.5 if omitted reason: anyOf: - type: string - type: 'null' title: Reason description: Human-readable explanation type: object required: - name - score title: ScoreInput description: A single evaluation score. ScoreResponse: properties: id: type: string title: Id name: type: string title: Name score: type: number title: Score passed: type: boolean title: Passed reason: anyOf: - type: string - type: 'null' title: Reason source: type: string title: Source source_label: type: string title: Source Label default: '' icon: type: string title: Icon default: '' badge_color: type: string title: Badge Color default: '' category: type: string title: Category change_type: anyOf: - type: string - type: 'null' title: Change Type field_changes: anyOf: - additionalProperties: true type: object - type: 'null' title: Field Changes type: object required: - id - name - score - passed - source - category title: ScoreResponse description: A single stored score in the response, with provenance. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: BearerAuth: type: http scheme: bearer description: Enter your API key (e.g. dai_sk_test_key_001) ````