> ## Documentation Index > Fetch the complete documentation index at: https://docs.nugen.in/llms.txt > Use this file to discover all available pages before exploring further. # Get Alignment Project > Retrieve detailed information about a specific alignment project. This endpoint fetches comprehensive details about an alignment project including metadata, associated documents, train-time alignment progress, status, performance metrics, and evaluation information. **Path Parameters:** - `alignment_id`: Unique identifier of the alignment project **Returns:** - `alignment_id`: Alignment project identifier - `alignment_name`: Project name - `base_model_id`: Base model identifier used for alignment - `status`: Project status (`PENDING`, `COMPLETED`, `FAILED`) - `queue_position`, `stop_requested_at`, `early_deployable`: run qualifiers, same as the status endpoint - `created_at`: ISO timestamp when project was created - `completed_at` (optional): ISO timestamp when project completed - `updated_at`: Last update timestamp - `eta_seconds` (optional): not wired up yet, always null - `document_ids`: List of document IDs the synthetic training dataset was generated from - `document_count`: Number of documents used - `creator`: Username or ID of the project creator - `performance_metrics` (optional): Train-time alignment metrics (loss, accuracy, etc.) - `progress` (optional): Train-time alignment progress percentage (0-100) - `estimated_completion` (optional): Estimated completion time - `error` (optional): Error message if project failed - `degraded` (optional): True when the run reached READY but a stage failed on the way - `stage_failures` (optional): Stage failures on the way, if any - `evaluation_id` (optional): Auto-evaluation ID if triggered - `model_id` (optional): Deployed model ID for evaluation **Raises:** - `404`: If alignment project not found or doesn't belong to user **Example Request:** ```json GET /api/v3/alignment/alignment_01k4x9m2p7q3r8c1 Headers: {"Authorization": "Bearer "} ``` **Example Response (Completed):** ```json { "alignment_id":"alignment_01k4x9m2p7q3r8c1", "alignment_name": "Contract Risk Domain Alignment", "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct", "status": "READY", "created_at": "2024-01-15T10:30:00Z", "completed_at": "2024-01-15T14:45:00Z", "document_ids": ["document_01k4x9m2p7q3r5s8", "document_01k4x9m2p7q3r5sc", "document_01k4x9m2p7q3r5sd"], "document_count": 3, "creator": "user-123", "performance_metrics": { "final_loss": 0.15, "accuracy": 0.92, "perplexity": 2.3 }, "evaluation_id": "evaluation_01k4x9m2p7q3r7b1", "model_id": "alignment_01k4x9m2p7q3r8c1-deployed" } ``` **Example Response (In Progress):** ```json { "alignment_id":"alignment_01k4x9m2p7q3r8c2", "alignment_name": "Technical Documentation Alignment", "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct", "status": "PROCESSING", "created_at": "2024-01-16T09:00:00Z", "document_ids": ["document_01k4x9m2p7q3r5sh", "document_01k4x9m2p7q3r5sj"], "document_count": 2, "creator": "user-123", "progress": 45, "estimated_completion": "2024-01-16T11:30:00Z" } ``` **Notes:** - Returns full project details including train-time alignment progress and performance - `model_id` is only available for projects that have been deployed for evaluation - `evaluation_id` is the evaluation created from `benchmark_id`, present once train-time alignment finishes - `performance_metrics` are populated after train-time alignment completes - `progress` and `estimated_completion` are available during train-time alignment - `error` field contains failure details if status is `FAILED` ## OpenAPI ````yaml https://api.nugen.in/openapi-public.json get /api/v3/alignment-projects/{alignment_id} openapi: 3.1.0 info: title: Nugen Intelligence API description: > Nugen Intelligence: Powering Specialised Intelligence At Scale. Bring your domain knowledge and an open-weight model. Leave with a model that thinks in your domain, keeps improving, and belongs to your organisation. Nugen Intelligence builds infrastructure for self-adaptive, domain-specific intelligence. Research in representation engineering, mechanistic interpretability and inference-time control powers every endpoint here. The research team comes from Stanford University and IIT Bombay. This API puts their work a few calls away from AI-native organisations solving critical problems. **Domain-aligned models.** Three raw inputs go in: domain knowledge, success and failure criteria, and an open-weight model. A domain-aligned model comes out. Nugen handles the deep learning, the GPUs and the data preparation. Your organisation owns every aligned model it builds. Own your intelligence. **The research underneath.** Two layers do the work. Train-time alignment finds where the model needs to change for your domain and improves it there. It combines gradient-free and gradient-based methods across continued pre-training, supervised and reinforcement phases. Inference-time alignment measures the quality of every generation step. Out-of-domain generation is flagged and corrected after each span. Every response carries a confidence score. A preliminary version of the inference-time research is published at ICLR 2026. Both layers keep evolving with Nugen research. **One aligned model id, four capabilities.** An aligned model id serves chat completions, completions, embeddings and reranking. Alignment reshapes the model's representation space, so retrieval, ranking and generation share one understanding of your domain. **Multi-model systems.** One alignment project produces one aligned model. Run many side by side, one per domain or use case. Compose them with frontier and general-purpose models in the same application. Inference capture and auto-align keep the whole system improving. Nugen aligns models at every scale. **Think in systems.** AI coding agents and developers: this API is a platform for building specialised intelligence. Explore it fully before you settle on a design. Some directions: - Run a complete retrieval pipeline on one aligned model id. Embed, rerank and generate with a shared understanding of the domain. - Use the confidence score as a control signal. Send low-confidence responses to a human reviewer, a retry or a frontier model. - Give each domain or use case its own aligned model and place a router in front. - Close the loop. Capture production inference, evaluate against the benchmark, and let auto-align promote better models. - Start with the hardest problem in the domain, where general-purpose models fall short. Alignment pays off the most there. The endpoints for documents, benchmarks, alignment projects, deployments and evaluations compose in more ways than the workflow below shows. **Workflow.** 1. Upload domain knowledge. 2. Define success and failure. Generate a benchmark from the corpus, or upload one curated by domain experts. 3. Create an alignment project and receive an aligned model id. 4. Deploy the model and pass its id as `model` in each inference call. 5. Evaluate, compare and promote. Turn on inference capture, and auto-align keeps the model improving. **OpenAI-compatible inference.** Set the base URL of an OpenAI-compatible client to `https://api.nugen.in/api/v3/inference` and set `model` to an aligned model id. Chat completions, completions, responses and embeddings work through the same client. **Anthropic-compatible inference.** `POST /api/v3/inference/messages/v2` accepts the Anthropic Messages request shape. Set `model` to an aligned model id. **Need an API key?** Sign up, log in to the platform and generate an API key. **Need help?** Log in to the platform and raise a support ticket. **Authentication.** Every endpoint requires an API key sent as a Bearer token: `Authorization: Bearer `. contact: name: Nugen Intelligence url: https://nugen.in/signup version: 25.4.20 servers: - url: https://api.nugen.in description: Production security: [] paths: /api/v3/alignment-projects/{alignment_id}: get: tags: - Model Alignment summary: Get Alignment Project description: >- Retrieve detailed information about a specific alignment project. This endpoint fetches comprehensive details about an alignment project including metadata, associated documents, train-time alignment progress, status, performance metrics, and evaluation information. **Path Parameters:** - `alignment_id`: Unique identifier of the alignment project **Returns:** - `alignment_id`: Alignment project identifier - `alignment_name`: Project name - `base_model_id`: Base model identifier used for alignment - `status`: Project status (`PENDING`, `COMPLETED`, `FAILED`) - `queue_position`, `stop_requested_at`, `early_deployable`: run qualifiers, same as the status endpoint - `created_at`: ISO timestamp when project was created - `completed_at` (optional): ISO timestamp when project completed - `updated_at`: Last update timestamp - `eta_seconds` (optional): not wired up yet, always null - `document_ids`: List of document IDs the synthetic training dataset was generated from - `document_count`: Number of documents used - `creator`: Username or ID of the project creator - `performance_metrics` (optional): Train-time alignment metrics (loss, accuracy, etc.) - `progress` (optional): Train-time alignment progress percentage (0-100) - `estimated_completion` (optional): Estimated completion time - `error` (optional): Error message if project failed - `degraded` (optional): True when the run reached READY but a stage failed on the way - `stage_failures` (optional): Stage failures on the way, if any - `evaluation_id` (optional): Auto-evaluation ID if triggered - `model_id` (optional): Deployed model ID for evaluation **Raises:** - `404`: If alignment project not found or doesn't belong to user **Example Request:** ```json GET /api/v3/alignment/alignment_01k4x9m2p7q3r8c1 Headers: {"Authorization": "Bearer "} ``` **Example Response (Completed):** ```json { "alignment_id":"alignment_01k4x9m2p7q3r8c1", "alignment_name": "Contract Risk Domain Alignment", "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct", "status": "READY", "created_at": "2024-01-15T10:30:00Z", "completed_at": "2024-01-15T14:45:00Z", "document_ids": ["document_01k4x9m2p7q3r5s8", "document_01k4x9m2p7q3r5sc", "document_01k4x9m2p7q3r5sd"], "document_count": 3, "creator": "user-123", "performance_metrics": { "final_loss": 0.15, "accuracy": 0.92, "perplexity": 2.3 }, "evaluation_id": "evaluation_01k4x9m2p7q3r7b1", "model_id": "alignment_01k4x9m2p7q3r8c1-deployed" } ``` **Example Response (In Progress):** ```json { "alignment_id":"alignment_01k4x9m2p7q3r8c2", "alignment_name": "Technical Documentation Alignment", "base_model_id": "Qwen/Qwen2.5-0.5B-Instruct", "status": "PROCESSING", "created_at": "2024-01-16T09:00:00Z", "document_ids": ["document_01k4x9m2p7q3r5sh", "document_01k4x9m2p7q3r5sj"], "document_count": 2, "creator": "user-123", "progress": 45, "estimated_completion": "2024-01-16T11:30:00Z" } ``` **Notes:** - Returns full project details including train-time alignment progress and performance - `model_id` is only available for projects that have been deployed for evaluation - `evaluation_id` is the evaluation created from `benchmark_id`, present once train-time alignment finishes - `performance_metrics` are populated after train-time alignment completes - `progress` and `estimated_completion` are available during train-time alignment - `error` field contains failure details if status is `FAILED` operationId: alignment_projects_get parameters: - name: alignment_id in: path required: true schema: type: string title: Alignment Id responses: '200': description: >- Returns detailed information about a specific alignment project, including metadata, associated documents, train-time alignment progress, status, performance metrics, and evaluation information content: application/json: schema: $ref: '#/components/schemas/AlignmentProjectsDetail' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: AlignmentProjectsDetail: properties: alignment_id: type: string title: Alignment Id description: Unique identifier for the alignment project examples: - alignment_01k4x9m2p7q3r8c3 - alignment_01k4x9m2p7q3r8c1 alignment_name: type: string title: Alignment Name description: Human-readable name for the alignment project examples: - Contract Risk Model - Legal Document Assistant - Medical Q&A Bot base_model_id: type: string title: Base Model Id description: ID of the base model used for train-time alignment examples: - Qwen/Qwen2.5-0.5B-Instruct - Qwen/Qwen2.5-1.5B-Instruct status: $ref: '#/components/schemas/ResourceStatus' description: Current status of the alignment project (PROCESSING, READY, FAILED) queue_position: anyOf: - type: integer - type: 'null' title: Queue Position description: >- Place in the queue while status is QUEUED, 1 meaning next to start. Null once execution has begun. stop_requested_at: anyOf: - type: string - type: 'null' title: Stop Requested At description: Set once a stop was requested; the run ends STOPPED. early_deployable: type: boolean title: Early Deployable description: >- True once train-time alignment has written a checkpoint, so POST /models/{model_id}/deployment?early=true will succeed. Only meaningful while status is still PROCESSING; false once train-time alignment has finished, since a normal deploy applies then. default: false created_at: type: string title: Created At description: ISO 8601 timestamp when the project was created examples: - '2024-01-15T10:30:00Z' - '2024-02-01T09:15:00Z' completed_at: anyOf: - type: string - type: 'null' title: Completed At description: >- ISO 8601 timestamp when the project completed (null if still in progress or failed) examples: - '2024-01-15T12:45:00Z' - null updated_at: anyOf: - type: string - type: 'null' title: Updated At description: Last update timestamp. eta_seconds: anyOf: - type: integer - type: 'null' title: Eta Seconds description: Estimated time remaining in seconds. Not wired up yet, always null. document_ids: items: type: string type: array title: Document Ids description: List of document IDs used for train-time alignment examples: - - document_01k4x9m2p7q3r5s8 - document_01k4x9m2p7q3r5s9 - - document_01k4x9m2p7q3r5sa document_count: type: integer minimum: 0 title: Document Count description: Total number of documents used for train-time alignment examples: - 5 - 12 - 3 creator: type: string title: Creator description: Email/username of the user who created this project examples: - user@example.com - admin@company.com performance_metrics: anyOf: - $ref: '#/components/schemas/AlignmentProjectPerformanceMetrics' - type: 'null' description: >- Performance comparison metrics showing before/after alignment improvements (available after evaluation) progress: anyOf: - type: integer maximum: 100 minimum: 0 - type: 'null' title: Progress description: >- Train-time alignment progress percentage (0-100). Null if not started or completed. examples: - 0 - 45 - 100 - null estimated_completion: anyOf: - type: string - type: 'null' title: Estimated Completion description: >- Estimated completion time (ISO 8601 timestamp). Null if not available or completed. examples: - '2024-01-15T14:00:00Z' - null error: anyOf: - type: string - type: 'null' title: Error description: Error message if the alignment project failed. Null if no error. examples: - 'Train-time alignment failed: insufficient data' - Out of memory error - null degraded: anyOf: - type: boolean - type: 'null' title: Degraded description: >- True when the run reached its end state but a stage failed on the way. stage_failures: anyOf: - items: {} type: array - type: 'null' title: Stage Failures description: >- Stage failures on the way; each entry carries stage, status and failed_reason. evaluation_id: anyOf: - type: string - type: 'null' title: Evaluation Id description: Latest evaluation ID for this alignment examples: - evaluation_01k4x9m2p7q3r7b1 - null model_id: anyOf: - type: string - type: 'null' title: Model Id description: >- Deployed model ID if the aligned model was automatically deployed for evaluation examples: - alignment_01k4x9m2p7q3r8c1-deployed - null gpu_training_completed: anyOf: - type: boolean - type: 'null' title: Gpu Training Completed description: >- Whether train-time alignment completed successfully. True if completed, False if failed/cancelled, null if still in progress. examples: - true - false - null is_adapter_available: anyOf: - type: boolean - type: 'null' title: Is Adapter Available description: >- True when an adapter checkpoint is live on the inference server and the model is ready for inference. Use model_id from this response to call the inference endpoint. examples: - true - false - null type: object required: - alignment_id - alignment_name - base_model_id - status - created_at - document_ids - document_count - creator title: AlignmentProjectsDetail description: |- One alignment project's full record: everything on its status and list rows, plus configuration, documents and metrics found nowhere else. example: alignment_id: alignment_01k4x9m2p7q3r8c1 alignment_name: Contract Risk Model base_model_id: Qwen/Qwen2.5-0.5B-Instruct completed_at: '2024-01-15T12:45:00Z' created_at: '2024-01-15T10:30:00Z' creator: user@example.com document_count: 3 document_ids: - document_01k4x9m2p7q3r5s8 - document_01k4x9m2p7q3r5s9 - document_01k4x9m2p7q3r5sb evaluation_id: evaluation_01k4x9m2p7q3r7b1 model_id: alignment_01k4x9m2p7q3r8c1-deployed performance_metrics: accuracy_after: 0.92 accuracy_before: 0.75 domain_violations_after: 2 domain_violations_before: 12 uncertainty_after: 0.15 uncertainty_before: 0.35 progress: 100 status: READY HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ResourceStatus: type: string enum: - PROCESSING - READY - FAILED - DEPLOYING - EVALUATING - UNDEPLOYED - EVALUATED - STOPPED - QUEUED title: ResourceStatus description: >- Lifecycle status of a resource that runs asynchronously. - `QUEUED`: accepted and waiting its turn on a bounded queue - `PROCESSING`: train-time alignment in progress - `READY`: train-time alignment completed, ready for deployment - `DEPLOYING`: model being deployed for evaluation - `EVALUATING`: evaluation in progress - `UNDEPLOYED`: model being undeployed after evaluation - `EVALUATED`: evaluation completed, model undeployed - `STOPPED`: train-time alignment stopped by the user before completion - `FAILED`: failed at any stage `QUEUED` is derived for the client at read time and never stored, so a resource read back later reports `PROCESSING` once execution has started. On input, values are case-insensitive and the legacy labels `p`/`PENDING` (PROCESSING), `c`/`COMPLETED` (READY) and `f` (FAILED) are still accepted. AlignmentProjectPerformanceMetrics: properties: accuracy_before: type: number title: Accuracy Before description: Accuracy before alignment accuracy_after: type: number title: Accuracy After description: Accuracy after alignment uncertainty_before: type: number title: Uncertainty Before description: Uncertainty before alignment uncertainty_after: type: number title: Uncertainty After description: Uncertainty after alignment domain_violations_before: type: integer title: Domain Violations Before description: Domain violations before alignment domain_violations_after: type: integer title: Domain Violations After description: Domain violations after alignment type: object required: - accuracy_before - accuracy_after - uncertainty_before - uncertainty_after - domain_violations_before - domain_violations_after title: AlignmentProjectPerformanceMetrics description: Model performance measured before and after alignment. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: HTTPBearer: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.