> ## Documentation Index > Fetch the complete documentation index at: https://omniloy.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Extract ICD-10 codes from clinical notes > Processes clinical notes (text or PDF) and returns ICD-10 code assessments with confidence scores, detailed justifications, and discarded codes analysis. Supports optional AI model selection and tracking headers. ## OpenAPI ````yaml /openapi/openapi.yaml post /v1/codify openapi: 3.0.3 info: title: Sofia Clinical Documentation API version: 1.0.0 description: > Comprehensive AI-powered clinical documentation platform that includes ICD-10 medical coding, transcription management, AI conversation threads, and clinical note generation with support for various clinical templates (SOAP, BIRP, etc.). servers: - url: https://{your-prod-endpoint} description: Production (provided after deployment) - url: https://{your-dev-endpoint} description: Development (provided upon request) security: - bearerAuth: [] paths: /v1/codify: post: summary: Extract ICD-10 codes from clinical notes description: > Processes clinical notes (text or PDF) and returns ICD-10 code assessments with confidence scores, detailed justifications, and discarded codes analysis. Supports optional AI model selection and tracking headers. operationId: codify parameters: - in: header name: x-doctor schema: type: string required: true description: Doctor identifier for tracking and auditing example: dr_123 - in: header name: x-patient schema: type: string required: false description: Patient identifier for tracking and auditing example: pt_456 requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CodifyRequest' examples: textInput: $ref: '#/components/examples/TextInputRequest' pdfInput: $ref: '#/components/examples/PdfInputRequest' responses: '200': description: Successfully extracted ICD-10 codes content: application/json: schema: $ref: '#/components/schemas/CodifyResponse' examples: successfulCoding: $ref: '#/components/examples/SuccessfulResponse' '400': description: Bad request (medical_note missing or invalid request format) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Bad Request details: medical_note is required '401': description: Unauthorized (invalid or missing token) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Unauthorized details: Missing or invalid authentication token '413': description: >- Payload too large (medical_note exceeds 50KB or pdf_file exceeds 5MB decoded) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Payload Too Large details: Request payload exceeds the maximum allowed size '422': description: Unprocessable entity (invalid PDF structure or encoding) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Unprocessable Entity details: Invalid JSON Schema Draft-07 '429': description: Too many requests (rate limit exceeded) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Too Many Requests details: Too many requests, please try again later '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Internal Server Error details: An unexpected error occurred during codification '503': description: Service unavailable (AI service temporarily unavailable) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Service Unavailable details: Service temporarily unavailable '504': description: Gateway timeout (processing exceeded 10-minute limit) content: application/json: schema: $ref: '#/components/schemas/Error' example: success: false error: Gateway Timeout details: Request timed out after 10 minutes components: schemas: CodifyRequest: type: object required: - medical_note properties: medical_note: type: string description: (REQUIRED) Clinical text to process for ICD-10 coding (max 50KB) example: Patient with Type 2 Diabetes... pdf_file: type: object description: >- (OPTIONAL) PDF file object with base64 encoded data for additional context (max 5MB decoded) required: - type - source_type - data - mime_type - filename properties: type: type: string enum: - file description: Must be "file" source_type: type: string enum: - base64 description: Must be "base64" data: type: string description: Base64 encoded PDF content mime_type: type: string enum: - application/pdf description: Must be "application/pdf" filename: type: string description: Original filename example: medical_report.pdf model: type: string description: Optional AI model quality level selection enum: - fast - balanced - high-quality example: balanced CodifyResponse: type: object required: - final_code_assessments - discarded_code_assessments - run_id properties: final_code_assessments: type: array description: Array of approved ICD-10 code assessments items: $ref: '#/components/schemas/CodeAssessment' discarded_code_assessments: type: array description: Array of considered but rejected code assessments items: $ref: '#/components/schemas/CodeAssessment' run_id: type: string description: Unique identifier (UUID) for this codification run example: 1ef8e0d4-7890-6b3c-8f90-abcdef123456 Error: type: object required: - success - error - details properties: success: type: boolean enum: - false description: Always false for error responses error: type: string description: Error name/type example: Bad Request details: type: string description: Detailed error message example: Either medical_note or pdf_file must be provided CodeAssessment: type: object required: - code - description - justification - confidence_percent properties: code: type: string description: ICD-10 medical code example: E11.9 description: type: string description: Medical description of the code example: Type 2 diabetes mellitus without complications justification: type: string description: AI reasoning for code selection example: >- The note documents Type 2 Diabetes without mention of decompensation or complications... confidence_percent: type: number format: float minimum: 0 maximum: 100 description: Confidence score (0-100) example: 95.2 examples: TextInputRequest: summary: Medical note text input value: medical_note: >- Patient presents with Type 2 Diabetes Mellitus. Current medications: Metformin 500mg BID, Glipizide 5mg QD. Blood glucose levels stable. No complications noted. Patient reports good compliance with medications and diet. HbA1c: 6.8%. model: balanced PdfInputRequest: summary: PDF file input (base64 encoded) value: pdf_file: type: file source_type: base64 data: JVBERi0xLjQKJeLjz9MKMyAwIG9iago8PC9GaWx0ZXI... mime_type: application/pdf filename: medical_report.pdf model: high-quality SuccessfulResponse: summary: Successful ICD-10 coding result value: final_code_assessments: - code: E11.9 description: Type 2 diabetes mellitus without complications justification: >- The note documents Type 2 Diabetes without mention of decompensation or complications; corresponds to E11.9 (DM2 without complications). The stable blood glucose levels and HbA1c of 6.8% indicate controlled diabetes with no evidence of complications. confidence_percent: 95.2 - code: Z79.84 description: Long term (current) use of oral hypoglycemic drugs justification: >- The patient uses metformin and glipizide chronically; both are oral antidiabetic drugs, supporting long term use of oral hypoglycemic drugs. confidence_percent: 98.1 discarded_code_assessments: - code: E11.65 description: Type 2 diabetes mellitus with hyperglycemia justification: >- Discarded because blood glucose levels are stable and controlled (120-140 mg/dL fasting), not indicating hyperglycemia. confidence_percent: 12.3 run_id: 1ef8e0d4-7890-6b3c-8f90-abcdef123456 securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: Bearer token for API authentication ````