import requests

# Multiple sources of clinical context
final_note = """
Assessment:
Acute otitis media of the right ear.

Plan:
Start amoxicillin for 7 days. Follow up if symptoms worsen.
"""

transcript_excerpt = """
Patient reports right ear pain for 3 days, mild fever at home,
and decreased hearing on the right side.
"""

supporting_context = """
Encounter type: outpatient
Specialty: family medicine
"""

# 1. Concatenate multiple contexts into a single text string
combined_context = "\n\n".join([
    "FINAL NOTE",
    final_note.strip(),
    "TRANSCRIPT EXCERPT",
    transcript_excerpt.strip(),
    "SUPPORTING CONTEXT",
    supporting_context.strip()
])

# 2. Pass the combined text into the Predict Codes endpoint
url = "https://api.{environment}.corti.app/v2/tools/coding/"

headers = {
    "Authorization": "Bearer <token>",
    "Tenant-Name": "<tenant-name>",
    "Content-Type": "application/json",
}

payload = {
    "system": [
        "icd10cm-outpatient",
        "cpt"
    ],
    "context": [
        {
            "type": "text",
            "text": combined_context
        }
    ]
}

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()

result = response.json()
print(result)

import requests

BASE_URL = "https://api.{environment}.corti.app/v2"
TOKEN = "<token>"
TENANT_NAME = "<tenant-name>"
INTERACTION_ID = "<interaction-id>"

headers = {
    "Authorization": f"Bearer {TOKEN}",
    "Tenant-Name": TENANT_NAME,
    "Content-Type": "application/json",
}

# Example input used to generate the H&P document.
# The Generate Document endpoint accepts context objects such as string, facts, or transcript. :contentReference[oaicite:1]{index=1}
document_payload = {
    "templateKey": "corti-h-and-p",
    "context": [
        {
            "type": "string",
            "data": """
Chief complaint: Chest pain.

History of present illness:
54-year-old patient with intermittent chest discomfort for 2 days,
worse with exertion, associated with mild shortness of breath.

Past medical history:
Hypertension, hyperlipidemia.

Medications:
Lisinopril, atorvastatin.

Allergies:
No known drug allergies.

Physical exam:
Patient appears comfortable. Heart regular rate and rhythm.
Lungs clear to auscultation.

Assessment:
Chest pain, rule out cardiac etiology.

Plan:
Obtain ECG, troponins, chest x-ray, and monitor closely.
            """.strip()
        }
    ]
}

# 1) Generate an H&P note to create a document ID
generate_document_url = f"{BASE_URL}/interactions/{INTERACTION_ID}/documents"
document_response = requests.post(
    generate_document_url,
    headers=headers,
    json=document_payload
)
document_response.raise_for_status()

document = document_response.json()
document_id = document["id"]

print("Generated document ID:", document_id)

# 2) Pass that documentId into Predict Codes
predict_codes_url = f"{BASE_URL}/tools/coding/"
coding_payload = {
    "system": [
        "icd10cm-outpatient",
        "cpt"
    ],
    "context": [
        {
            "type": "documentId",
            "documentId": document_id
        }
    ]
}

coding_response = requests.post(
    predict_codes_url,
    headers=headers,
    json=coding_payload
)
coding_response.raise_for_status()

codes_result = coding_response.json()
print(codes_result)