Update medication_agent.py

medication_agent.py

@@ -1,30 +1,11 @@
-import datetime
-import openai
-
-openai.api_key = "your-openai-api-key"
-
-# Placeholder medication data
-medications = {}
-
-def set_medication_reminder(medicine: str, time: str):
-    """Set a medication reminder."""
-    reminder_id = str(datetime.datetime.now().timestamp())[:10]
-    medications[reminder_id] = {"medicine": medicine, "time": time, "status": "Pending"}
-    return f"Reminder set for {medicine} at {time}. Reminder ID: {reminder_id}"
-
-def mark_medication_taken(reminder_id: str):
-    """Mark a medication as taken."""
-    if reminder_id in medications:
-        medications[reminder_id]["status"] = "Taken"
-        return f"Medication {medications[reminder_id]['medicine']} marked as taken."
-    return "Reminder not found."
-
-def suggest_medications(symptom: str):
-    """Suggest medications based on symptoms."""
-    # Query OpenAI GPT for suggestions based on symptom
-    response = openai.Completion.create(
-        model="gpt-3.5-turbo",
-        prompt=f"Suggest medications for a patient with the symptom {symptom}.",
-        max_tokens=150
-    )
-    return response.choices[0].text.strip().split("\n")
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+def get_medication_suggestions(symptom):
+    model_name = "m42-health/med42-70b"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    prompt = f"Suggest medications for a patient with the symptom: {symptom}."
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=150)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)