API (no TLS)

Base URL: http://34.100.218.51:8000

Health

GET /health
Returns service status.

• 200 application/json
  • Body: {"status":"ok"}

Example:

curl -sS http://34.100.218.51:8000/health

---

Medical RAG (JSON response)

POST /rag/med/retrieve
Runs the medical RAG pipeline and returns a single JSON response.

Request (application/json)

{
  "query": "What are the symptoms of appendicitis?",
  "session_id": "demo-session-1"
}

Response

• 200 application/json
  • Body:

    { "response": "<ai_answer>" }

• 400 application/json (query must be a meaningful question; at least two words)
  • Body: {"error":"Query must be a meaningful medical question (at least two words)."}
• 500 application/json
  • Body: {"error":"<exception message>"}

Example:

curl -sS -X POST http://34.100.218.51:8000/rag/med/retrieve \
  -H 'Content-Type: application/json' \
  -d '{"query":"What are the symptoms of appendicitis?","session_id":"demo-session-1"}'

---

Medical RAG (streaming response)

POST /rag/med/retrieve/stream
Runs the medical RAG pipeline and streams the answer as plain text.

Request (application/json)

{
  "query": "Explain the difference between type 1 and type 2 diabetes.",
  "session_id": "demo-session-1"
}

Response

• 200 text/plain (streamed)
• 400/500 application/json with the same error shapes as /rag/med/retrieve

Example (streaming):

curl -N -X POST http://34.100.218.51:8000/rag/med/retrieve/stream \
  -H 'Content-Type: application/json' \
  -d '{"query":"Explain the difference between type 1 and type 2 diabetes.","session_id":"demo-session-1"}'

run server

uvicorn main:app --host 0.0.0.0 --port 8000