ella-sdk 1.2.5

Medical Triage & Clinical RAG Engine

⭐ If Ella's RAG-based medical triage architecture gave you ideas — a star helps other health-AI builders find it. Takes 2 seconds.

ELLA

Medical Triage & Clinical RAG Engine

Ella is a production-grade Retrieval-Augmented Generation (RAG) system purpose-built for medical triage. She ingests 90,000+ clinical text chunks, embeds them via NVIDIA NIM, stores them in Pinecone, and retrieves context-grounded answers through a multi-stage pipeline — eliminating hallucinations in healthcare workflows.

Install • Quick Start • Architecture • Live Demo • Benchmark

---

Install

pip install ella-sdk

---

Quick Start

from ella_medical import Ella

client = Ella()
response = client.query("What are the symptoms of a heart attack?")

response.show()

Output:

------------------------------------------------------------
 [^] TRIAGE P2
------------------------------------------------------------

  Chest pain, shortness of breath, and fatigue are common...

  *  Chest pain or discomfort
  *  Numbness or tingling in the arms, back, neck, jaw
  *  Shortness of breath

------------------------------------------------------------
 Sources
------------------------------------------------------------
  [Source: Medical Handbook.pdf]: ...
------------------------------------------------------------

---

Usage

Basic Query

from ella_medical import Ella

client = Ella()
response = client.query("What are the symptoms of a heart attack?")

print(response.intent)              # "TRIAGE"
print(response.priority)            # "P2"
print(response.response)            # Ella's clinical response
print(response.retrieved_context)   # Retrieved medical documents

Pretty Print

from ella_medical import Ella

client = Ella()
response = client.query("What are the symptoms of a heart attack?")
response.show()  # Formatted output with intent badge, response, and sources

Context Manager

from ella_medical import Ella

with Ella() as client:
    response = client.query("What are the symptoms of diabetes?")
    response.show()

Response Object

@dataclass
class QueryResponse:
    intent: str            # EMERGENCY | TRIAGE | BOOKING | GENERAL_INFO | CLOSING
    priority: str          # P1 | P2 | P3
    thought_process: str   # Router's reasoning
    justification: str     # Clinical justification
    response: str          # Ella's response
    retrieved_context: str # Retrieved medical documents

---

Live Demo

→ Launch Ella on HuggingFace Spaces

---

Architecture

                     ┌─────────────────────────────────────────────────────────────────────┐
                     │                        USER'S INPUT                                 │
                     └────────────────────────────┬────────────────────────────────────────┘
                                                  │
                                                  ▼
                     ┌─────────────────────────────────────────────────────────────────────┐
                     │  INTENT ROUTER (Groq llama-3.1-8b-instant + Pydantic Schema)        │
                     │  Classifies: EMERGENCY │ TRIAGE │ BOOKING │ GENERAL_INFO │ CLOSING  │
                     └────────────────────────────┬────────────────────────────────────────┘
                                                  │
                                   ┌──────────────┼──────────────┐
                                   ▼              ▼              ▼
                           ┌──────────┐  ┌──────────────┐  ┌──────────┐
                           │ EMERGENCY│  │    TRIAGE    │  │ BOOKING  │
                           │ GUARDRAIL│  │  RAG SEARCH  │  │ HANDLER  │
                           └──────────┘  └──────┬───────┘  └──────────┘
                                                │
                                                ▼
                     ┌─────────────────────────────────────────────────────────────────────┐
                     │                    RETRIEVAL PIPELINE                               │
                     │                                                                     │
                     │  ┌─────────────┐   ┌─────────────┐   ┌─────────────────────────┐    │
                     │  │  NVIDIA NIM │   │   BM25      │   │  CrossEncoder Reranker  │    │
                     │  │  Embeddings │ + │  Keyword    │ → │  ms-marco-MiniLM-L-6    │    │
                     │  │  (Semantic) │   │  Matching   │   │  (Top-10 → Top-3)       │    │
                     │  └──────┬──────┘   └──────┬──────┘   └───────────┬─────────────┘    │
                     │         │                 │                      │                  │
                     │         ▼                 ▼                      ▼                  │
                     │  ┌─────────────────────────────────────────────────────────────┐    │
                     │  │              PINECONE VECTOR DATABASE                       │    │
                     │  │         90,306 vectors • cosine • 1024 dimensions           │    │
                     │  └─────────────────────────────────────────────────────────────┘    │
                     └────────────────────────────┬────────────────────────────────────────┘
                                                  │
                                                  ▼
                     ┌─────────────────────────────────────────────────────────────────────┐
                     │  SYNTHESIS (Groq llama-3.1-8b-instant)                              │
                     │  Grounded response + clinical justification + source attribution    │
                     └────────────────────────────┬────────────────────────────────────────┘
                                                  │
                                                  ▼
                     ┌─────────────────────────────────────────────────────────────────────┐
                     │                       PATIENT RESPONSE                              │
                     └─────────────────────────────────────────────────────────────────────┘

---

Benchmark

Metric	Value
Intent Accuracy	96.0%
Avg Latency	9.26s
Avg Retrieval Score	0.92
Records in DB	90,306

Intent	Correct	Total	Accuracy
EMERGENCY	10	10	100%
TRIAGE	18	20	90%
BOOKING	10	10	100%
GENERAL_INFO	5	5	100%
CLOSING	5	5	100%

---

Tech Stack

Layer	Technology	Purpose
SDK	ella-sdk (PyPI)	Python client
Embeddings	NVIDIA NIM (nv-embedqa-e5-v5)	1024-dim semantic vectors
Vector DB	Pinecone (Serverless, AWS)	Cosine similarity search
LLM	Groq (llama-3.1-8b-instant)	Intent classification + response generation
Reranker	CrossEncoder (ms-marco-MiniLM-L-6-v2)	Precision reranking
Orchestration	LangChain + LangGraph	Agent pipeline
Validation	Pydantic	Schema-validated outputs

---

License

MIT License — see LICENSE for details.

---

Built with ❤️ for healthcare AI