Back to packageRELEASE DETAILS

0.1.0a0

PyPI

aicliniq

Open-source AI agent framework for healthcare and life sciences

Published4 Oct 2026

Direct dependencies63

Transitive dependenciesNot calculated

README

Version 0.1.0a0 documentation

AICliniq

The open-source Python framework for building healthcare AI applications.
Like Django is to web apps, like HuggingFace is to ML models, AICliniq is to clinical AI.

Created and maintained by Satheesh Kola.

Install the framework. Use pre-built clinical agents. Build your healthcare AI product in days.

What is AICliniq?

AICliniq is a 5-layer framework for healthcare AI:

Layer 1: Core Framework      → pip install aicliniq
Layer 2: Domain Packs         → pip install aicliniq[clinical]
Layer 3: Server               → aicliniq serve
Layer 4: Dashboard            → aicliniq ui
Layer 5: CLI Scaffolding      → aicliniq new my-app

17 clinical domains · 39 model providers · LLM Council (multi-model consensus) · MCP Server · HIPAA audit trail · FHIR R4 · 4 memory types · 6 reasoning patterns · 7 safety layers

New to AICliniq? Read ARCHITECTURE.md to understand the 5-layer framework model.

Quick Start — 5 Levels

Level 1: Beginner (3 lines, 5 minutes)

pip install aicliniq[groq]
export GROQ_API_KEY=gsk_...

from aicliniq import quick
import asyncio

# Clinical scribe — transcript to SOAP note
note = asyncio.run(quick.scribe("Patient is a 45yo male with chest pain..."))
print(note.soap)

# Triage — symptoms to urgency classification
result = asyncio.run(quick.triage("chest pain, diaphoresis", age=62))
print(f"{result.urgency} ({result.score}/10)")

# Clinical Q&A — evidence-based answers
answer = asyncio.run(quick.ask("First-line treatment for HFrEF?"))
print(answer.answer)

Level 2: Builder (use pre-built domain agents)

pip install aicliniq[clinical-radiology]

from aicliniq.domains.clinical.radiology import RadiologyReportAgent
from aicliniq.providers.vlm.medgemma import MedGemmaProvider

agent = RadiologyReportAgent(vlm=MedGemmaProvider())
report = await agent.run(input=dicom_image)
print(report.findings)

Level 3: Customizer (extend for your hospital)

from aicliniq.domains.clinical.radiology import RadiologyReportAgent

class CityGeneralRadiologyAgent(RadiologyReportAgent):
    """Customized for City General Hospital"""
    REPORT_TEMPLATE = CITY_GENERAL_TEMPLATE
    
    async def on_critical_finding(self, finding):
        await notify_slack(finding)

Level 4: Product Builder (scaffold full app)

aicliniq new my-radiology-saas --template radiology
cd my-radiology-saas
docker compose up -d
# Full FastAPI + React + Postgres app running

Level 5: Enterprise (self-hosted platform)

git clone https://github.com/kolasatheesh/aicliniq
cd aicliniq
docker compose up -d
# Postgres (pgvector) + FastAPI server + React console, all on your own infrastructure

I Want To...

Goal	Start Here	Time
Try it in 3 lines	`quick.py`	5 min
Build a radiology tool	`RadiologyReportAgent`	1 hour
Build a pharma trainer	`MedRepTrainingAgent`	2 hours
Build a patient portal	`PatientJourneyOrchestrator`	1 day
Build something custom	`BaseAgent` + `AgentGraph`	2 days
Deploy for a hospital	Docker + Server Layer	1 week

What's Inside

17 Clinical Domains (34+ Agents)

Domain	Agents
Cardiology	ECG Interpreter, Cardiac Risk, Zodiac Pipeline
Emergency/ICU	ED Triage, ICU Supervisor, Sepsis Management Graph
Surgery	Surgical Scribe, Pre-Op Assessment
Oncology	Tumor Board, Trial Matching
Radiology	Radiology Scribe, Imaging Triage
Primary Care	Intake, Follow-Up, Screening
Drug Discovery	Target ID, Molecule Design, ADMET, Repurposing
Pathology	Pathology Scribe, Biopsy Triage
Genomics	Variant Interpretation, Pharmacogenomics
+ 8 more	Pharmacovigilance, Digital Health, Clinical Trials, Operations, Population Health, Med Education, Compliance, Pharma Ops

39 Model Providers

LLM (24): Groq, OpenAI, Anthropic, Gemini, DeepSeek, xAI/Grok, Cohere, Mistral, Fireworks, Together, HuggingFace, LiteLLM, Ollama, + 11 more VLM (3): MedGemma 1.5, PathChat+, BiomedCLIP Genomics (2): ESM-2 (proteins), Enformer (gene expression) Chemistry (2): ChemBERTa, RDKit Speech (6): Whisper, AssemblyAI, ElevenLabs, Google STT, Azure Speech, Kokoro

Production Platform

Layer	What it does
LLM Council	Multi-model consensus with 4 modes, PHI-aware routing, confidence scoring
Observability	Langfuse + OpenTelemetry tracing, cost tracking, drift detection
Safety (7 layers)	PHI masking, AES-256 encryption, sandboxed execution, HITL, scope constraints, hallucination guard, audit trail
Explainability	SHAP, narrative explanations, attention visualization
Memory (4 types)	Working, episodic (learns from feedback), semantic (pgvector), procedural (clinical playbooks)
Reasoning (6 patterns)	ReAct, CoT, Plan-and-Execute, ReWOO, Swarm, Council
Protocols	MCP Server (plug into Claude/Cursor), A2A (cross-framework agents)
Federated Learning	Train across hospitals without sharing data (Flower + Opacus)
Voice AI	Ambient scribe, conversational voice agent
Fine-Tuning	LoRA/QLoRA trainer, data curator, model registry
Interoperability	SMART on FHIR, HL7 v2, CDA, SNOMED/LOINC/ICD-10 terminology
Benchmarks	MedAgentBench (Stanford), AgentDS Healthcare

Full-Stack Application

FastAPI server — 11 API routers (50+ endpoints), JWT auth, multi-tenant, SSE streaming
React console — 28 pages covering every clinical domain + LLM Council
PostgreSQL + pgvector — semantic search and long-term memory
Docker Compose — one-command deployment

CLI

aicliniq serve          # Start API server
aicliniq ui             # Start React console
aicliniq agents         # List all 34+ agents
aicliniq domains        # List all 17 domains
aicliniq init           # Generate starter project
aicliniq sandbox        # Explore synthetic clinical data
aicliniq learn          # Interactive tutorials
aicliniq run scribe -i '{"transcript": "..."}'  # Run agent from CLI
aicliniq validate       # Check configuration

v0.1.0-alpha Status

Covered by Tests (1,800+ automated tests, LLM calls mocked)

All template agents (Scribe, Triage, RAG-QA, Diagnostic Dialogue)
LLM Council (25 tests: consensus, PHI routing, agreement scoring)
Groq and OpenAI LLM providers
PHI Masker, AES-256 encryption, sandbox, hallucination guard
FHIR R4 resources (all 11 types), HL7 v2 parser, terminology service
Observability (tracing, cost tracking, drift detection)
Full server test suite (auth, agents, audit, compliance, multitenancy, FHIR)

Scaffolded (Contributions Welcome)

22 of 39 providers (stubs with clear error messages — see PROVIDERS.md)
Federated learning, voice AI, fine-tuning (architecture ready)

Documentation

Full documentation at docs.aicliniq.org: concepts, platform layers, guides, deployment, and persona-specific onboarding.

For the complete usage guide including how to run, build, package, and deploy: HOW_TO_USE.md

Contributing

See CONTRIBUTING.md. We especially welcome:

New clinical domain packs
Provider implementations
Evaluation benchmarks
Translations (10 languages supported)

License

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 260

Native requirements

63 direct targetsNot calculated transitive count

Package / target	Requirement	Relationship
anyio Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`anyio<5,>=4.3`	runtime
httpx Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`httpx<1,>=0.27`	runtime
pydantic-settings Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pydantic-settings<3,>=2.2`	runtime
pydantic Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pydantic<3,>=2.5`	runtime
typing-extensions Environment { "extras": "", "marker": null, "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`typing-extensions>=4.10`	runtime
accelerate Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`accelerate>=0.33; extra == "all"`	runtime
alembic Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`alembic<2,>=1.13; extra == "all"`	runtime
anthropic Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`anthropic>=0.50; extra == "all"`	runtime
asyncpg Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`asyncpg>=0.29; extra == "all"`	runtime
bitsandbytes Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`bitsandbytes>=0.43; extra == "all"`	runtime
cookiecutter Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cookiecutter>=2.5; extra == "all"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "all"`	runtime
datasets Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`datasets>=2.18; extra == "all"`	runtime
fair-esm Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`fair-esm>=0.4; extra == "all"`	runtime
fastapi Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`fastapi<1,>=0.111; extra == "all"`	runtime
faster-whisper Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`faster-whisper>=1.0; extra == "all"`	runtime
google-genai Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`google-genai>=1.0; extra == "all"`	runtime
groq Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "all"`	runtime
langfuse Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`langfuse>=2.0; extra == "all"`	runtime
lxml Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`lxml>=5.0; extra == "all"`	runtime
matplotlib Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`matplotlib>=3.8; extra == "all"`	runtime
nltk Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`nltk>=3.8; extra == "all"`	runtime
open-clip-torch Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`open-clip-torch>=2.23; extra == "all"`	runtime
openai Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`openai>=1.35; extra == "all"`	runtime
opentelemetry-api Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`opentelemetry-api>=1.20; extra == "all"`	runtime
opentelemetry-sdk Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`opentelemetry-sdk>=1.20; extra == "all"`	runtime
passlib Environment { "extras": "bcrypt", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`passlib[bcrypt]>=1.7; extra == "all"`	runtime
peft Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`peft>=0.12; extra == "all"`	runtime
pgvector Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pgvector>=0.3; extra == "all"`	runtime
pillow Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pillow>=10.0; extra == "all"`	runtime
python-jose Environment { "extras": "cryptography", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`python-jose[cryptography]>=3.3; extra == "all"`	runtime
python-multipart Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`python-multipart>=0.0.9; extra == "all"`	runtime
rdkit-pypi Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`rdkit-pypi; extra == "all"`	runtime
rich Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`rich>=13.0; extra == "all"`	runtime
rouge-score Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`rouge-score>=0.1.2; extra == "all"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "all"`	runtime
shap Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`shap>=0.45; extra == "all"`	runtime
slowapi Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`slowapi>=0.1.9; extra == "all"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "all"`	runtime
sqlalchemy Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sqlalchemy<3,>=2.0; extra == "all"`	runtime
torch Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.2; extra == "all"`	runtime
torch Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.3; extra == "all"`	runtime
transformers Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`transformers>=4.35; extra == "all"`	runtime
transformers Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`transformers>=4.44; extra == "all"`	runtime
typer Environment { "extras": "", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`typer>=0.9; extra == "all"`	runtime
uvicorn Environment { "extras": "standard", "marker": "extra == \"all\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`uvicorn[standard]>=0.30; extra == "all"`	runtime
anthropic Environment { "extras": "", "marker": "extra == \"anthropic\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`anthropic>=0.50; extra == "anthropic"`	runtime
docker Environment { "extras": "", "marker": "extra == \"bench\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`docker>=7.0; extra == "bench"`	runtime
torch Environment { "extras": "", "marker": "extra == \"biogpt\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.2; extra == "biogpt"`	runtime
transformers Environment { "extras": "", "marker": "extra == \"biogpt\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`transformers>=4.35; extra == "biogpt"`	runtime
open-clip-torch Environment { "extras": "", "marker": "extra == \"biomedclip\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`open-clip-torch>=2.23; extra == "biomedclip"`	runtime
rdkit-pypi Environment { "extras": "", "marker": "extra == \"chem\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`rdkit-pypi; extra == "chem"`	runtime
cookiecutter Environment { "extras": "", "marker": "extra == \"cli\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cookiecutter>=2.5; extra == "cli"`	runtime
rich Environment { "extras": "", "marker": "extra == \"cli\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`rich>=13.0; extra == "cli"`	runtime
typer Environment { "extras": "", "marker": "extra == \"cli\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`typer>=0.9; extra == "cli"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-cardiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-cardiology"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-cardiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-cardiology"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-cardiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-cardiology"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-cardiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-cardiology"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-emergency-icu\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-emergency-icu"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-emergency-icu\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-emergency-icu"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-emergency-icu\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-emergency-icu"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-emergency-icu\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-emergency-icu"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-genomics"`	runtime
fair-esm Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`fair-esm>=0.4; extra == "clinical-genomics"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-genomics"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-genomics"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-genomics"`	runtime
torch Environment { "extras": "", "marker": "extra == \"clinical-genomics\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.2; extra == "clinical-genomics"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-oncology"`	runtime
fair-esm Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`fair-esm>=0.4; extra == "clinical-oncology"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-oncology"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-oncology"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-oncology"`	runtime
torch Environment { "extras": "", "marker": "extra == \"clinical-oncology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.2; extra == "clinical-oncology"`	runtime
accelerate Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`accelerate>=0.33; extra == "clinical-pathology"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-pathology"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-pathology"`	runtime
pillow Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pillow>=10.0; extra == "clinical-pathology"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-pathology"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-pathology"`	runtime
timm Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`timm>=1.0; extra == "clinical-pathology"`	runtime
torch Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.3; extra == "clinical-pathology"`	runtime
transformers Environment { "extras": "", "marker": "extra == \"clinical-pathology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`transformers>=4.44; extra == "clinical-pathology"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-primary-care\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-primary-care"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-primary-care\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-primary-care"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-primary-care\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-primary-care"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-primary-care\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-primary-care"`	runtime
accelerate Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`accelerate>=0.33; extra == "clinical-radiology"`	runtime
cryptography Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`cryptography>=42.0; extra == "clinical-radiology"`	runtime
groq Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`groq>=0.9; extra == "clinical-radiology"`	runtime
pillow Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`pillow>=10.0; extra == "clinical-radiology"`	runtime
sentence-transformers Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`sentence-transformers>=3.0; extra == "clinical-radiology"`	runtime
spacy Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`spacy>=3.7; extra == "clinical-radiology"`	runtime
torch Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`torch>=2.3; extra == "clinical-radiology"`	runtime
transformers Environment { "extras": "", "marker": "extra == \"clinical-radiology\"", "requires_python": ">=3.11", "evaluation": "NOT_EVALUATED" }	`transformers>=4.44; extra == "clinical-radiology"`	runtime