Python SDK

​

Installation

pip install --upgrade prometheux_chain

​

Configuration

import prometheux_chain as px
import os

# Set your authentication token
os.environ['PMTX_TOKEN'] = 'YOUR_PMTX_TOKEN'

# Configure the backend URL
px.config.set('JARVISPY_URL', "https://api.prometheux.ai/jarvispy/{organization}/{username}")

​

First API Call

# Create a new ontology
ontology_id = px.save_ontology(ontology_name="my_first_ontology")
print(f"Created ontology: {ontology_id}")

​

Install into Jupyter

1. Create a new notebook with kernel Python and run the following commands in a dedicated cell
2. Clone the repo
   !git clone https://github.com/prometheuxresearch/prometheux_chain.git
   
3. Navigate into the project and install it
   !cd prometheux_chain && pip install -e .
   
4. Copy the project into site-packages to allow importing and using it
   !cd prometheux_chain && cp -r prometheux_chain /opt/app-root/lib/python3.x/site-packages
   
5. Restart the kernel

1. Uninstall the project
   !pip uninstall prometheux_chain -y
   
2. Clone the repo if it is not present
   !git clone https://github.com/prometheuxresearch/prometheux_chain.git
   
   else update it to the latest changes
   !cd prometheux_chain && git pull
   
3. Navigate into the project and install it
   !cd prometheux_chain && pip install -e .
   
4. Remove an existing installation if present
   !rm -r /opt/app-root/lib/python3.x/site-packages/prometheux_chain
   
5. Copy the project into site-packages to allow importing and using it
   !cd prometheux_chain && cp -r prometheux_chain /opt/app-root/lib/python3.x/site-packages
   
6. Restart the kernel

​

Response Format

{
  "data": {},           // Response data (varies by endpoint)
  "message": "string",  // Human-readable message
  "status": "success"   // Status: "success" or "error"
}

​

Streaming responses

import prometheux_chain as px

# Agent chat — each event is a dict with a "type" and "data"
for event in px.agent_chat(ontology_id="ont_123", message="Find all transitive suppliers and run it"):
    if event["type"] == "content":
        print(event["data"]["chunk"], end="")
    elif event["type"] == "done":
        print("\n[done]")

​

API Categories

​

Error Handling

import prometheux_chain as px

try:
    result = px.run_concept(ontology_id="invalid_id", concept_name="test")
except Exception as e:
    print(f"Error: {e}")

​

Requirements

• Python 3.9 or higher
• Install via pip: pip install prometheux_chain