Agent NoCode

Technology

Built with Python & LangGraph

A2A Protocol v0.3.0 Compliant Server

Built with Python and powered by LangGraph, this NoCode RAG agent enables seamless agent-to-agent communication using the standardized A2A protocol. Implemented with FastAPI and the official A2A SDK, it provides intelligent RAG capabilities, stateful multi-agent workflow orchestration, and comprehensive no-code tool integration for enterprise applications.

Uses LangGraph with a graph-based architecture for defining complex agent interactions and stateful workflows. Workflows are composed of nodes (representing processing steps) and edges (representing state transitions and message flow), enabling sophisticated multi-step reasoning, conditional logic, and human-in-the-loop patterns.

Python LangGraph A2A Protocol LangGraph Docs

API Endpoints & Documentation

Explore the A2A protocol endpoints, agent cards, and LangGraph RAG APIs.

API Documentation Health Status A2A Agent Card

Agent Orchestrator Dashboard

Live monitoring of all subsystems and services. Updates every 30 seconds.

Loading system status...

Quick Start: Chat with Agent

Use this curl command to send a message to the agent via the A2A protocol using JSON-RPC. The agent will process your request and return a complete response including task status, artifacts, and conversation history.

Terminal Command

curl --location 'http://localhost:5002/' \
--header 'Content-Type: application/json' \
--data '{
    "jsonrpc": "2.0",
    "method": "message/send",
    "params": {
        "configuration": {
            "blocking": true
        },
        "message": {
            "role": "user",
            "messageId": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
            "contextId": "12345678-90ab-cdef-1234-567890abcdef",
            "kind": "message",
            "parts": [
                {
                    "kind": "text",
                    "text": "Explain quantum computing in simple terms"
                }
            ]
        }
    },
    "id": 1
}'

Response:

{
    "jsonrpc": "2.0",
    "result": {
        "task": {
            "taskId": "a52b3af8-bbb3-4864-8a48-f68a9334de9e",
            "state": "completed"
        }
    },
    "id": 1
}

Agent Configuration

Configure the NoCode RAG Langraph agent with LLM, RAG database, and authentication settings.

Required Environment Variables

Configure these parameters to enable full agent functionality:

Parameter	Required	Default	Description
Agent Configuration
`AGENT_ID`	Required	`""`	Unique identifier for this agent instance
`AGENT_NAME`	Optional	`NoCode RAG Langraph Agent`	Display name for the agent
`AGENT_DESCRIPTION`	Optional	`A LangGraph-based AI assistant`	Description of agent capabilities
LLM Configuration
`LLM_ENDPOINT`	Required	`""`	Azure OpenAI endpoint URL (e.g., https://your-resource.openai.azure.com/)
`LLM_KEY`	Required	`""`	Azure OpenAI API key for authentication
`LLM_DEPLOYMENT_NAME`	Optional	`gpt-4o`	Azure OpenAI deployment name
`LLM_VERSION`	Optional	`2024-02-01`	Azure OpenAI API version
`LLM_MODEL`	Optional	`gpt-4`	Azure OpenAI model name
Embedding Service Configuration
`EMBEDDING_BASE_URL`	Optional	`""`	Base URL for embedding service
`EMBEDDING_API_KEY`	Optional	`""`	API key for embedding service authentication
`EMBEDDING_PROVIDER`	Optional	`azure`	Embedding provider (azure, openai, etc.)
Database Configuration
`DB_HOST` or `PG_HOST`	Optional	`localhost`	PostgreSQL database host
`DB_PORT` or `PG_PORT`	Optional	`5432`	PostgreSQL database port
`DB_NAME`	Optional	`orchestrator`	PostgreSQL database name
`DB_USERNAME` or `PG_USER`	Optional	`postgres`	PostgreSQL database username
`DB_PASSWORD` or `PG_PASSWORD`	Optional	`""`	PostgreSQL database password
Authentication Configuration
`AUTH_ENABLED`	Optional	`false`	Enable/disable authentication
`AUTH_AUTHORITY`	Optional	`""`	Authentication authority URL (e.g., Azure AD tenant URL)
`AUTH_ISSUER`	Optional	`""`	JWT token issuer URL for validation
`AUTH_TENANT_ID`	Optional	`""`	Azure AD tenant identifier
`AUTH_CLIENT_ID`	Optional	`""`	Application (client) ID registered in Azure AD
`AUTH_REDIRECT_URI`	Optional	`""`	OAuth redirect URI for authentication flow
`AUTH_LOGIN_SCOPES`	Optional	`""`	Comma-separated OAuth scopes for user login
`AUTH_API_SCOPES`	Optional	`""`	Comma-separated OAuth scopes for API access
`AUTH_VALIDATE_ISSUER`	Optional	`true`	Validate JWT issuer claim during token verification
`AUTH_VALIDATE_AUDIENCE`	Optional	`true`	Validate JWT audience claim during token verification
`AUTH_VALIDATE_SIGNING_KEY`	Optional	`true`	Validate JWT signature using signing keys
`AUTH_VALIDATE_LIFETIME`	Optional	`true`	Validate JWT expiration and not-before claims
`AUTH_LIFETIME_SKEW`	Optional	`5`	Allowed clock skew in minutes for lifetime validation
Server Configuration
`PORT`	Optional	`8080`	Server port (5015 for local development)
`HOST`	Optional	`0.0.0.0`	Server host address
`ENVIRONMENT`	Optional	`development`	Application environment (development, production)
`DEBUG`	Optional	`false`	Enable debug mode

Example Configuration

.env file

########################################
# Agent Configuration
########################################
AGENT_ID=simple-ag
AGENT_NAME=LowCodeAgent
AGENT_DESCRIPTION=A low-code AI agent for rapid application development.
AGENT_ICON_URL=
AGENT_DOCUMENTATION_URL=
AGENT_PROVIDER_ORG=EY
AGENT_PROVIDER_URL=https://ey.com

########################################
# LLM configuration
########################################
LLM_PROVIDER=azure_openai
LLM_ENDPOINT=https://your-openai-instance.openai.azure.com/
LLM_MODEL=gpt-4o
LLM_KEY=your-api-key-here
LLM_API_VERSION=2025-01-01-preview
LLM_SYSTEM_PROMPT=You are a helpful, tool-using assistant.
LLM_TEMPERATURE=0.0
LLM_MAX_TOKENS=1000

########################################
# Embeddings configuration (optional)
########################################
EMBED_PROVIDER=azure_openai
EMBED_MODEL=text-embedding-ada-002
EMBED_API_VERSION=2023-05-15

########################################
# Postgres (pgvector) configuration
########################################
PGHOST=localhost
PGPORT=5432
POSTGRES_USER=postgres
POSTGRES_PASSWORD=postgres
Platform_DB=art-context

########################################
# Logging
########################################
LOG_LEVEL=INFO

########################################
# Context Configuration
########################################
CONTEXTS="[]"

########################################
# Authentication Configuration (Optional)
########################################
AUTH_ENABLED=false
AUTH_AUTHORITY=https://login.microsoftonline.com/your-tenant-id
AUTH_ISSUER=https://sts.windows.net/your-tenant-id/
AUTH_TENANT_ID=your-tenant-id
AUTH_CLIENT_ID=your-client-id
AUTH_REDIRECT_URI=http://localhost:3000
AUTH_LOGIN_SCOPES=User.Read
AUTH_API_SCOPES=api://your-app-id/.default
AUTH_VALIDATE_ISSUER=true
AUTH_VALIDATE_AUDIENCE=false
AUTH_VALIDATE_SIGNING_KEY=false
AUTH_VALIDATE_LIFETIME=true
AUTH_LIFETIME_SKEW=300

########################################
# MCP URLs
########################################
TOOL_SERVERS='["http://localhost:5010/mcp"]'

Sync Parameters to Fabric Developer Workflow Application

Automatically sync your local environment variables to Fabric Developer Workflow Application using the make params command. This eliminates manual configuration in the Application Dashboard.

Prerequisites

Install Fabric Developer Journey CLI from Null Platform:
```
npm install -g @nullplatform/cli
```
Get your API Key:
Go to your App Dashboard from Fabric Workspace → Click user profile icon → Click "Copy personal access token"
Export the API Key:
```
export NP_TOKEN=<your-token>
```
Get your App NRN (Null Resource Name):
1. Go to your Application Dashboard
2. Click the NRN button to copy your application's NRN
3. You'll use this NRN when running the make params command
```
# Format: organization=ID:account=ID:namespace=ID:application=ID
# Example: organization=1234567890:account=9876543210:namespace=1122334455:application=5544332211
```

Run the Command

Once prerequisites are met, run this command in your terminal: