Chat API

The Chat API provides AI-powered Vadalog code assistance and answers questions about the platform. It is available at https://chat-docs.prometheux.ai and can be integrated into your applications.

Overview

The Chat API provides:

Vadalog code generation tailored to your specific question
Syntax assistance and debugging help
Documentation search integration via Algolia
Context-aware responses based on Prometheux documentation
Grammar-compliant code following Vadalog best practices
Intelligent examples — simple questions get focused snippets, complex questions get full programs

Endpoints

`/api/docsChat` (Streaming)

Optimized for chat interfaces and streaming responses.

URL: https://chat-docs.prometheux.ai/api/docsChat
Method: POST
Content-Type: application/json
Response: Streaming text (AI SDK format)

Request Format:

{
  "messages": [
    {
      "role": "user",
      "content": "Show me a PostgreSQL connection example"
    }
  ]
}

Response Format: Streaming text response in AI SDK format:

"Below"
" is"
" a"
" complete"
" Vadalog"
" example..."

Example Usage:

JavaScript
Python
cURL

const response = await fetch('https://chat-docs.prometheux.ai/api/docsChat', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    messages: [
      { role: 'user', content: 'How do I connect to Neo4j?' }
    ]
  })
});

// Handle streaming response
const reader = response.body.getReader();
const decoder = new TextDecoder();
let result = '';

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  const chunk = decoder.decode(value, { stream: true });
  // Parse AI SDK format: 0:"text"
  const lines = chunk.split('\n');
  for (const line of lines) {
    if (line.startsWith('0:"') && line.endsWith('"')) {
      result += line.slice(3, -1); // Extract text content
    }
  }
}

console.log(result); // Complete Vadalog code example

import requests
import re

url = "https://chat-docs.prometheux.ai/api/docsChat"
payload = {
    "messages": [
        {"role": "user", "content": "Show me aggregation examples"}
    ]
}

response = requests.post(url, json=payload, stream=True)

result = ""
for chunk in response.iter_content(chunk_size=1024, decode_unicode=True):
    if chunk:
        # Parse AI SDK format: 0:"text"
        lines = chunk.split('\n')
        for line in lines:
            if line.startswith('0:"') and line.endswith('"'):
                result += line[3:-1]  # Extract text content

print(result)  # Complete Vadalog code

curl -X POST https://chat-docs.prometheux.ai/api/docsChat \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "How do I use math functions?"}
    ]
  }'

`/api/vadalog` (Standard JSON)

Standard REST API for programmatic integration.

URL: https://chat-docs.prometheux.ai/api/vadalog
Method: POST
Content-Type: application/json
Response: Standard JSON

Request Format:

{
  "query": "Show me a PostgreSQL connection example",
  "context": "database connection",
  "include_docs": true
}

Response Format:

{
  "response": "Below is a complete Vadalog example...",
  "code_examples": [
    {
      "language": "vadalog",
      "code": "@bind(\"customer\", \"postgresql host=localhost port=5432 user=myuser password=mypass\", \"mydb\", \"customer\").\n@model(\"customer\", \"['id:int', 'name:string', 'age:int']\").\n@output(\"result\").",
      "description": "PostgreSQL connection with customer data processing"
    }
  ],
  "relevant_docs": [
    {
      "title": "Connecting to Databases",
      "url": "https://api.prometheux.ai/docs/learn/vadalog/data-sources",
      "excerpt": "PostgreSQL database connections..."
    }
  ],
  "metadata": {
    "provider": "Azure OpenAI",
    "model": "gpt-4o",
    "tokens_used": 1247,
    "search_results": 3
  }
}

Example Usage:

JavaScript
Python
cURL

const response = await fetch('https://chat-docs.prometheux.ai/api/vadalog', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    query: 'How do I use aggregations in Vadalog?',
    include_docs: true
  })
});

const data = await response.json();
console.log(data.response);        // Text response
console.log(data.code_examples);   // Extracted code blocks
console.log(data.relevant_docs);   // Related documentation

import requests

url = "https://chat-docs.prometheux.ai/api/vadalog"
payload = {
    "query": "Show me CSV file processing",
    "context": "data integration",
    "include_docs": True
}

response = requests.post(url, json=payload)
data = response.json()

print(f"Response: {data['response']}")
print(f"Code examples: {len(data['code_examples'])}")
print(f"Related docs: {len(data['relevant_docs'])}")

curl -X POST https://chat-docs.prometheux.ai/api/vadalog \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Show me CSV file processing",
    "context": "data integration", 
    "include_docs": true
  }'

Features

Vadalog Code Generation

Focused, relevant code examples matched to your question
Proper syntax with appropriate annotations (only when needed)
Database connection examples for data source questions
Full data processing workflows for integration scenarios
Simple syntax examples for concept/logic questions
Grammar-compliant code

Documentation Integration (RAG)

Uses Retrieval Augmented Generation (RAG) via Algolia
Dynamically searches documentation based on your query
Retrieves top 3 most relevant sections
Always up-to-date — automatically includes new documentation
No manual prompt updates needed when docs change

AI-Powered Assistance

Powered by Azure OpenAI (gpt-4o)
Context-aware responses
Iterative conversation support
Syntax error prevention

Response Types

Endpoint	Best For	Format	Use Case
`/api/docsChat`	Chat interfaces, real-time applications	AI SDK compatible streaming	Frontend chat components
`/api/vadalog`	Programmatic integration, APIs, automation	Standard JSON with structured data	Backend services, integrations

Rate Limits

Limit	Value
Requests per minute	180
Tokens per minute	30,000,000
Response token limit	1,500
Concurrent requests	Supported

Error Handling

Error Response Format:

{
  "error": "AI assistant not available",
  "message": "Service temporarily unavailable",
  "status": 503,
  "timestamp": "2024-01-15T10:30:00Z"
}

Common Error Codes:

Code	Description	Solution
400	Bad Request	Check request format
429	Rate Limited	Reduce request frequency
503	Service Unavailable	Retry after delay
500	Internal Error	Contact support

Best Practices

Use conversation context: Include previous messages for better responses
Be specific: Ask detailed questions about Vadalog syntax
Match question complexity:
- For syntax questions: “How do I use the and() function?”
- For complete programs: “Show me a complete PostgreSQL connection example”
Handle streaming: Implement proper streaming for real-time responses
Error handling: Implement retry logic for rate limits

Examples

Database Connections

JavaScript
Python
cURL

const response = await fetch('https://chat-docs.prometheux.ai/api/docsChat', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    messages: [
      { role: 'user', content: 'How do I connect to PostgreSQL with authentication?' }
    ]
  })
});

// Parse streaming response
const reader = response.body.getReader();
const decoder = new TextDecoder();
let vadalogCode = '';

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  const chunk = decoder.decode(value, { stream: true });
  const lines = chunk.split('\n');
  for (const line of lines) {
    if (line.startsWith('0:"') && line.endsWith('"')) {
      vadalogCode += line.slice(3, -1);
    }
  }
}

console.log(vadalogCode); // Complete @bind example with connection parameters

import requests

url = "https://chat-docs.prometheux.ai/api/docsChat"
payload = {
    "messages": [
        {"role": "user", "content": "How do I connect to PostgreSQL with authentication?"}
    ]
}

response = requests.post(url, json=payload, stream=True)

vadalog_code = ""
for chunk in response.iter_content(chunk_size=1024, decode_unicode=True):
    if chunk:
        lines = chunk.split('\n')
        for line in lines:
            if line.startswith('0:"') and line.endswith('"'):
                vadalog_code += line[3:-1]

print(vadalog_code)  # Complete @bind example with connection parameters

curl -X POST https://chat-docs.prometheux.ai/api/docsChat \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "How do I connect to PostgreSQL with authentication?"}
    ]
  }'

Data Processing with Aggregations

JavaScript
Python
cURL

const response = await fetch('https://chat-docs.prometheux.ai/api/vadalog', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    query: 'Show me aggregation examples with grouping',
    context: 'data analysis',
    include_docs: true
  })
});

const data = await response.json();
console.log('Response:', data.response);
console.log('Code Examples:', data.code_examples);
data.code_examples.forEach(example => {
  console.log(`\n--- ${example.description} ---`);
  console.log(example.code);
});

import requests

url = "https://chat-docs.prometheux.ai/api/vadalog"
payload = {
    "query": "Show me aggregation examples with grouping",
    "context": "data analysis",
    "include_docs": True
}

response = requests.post(url, json=payload)
data = response.json()

print(f"Response: {data['response']}")
for example in data['code_examples']:
    print(f"\n--- {example['description']} ---")
    print(example['code'])

curl -X POST https://chat-docs.prometheux.ai/api/vadalog \
  -H "Content-Type: application/json" \
  -d '{
    "query": "Show me aggregation examples with grouping",
    "context": "data analysis",
    "include_docs": true
  }' | jq '.code_examples[].code'

Advanced AI Features

JavaScript
Python
cURL

const response = await fetch('https://chat-docs.prometheux.ai/api/docsChat', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    messages: [
      { role: 'user', content: 'How do I use LLM functions and embeddings in Vadalog?' }
    ]
  })
});

// Handle conversation context
const conversationHistory = [
  { role: 'user', content: 'How do I use LLM functions and embeddings in Vadalog?' }
];

// Parse response and continue conversation
const reader = response.body.getReader();
const decoder = new TextDecoder();
let assistantResponse = '';

while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  
  const chunk = decoder.decode(value, { stream: true });
  const lines = chunk.split('\n');
  for (const line of lines) {
    if (line.startsWith('0:"') && line.endsWith('"')) {
      assistantResponse += line.slice(3, -1);
    }
  }
}

// Add to conversation history for follow-up questions
conversationHistory.push({ role: 'assistant', content: assistantResponse });
console.log('AI Functions Example:', assistantResponse);

import requests

url = "https://chat-docs.prometheux.ai/api/docsChat"

# Start conversation
conversation = [
    {"role": "user", "content": "How do I use LLM functions and embeddings in Vadalog?"}
]

response = requests.post(url, json={"messages": conversation}, stream=True)

assistant_response = ""
for chunk in response.iter_content(chunk_size=1024, decode_unicode=True):
    if chunk:
        lines = chunk.split('\n')
        for line in lines:
            if line.startswith('0:"') and line.endswith('"'):
                assistant_response += line[3:-1]

# Add to conversation for follow-up
conversation.append({"role": "assistant", "content": assistant_response})
print("AI Functions Example:", assistant_response)

# Follow-up question
conversation.append({"role": "user", "content": "Can you show me a similarity analysis example?"})
follow_up = requests.post(url, json={"messages": conversation}, stream=True)
# Process follow-up response...

# Initial request
curl -X POST https://chat-docs.prometheux.ai/api/docsChat \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "How do I use LLM functions and embeddings in Vadalog?"}
    ]
  }'

# Follow-up with conversation context
curl -X POST https://chat-docs.prometheux.ai/api/docsChat \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {"role": "user", "content": "How do I use LLM functions and embeddings in Vadalog?"},
      {"role": "assistant", "content": "Previous response..."},
      {"role": "user", "content": "Can you show me a similarity analysis example?"}
    ]
  }'

Integration

Frontend Integration

Use the streaming endpoint with AI SDK components for real-time chat interfaces.

Backend Integration

Use the JSON endpoint for programmatic access, automation, and service integration.

Documentation Bot

Embed the chat functionality directly in your documentation using the provided components. The Chat API provides comprehensive Vadalog assistance powered by AI and integrated with the complete Prometheux documentation.

Introduction

Get Started

Platform

Integrations

Examples

Vadalog Reference

Resources

Overview

Endpoints

`/api/docsChat` (Streaming)

`/api/vadalog` (Standard JSON)

Features

Response Types

Rate Limits

Error Handling

Best Practices

Examples

Database Connections

Data Processing with Aggregations

Advanced AI Features

Integration

Frontend Integration

Backend Integration

Documentation Bot

​Overview

​Endpoints

​/api/docsChat (Streaming)

​/api/vadalog (Standard JSON)

​Features

​Response Types

​Rate Limits

​Error Handling

​Best Practices

​Examples

​Database Connections

​Data Processing with Aggregations

​Advanced AI Features

​Integration

​Frontend Integration

​Backend Integration

​Documentation Bot

Overview

Endpoints

`/api/docsChat` (Streaming)

`/api/vadalog` (Standard JSON)

Features

Response Types

Rate Limits

Error Handling

Best Practices

Examples

Database Connections

Data Processing with Aggregations

Advanced AI Features

Integration

Frontend Integration

Backend Integration

Documentation Bot