Overview

View Assistant is a comprehensive solution built into View AI that enables conversational experiences with protected, on-premises data. It provides both simple chat APIs for direct interaction with large language models and retrieval augmented generation (RAG) APIs for context-aware conversations using your data. The platform includes both an easy-to-use built-in conversational AI interface and a standalone deployable conversational AI interface for maximum flexibility and integration options.

View Assistant supports multiple conversation modes, AI-powered content analysis, and seamless integration with your existing data infrastructure for enhanced conversational experiences and AI-powered insights.

Key Features

Conversational AI: Direct interaction with large language models for general conversation and question answering
RAG Capabilities: Retrieval augmented generation for context-aware conversations using your protected data
On-Premises Data: Secure access to your on-premises data with full privacy and control
Multiple Interfaces: Both built-in and standalone deployable conversational AI interfaces
Flexible Integration: Easy integration with existing systems and workflows
AI-Powered Analysis: Advanced content analysis and insights using your data

SDK Setup

JavaScript SDK Setup

Install SDK from npm

npm install view-sdk

Initialize Configuration Sdk

import { ViewAssistantSdk } from "view-sdk";

const assistant = new ViewAssistantSdk(
  "00000000-0000-0000-0000-000000000000", //tenant Id
  "default", //access token
  "http://localhost:8000/" //endpoint
);

Python setup

Install SDK from pip

pip install view-sdk

Initialize Configuration Sdk

import view_sdk
from view_sdk import assistant
from view_sdk.sdk_configuration import Service

sdk = view_sdk.configure(
    access_key="default",
    base_url="localhost",
    tenant_guid="tenant-guid",
    service_ports={Service.ASSISTANT: 8000},
)

C# setup

Install SDK from NuGet

dotnet add package View.Sdk

Initialize Assistant Sdk

using View.Sdk;
using View.Sdk.Assistant;

public static class Example {
    public static async Task Main(string[] args)
    {
        Guid _TenantGuid = Guid.Parse("00000000-0000-0000-0000-000000000000");
        string _AccessKey = "default";
        string _Endpoint = "http://localhost:8000/";
        ViewAssistantSdk sdk = new ViewAssistantSdk(_TenantGuid, _AccessKey, _Endpoint);      
    }
}

Best Practices

When implementing View AI Assistant in your platform, consider the following recommendations for optimal conversational AI experiences, RAG implementation, and assistant functionality:

Data Security: Implement robust data security measures to protect your on-premises data while enabling AI-powered analysis and insights
RAG Configuration: Configure appropriate RAG settings and vector database connections for optimal context-aware conversations and data retrieval
Model Selection: Choose appropriate language models based on your use cases, performance requirements, and content types for optimal conversational experiences
Integration Strategy: Implement effective integration strategies with your existing systems and workflows for seamless assistant functionality
Performance Optimization: Monitor and optimize assistant performance for enhanced user experiences and efficient resource utilization

Next Steps

After successfully implementing View AI Assistant, you can:

Assistant Configuration: Create and manage assistant configurations for specialized chat behaviors and RAG settings
Chat Threads: Implement chat thread management for persistent conversations and context preservation
Model Management: Manage and optimize language models for different assistant scenarios and performance requirements
RAG Implementation: Implement advanced RAG capabilities for enhanced content understanding and context-aware conversations
Integration: Integrate assistant functionality with your applications for enhanced user experiences and AI-powered interactions