Ragchat FAQs

Question 1

What LLM and embedding providers are compatible with Ragchat?

Accepted Answer

Ragchat offers flexible multi-provider support. For Large Language Models (LLMs), it integrates with OpenAI, Anthropic, and Google Gemini. For embeddings (used in vector search), it supports OpenAI, Google Gemini, and AWS Bedrock, allowing you to choose your preferred backend.

Question 2

What are the key advantages of Ragchat's local, zero-cloud architecture?

Accepted Answer

The local, zero-cloud architecture ensures unparalleled data privacy and security, as all your content and chat interactions remain within your environment without touching external cloud services. It also provides lower latency, greater control over your data, and eliminates reliance on third-party infrastructure for core AI operations.

Question 3

How is Ragchat deployed and integrated into a website?

Accepted Answer

Deployment is exceptionally simple, often with a single command via Claude Code. Ragchat automatically crawls your website content, builds a local vector store, and then generates a self-contained HTML widget (a `<script>` tag) that you can easily embed into any website's HTML.

Ragchat

关于

主要功能

使用案例

Ragchat

关于

主要功能

使用案例