Demo

Document-based AI assistant platform

AI assistants that answer from your documents, and cite their sources.

EasyRag turns your documents, web pages and knowledge repositories into reliable assistants: configure them without code, publish them on your website or intranet, and stay in control of models, access and data.

See the demoExplore the platform
  • Verified citations
  • 7 model families, including self-hosted
  • Installable in your infrastructure
  • French / English interface
Which documents do I need to provide for a reimbursement request?

Attach the paid invoice and the signed request form 1. Above €500, prior approval from your manager is also required 2.

Sources

  1. 1Reimbursement procedure.pdfPDF“…every request must include the paid invoice and the signed form…”
  2. 2Internal memo no. 12.docxWord“…above €500, the manager’s prior approval is required…”
Interface diagram: sourced answer in the conversation portal (sample content).
UnderstandHow it works, from document to answerSeeThe demo assistant and the screensGo deeperDocumentation, guides, API

Why EasyRag

Make AI useful every day, without losing control

A language model on its own knows nothing about your organization. EasyRag gives it access to your content, governs its behavior and makes it available wherever your users need it.

Access to knowledge

Your procedures, guides and standards can be queried in plain language, by your teams and your end users alike.

Verifiable answers

Every answer is grounded in your documents and cites the excerpts it used. When nothing is found, the assistant says so.

Go live without development

Upload, configure, test and publish from a single interface, with AI helping you write the configuration.

Operational control

Choice of models, roles, single sign-on, data retention, auditing and installation in your own infrastructure.

Features

A complete platform, not a patchwork of components

Document import and indexing, search, agent, publishing, monitoring and administration are designed to work together and are all managed from the same interface.

AI assistants

One assistant per need: role, tone, knowledge, tools and publishing rules, configured from a single interface and versioned.

Knowledge bases

Import your files, index websites, transcribe audio and video, and screen every document before it feeds into answers.

Sourced answers (RAG)

Hybrid search, contextual enrichment and verified citations: every answer points to the excerpts that support it.

Language models

OpenAI, Mistral, Anthropic, Gemini or a model you host yourself: a choice per assistant, encrypted keys and a benchmark to decide based on facts.

Publishing and channels

Widget on your website, public page, internal portal, email, Slack and phone: one assistant, many touchpoints.

Phone callbot

One number, one voice, the same knowledge as the chat: the callbot answers calls, routes them by topic and transfers to an agent when needed.

Tools and agents

Connect your services via MCP, webhooks or REST APIs: the assistant queries your systems, triggers actions and hands the conversation over to the right person.

Document workflows

Synchronize folders, FTP/SFTP servers and websites, have changes approved and publish knowledge base versions on a schedule.

Monitoring and improvement

Metrics, conversation review, AI analysis, reports, live takeover by an agent and a multichannel ticket center.

All features and their availability

How it works

From your documents to a live assistant

The four stages of the EasyRag workflow, just as they unfold in the interface.

  1. Bring your knowledge together

    Upload your documents, index your web pages, sync your folders. Every document can be reviewed before it is used.

    Learn more
    DocumentsWebsitesContent validation Import
    DocumentTypeStatus
    User guide.pdfPDFApproved
    Pricing 2026.xlsxExcelApproved
    Offer overview.pptxPowerPointAnalyzing
    Onboarding training.mp4VideoTranscribed
    Forum export.htmlHTMLTo review

    Documents marked “To review” stay quarantined: they are never used in answers.

    Interface diagram: documents in a corpus and their validation status (sample content).

  2. Configure the assistant

    Role, tone, model, knowledge base and tools: AI suggests an initial configuration that you fine-tune, and every change is versioned.

    Learn more
    System prompt Generate with AI
    You are the customer support assistant. Answer only from the documents provided, cite your sources and offer a human contact if you cannot find the answer.
    Provider · ModelTemperature 0.2Response: text
    Corpora and priorities
    Support knowledge basePriority 1
    Website — help pagesPriority 3
    Agent handoff
    Web search
    Interface diagram: configuring an assistant (sample content).

  3. Publish it where your users are

    Widget on your website, public page, internal portal, email, Slack or API: one configuration, many touchpoints.

    Learn more
    Embed code — scriptAllowed origins: 2
    <script src="https://app.example.com/api/v1/widget.js"
  data-chatbot-id="3f2a…c91e"
  data-button-label="Any questions?"
  data-button-color="#1460d6"></script>

    Channels

    Widget Public page Email Slack API
    Interface diagram: widget embed code and publishing channels (fictitious IDs).

  4. Monitor and improve

    Metrics, conversation review, AI-powered analysis and handover to a human agent when needed.

    Learn more
    Completion rate
    Satisfaction
    Answer ratings
    Review score
    OverviewConversationsLogsEscalationsReports
    Interface diagram: monitoring dashboard (illustrative charts, no real data).

Use cases

Real-world scenarios for every team

Implementation examples built on the features available today.

Employees, business departments

Internal knowledge assistant

Give every employee an immediate, sourced answer about internal procedures, memos and guides.

Customer service teams, support centers

First-level user support

Answer frequently asked questions around the clock and hand over to a human agent when needed, within the same conversation.

Institutional websites, public services

Smart FAQ

Replace a static FAQ with an assistant that understands questions as they are asked and points to the right page.

Legal, sales and technical teams

Specialized business assistant

A form-driven assistant for a specific task: analyzing a request, drafting a standard response, supporting a decision.

All 8 usage scenarios

Integrations

Open to your models, channels and tools

EasyRag is built on standards: a documented REST API, the MCP protocol, webhooks, OpenID Connect. We state precisely what is native, what is configurable and what requires development.

See all integrations

Models

  • OpenAI
  • Mistral
  • Anthropic
  • Gemini
  • Ollama
  • vLLM

Channels

  • Web widget
  • Public page
  • Email
  • Slack
  • REST API

Tools and automation

  • MCP servers
  • Webhooks
  • Third-party APIs
  • n8n (via API)

Identity

  • OpenID Connect
  • FranceConnect+
  • Google

Deployment

Your assistants, in the environment you choose

In your infrastructure

The platform ships as Docker containers (API, RAG service, web interface, PostgreSQL, pgvector, Redis) that you can install on your own servers or cloud.

With the models you choose

Cloud providers or models hosted on your premises (Ollama, vLLM) to generate answers. Embeddings currently rely on OpenAI or Mistral.

With expert support

Installation, source and model configuration, first assistants: the EasyRag team works with you to find the right implementation approach.

Requirements, data, updates: everything about deployment

Community

Learn, share and help EasyRag grow

Practical guides, documentation organized by profile, a changelog and a contribution channel: the EasyRag community is starting out with useful resources, and will grow with its users.

Join the communityRead the guides

Frequently asked questions

What people often ask us

What is EasyRag?

A platform for creating, publishing and monitoring AI assistants (chatbots) that answer from your organization’s documents and cite their sources. It covers document import, assistant and model configuration, publishing (widget, public page, email, Slack, phone, API) and administration.

Do the answers really cite their sources?

Yes. The assistant can only cite excerpts actually retrieved from your documents; citations are numbered and shown with the document name, an excerpt and, for a web page, its URL. The embeddable widget currently displays the numbered answer without the detailed list of sources, which is provided by the chat portal, the public page and the API.

Where is my data stored?

In the infrastructure where the platform is installed: PostgreSQL database, pgvector vector database and file storage. However, questions and the necessary excerpts are sent to the chosen model provider (unless you use a self-hosted model), and embedding goes through OpenAI or Mistral.

Can EasyRag be installed on our own infrastructure?

Yes. The platform consists of Docker containers (API, RAG service, web interface, PostgreSQL, pgvector, Redis). A license is required beyond the free tier. The Deployment page details the prerequisites and external services.

Which language models are supported?

OpenAI, Mistral, Anthropic and Google Gemini, as well as Ollama, vLLM and any service compatible with the OpenAI API. The model is chosen per assistant, and the benchmark compares several models on your own questions.

How does licensing work?

Without a license, the platform runs in a limited free mode (one knowledge base of 5 documents). A “Registered” license, free after email verification, raises the limit to 50 documents per knowledge base. The Pro license removes the limits and enables website indexing, agent tools, monitoring, human handover, the conversation center and assistant trees. Contact us for Pro license terms.

All questions

Let’s see what EasyRag can do with your documents

Try the demo assistant, or tell us about your project: we’ll get back to you with a concrete feasibility assessment.

See the demoTell us about my project