quickstart

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. When integrated with LLMs, it is capable of providing truthful question-answering capabilities, backed by well-founded citations from various complex formatted data.

This quick start guide describes a general process from:

Starting up a local RAGFlow server,
Creating a dataset,
Establishing an AI chat based on your datasets.

IMPORTANT

This guide deploys RAGFlow using Docker images and the Docker Compose configuration provided in the repository. Docker images are available for Linux x86-64 and ARM64 starting with v1.0.0-rc2. Docker automatically selects the image matching your host architecture when you use the release tag.

Prerequisites

A recommended starting configuration of 4 CPU cores (x86-64 or ARM64), 16 GB RAM, and 50 GB free disk space. Actual requirements depend on the document engine, data volume, parsing workload, and concurrency. Local models and OceanBase require additional resources.
Docker ≥ 24.0.0 with Docker Compose ≥ v2.26.1 and BuildKit;
Access to the dependency image infiniflow/ragflow_deps:latest during the image build, and to an LLM and embedding model at runtime.

If Docker is not installed, see Install Docker Engine.

Start up the server

For the default Elasticsearch document engine, ensure vm.max_map_count is at least 262144 on the Docker host:
```
sysctl vm.max_map_count
sudo sysctl -w vm.max_map_count=262144
```
The change made with sysctl -w is temporary. To keep it after a reboot, set vm.max_map_count=262144 in /etc/sysctl.conf. On Docker Desktop, apply the setting to its Linux VM.

Clone the repository:

git clone https://github.com/infiniflow/ragflow.git

Check out the release tag and start the prebuilt RAGFlow Docker image with Docker Compose:
```
# Enter the Docker deployment directory.
cd ragflow/docker
# Check out the latest release tag; replace it with another version if needed.
git checkout v1.0.0-rc2
# Start the RAGFlow services and their dependencies in the background.
docker compose -f docker-compose.yml up -d
```
To deploy another version, replace v1.0.0-rc2 with a tag from the Releases page. Before starting the services, ensure RAGFLOW_IMAGE in docker/.env uses the matching image tag.

The docker/.env file controls DOC_ENGINE, service ports, and dependency credentials. Change the default passwords before deploying to a network-accessible host.

In the RAGFlow open-source 1.0 release, DeepDoc layout analysis, OCR, and table recognition use CPU inference.

Development checkouts
A development checkout can report a code version older than the database migration version, including immediately after its own migrations. In that case, the RAGFlow server refuses to start with Refusing to start: database was migrated by a newer version. For local development with this checkout, set RAGFLOW_DEV_MODE=true in .env and run the Compose command again. This disables the database downgrade check; leave RAGFLOW_DEV_MODE=false for production, and use a binary whose version is at least the database migration version.
Check that the service is running:
```
docker ps
docker logs -f ragflow-cpu
```
After initialization, check the RAGFlow API and its dependencies through the web port from another terminal:
```
curl -f http://localhost/api/v1/system/healthz
```
A successful response has HTTP status 200. If you changed SVR_WEB_HTTP_PORT in .env, include that port in the URL. Wait for this check to pass before opening the web interface.
Open http://IP_OF_YOUR_MACHINE in a browser and log in. If you changed SVR_WEB_HTTP_PORT in .env, include that port in the URL.

The RAGFlow container runs the API server, ingestion workers, and data synchronization. Its startup script runs the database migrations before starting the services.

Configure LLMs

RAGFlow is a RAG engine and needs to work with an LLM to offer grounded, hallucination-free question-answering capabilities. RAGFlow supports most mainstream LLMs.

note

RAGFlow also supports deploying models locally using Ollama or vLLM, but this part is not covered in this quick start guide. See Deploy Local Models for instructions.

To add and configure an LLM:

Open User settings from your avatar, then select Model providers.
In Available models, select a provider and create a provider instance.
Enter the instance name and required connection information, such as API Key and Base URL. Select or add the models you need, verify them, and save the instance.
Under Set default models, select a Chat model and an Embedding model. Configure other model types as needed.

See Configure Model Providers for provider-specific fields and screenshots.

Create your first dataset

You can upload files to a dataset in RAGFlow and parse them into chunks. A dataset is a collection of documents. Question answering in RAGFlow can be based on one or more datasets. Supported file formats include documents (PDF, DOC, DOCX, TXT, MD, MDX), tables (CSV, XLSX, XLS), images (JPEG, JPG, PNG, TIF, GIF), and slides (PPT, PPTX).

To create your first dataset:

Select Datasets in the navigation bar, then click Create dataset.
Enter Name, select Embedding model, and choose Parse type. For a first dataset, select Built-in and a parsing method suitable for your files. To use Pipeline, first create an Ingestion Pipeline in Agent > Ingestion Pipeline, then select it in the creation dialog.
Click Save, open the dataset, and review its Configuration before uploading files.

See Dataset List and Creation and Dataset Configuration for details.

IMPORTANT
Choose the embedding model before parsing files. Before the dataset contains chunks, you can change the model directly. Once chunks exist, selecting a different model on the configuration page triggers a compatibility check against sampled existing vectors. The vector dimensions must match, and the average cosine similarity must be at least 0.9. If the check fails, the previous selection is restored. Saving a model change does not automatically re-embed existing chunks.
Open the dataset's Files page. Click Add file > Upload file, select local files, and confirm the upload. Enable Parse on creation to start parsing automatically.
If parsing was not started during upload, select the uploaded documents and click Run. Wait for parsing to complete before using them in Chat.

See Files: Dataset Document Management for upload and parsing options. If parsing stalls, check the document's Logs and the ragflow-cpu service logs for ingestion errors.

Intervene with file parsing

RAGFlow features visibility and explainability, allowing you to view the chunking results and intervene where necessary. To do so:

Click on the file that completes file parsing to view the chunking results:

You are taken to the Chunk page:
Hover over each snapshot for a quick view of each chunk.
Double click the chunked texts to add keywords or make manual changes where necessary:

NOTE
You can add keywords or questions to a file chunk to improve its ranking for queries containing those keywords. This action increases its keyword weight and can improve its position in search list.
In Retrieval testing, ask a quick question in Test text to double check if your configurations work:

As you can tell from the following, RAGFlow responds with truthful citations.

Set up an AI chat

Conversations in RAGFlow are based on a particular dataset or multiple datasets. Once you have created your dataset and finished file parsing, you can go ahead and start an AI conversation.

Select Chat in the navigation bar, then click Create chat.
Enter a name and confirm creation.
Open Chat setting, select the dataset you parsed, and choose a chat model. You can configure model defaults under User settings > Model providers > Set default models.
Review the System prompt and retrieval settings. Set Empty response to the message you want returned when no answer can be found, or leave it blank to allow the model to generate a response without matching dataset content.
Save the settings, open the chat window, and ask a question about your documents. Select Naive for straightforward questions or Agentic for questions requiring deeper investigation.

See Feature Overview and Creation for Chat creation screenshots and Chat Configuration for the available settings.

NOTE

RAGFlow also offers an HTTP API for integrating its capabilities into your applications: