Quickstart |
@@ -26,67 +27,17 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
## Quickstart
+To get started quickly, use the OpenRAG Terminal User Interface (TUI) to manage your OpenRAG installation without complex command-line operations.
-### Prerequisites
-
-- Docker or Podman with Compose installed
-- Make (for development commands)
-
-### Install and start OpenRAG
-
-1. Set up development environment.
+To launch OpenRAG with the TUI, do the following:
+1. Clone the OpenRAG repository.
```bash
-# Clone and setup environment
git clone https://github.com/langflow-ai/openrag.git
cd openrag
-make setup # Creates .env and installs dependencies
```
-2. Configure the `.env` file with your API keys and credentials.
-
-```bash
-# Required
-OPENAI_API_KEY=your_openai_api_key
-OPENSEARCH_PASSWORD=your_secure_password
-LANGFLOW_SUPERUSER=admin
-LANGFLOW_SUPERUSER_PASSWORD=your_secure_password
-LANGFLOW_CHAT_FLOW_ID=your_chat_flow_id
-LANGFLOW_INGEST_FLOW_ID=your_ingest_flow_id
-NUDGES_FLOW_ID=your_nudges_flow_id
-```
-
-For extended configuration, including ingestion and optional variables, see [docs/reference/configuration.mdx](docs/docs/reference/configuration.mdx)
-
-3. Start OpenRAG.
-
-```bash
-# Full stack with GPU support
-make dev
-
-# Or CPU only
-make dev-cpu
-```
-
-Access the services:
-- **Frontend**: http://localhost:3000
-- **Backend API**: http://localhost:8000
-- **Langflow**: http://localhost:7860
-- **OpenSearch**: http://localhost:9200
-- **OpenSearch Dashboards**: http://localhost:5601
-
-With OpenRAG started, ingest and retrieve documents with the [OpenRAG Quickstart](docs/docs/get-started/quickstart.mdx).
-
-## TUI interface
-
-OpenRAG includes a powerful Terminal User Interface (TUI) for easy setup, configuration, and monitoring. The TUI provides a user-friendly way to manage your OpenRAG installation without complex command-line operations.
-
-
-
-### Launch OpenRAG with the TUI
-
-From the repository root, run:
-
+2. To start the TUI, from the repository root, run:
```bash
# Install dependencies first
uv sync
@@ -95,6 +46,8 @@ uv sync
uv run openrag
```
+The TUI opens and guides you through OpenRAG setup.
+
For the full TUI guide, see [TUI](docs/docs/get-started/tui.mdx).
## Docker Deployment
@@ -133,16 +86,4 @@ For common issues and fixes, see [Troubleshoot](docs/docs/support/troubleshoot.m
## Development
-For developers wanting to contribute to OpenRAG or set up a development environment, please see our comprehensive development guide:
-
-**[📚 See CONTRIBUTING.md for detailed development instructions](CONTRIBUTING.md)**
-
-### Quick Development Commands
-
-```bash
-make help # See all available commands
-make setup # Initial development setup
-make infra # Start infrastructure services
-make backend # Run backend locally
-make frontend # Run frontend locally
-```
\ No newline at end of file
+For developers wanting to contribute to OpenRAG or set up a development environment, see [CONTRIBUTING.md](CONTRIBUTING.md).
\ No newline at end of file
From 19c86c8b72e4ef0701e1f6c8b9114dd65148bf30 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 12:02:46 -0400
Subject: [PATCH 07/13] style
---
README.md | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/README.md b/README.md
index 4c06e4a9..b4beef2a 100644
--- a/README.md
+++ b/README.md
@@ -52,7 +52,7 @@ For the full TUI guide, see [TUI](docs/docs/get-started/tui.mdx).
## Docker Deployment
-The repository includes two Docker Compose `.yml` files.
+If you prefer to use Docker to run OpenRAG, the repository includes two Docker Compose `.yml` files.
They deploy the same applications and containers, but to different environments.
- [`docker-compose.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose.yml) is an OpenRAG deployment for environments with GPU support. GPU support requires an NVIDIA GPU with CUDA support and compatible NVIDIA drivers installed on the OpenRAG host machine.
@@ -67,16 +67,16 @@ cd openrag
2. Build and start all services.
-For the GPU-accelerated deployment, run:
-```bash
-docker compose build
-docker compose up -d
-```
+ For the GPU-accelerated deployment, run:
+ ```bash
+ docker compose build
+ docker compose up -d
+ ```
-For environments without GPU support, run:
-```bash
-docker compose -f docker-compose-cpu.yml up -d
-```
+ For environments without GPU support, run:
+ ```bash
+ docker compose -f docker-compose-cpu.yml up -d
+ ```
For more information, see [Deploy with Docker](docs/docs/get-started/docker.mdx).
From 1b45813dfdbb16bf2dab0fb71a17396c77b32848 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 12:03:56 -0400
Subject: [PATCH 08/13] restating-headline
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index b4beef2a..b4838cd8 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
## Quickstart
-To get started quickly, use the OpenRAG Terminal User Interface (TUI) to manage your OpenRAG installation without complex command-line operations.
+Use the OpenRAG Terminal User Interface (TUI) to manage your OpenRAG installation without complex command-line operations.
To launch OpenRAG with the TUI, do the following:
From e88601c05aa72f58d223fbea4b7dbf21788eff55 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 12:05:54 -0400
Subject: [PATCH 09/13] spacing
---
README.md | 32 ++++++++++++++++----------------
1 file changed, 16 insertions(+), 16 deletions(-)
diff --git a/README.md b/README.md
index b4838cd8..bfccdb6a 100644
--- a/README.md
+++ b/README.md
@@ -32,21 +32,21 @@ Use the OpenRAG Terminal User Interface (TUI) to manage your OpenRAG installatio
To launch OpenRAG with the TUI, do the following:
1. Clone the OpenRAG repository.
-```bash
-git clone https://github.com/langflow-ai/openrag.git
-cd openrag
-```
+ ```bash
+ git clone https://github.com/langflow-ai/openrag.git
+ cd openrag
+ ```
2. To start the TUI, from the repository root, run:
-```bash
-# Install dependencies first
-uv sync
+ ```bash
+ # Install dependencies first
+ uv sync
+
+ # Launch the TUI
+ uv run openrag
+ ```
-# Launch the TUI
-uv run openrag
-```
-
-The TUI opens and guides you through OpenRAG setup.
+ The TUI opens and guides you through OpenRAG setup.
For the full TUI guide, see [TUI](docs/docs/get-started/tui.mdx).
@@ -60,10 +60,10 @@ They deploy the same applications and containers, but to different environments.
- [`docker-compose-cpu.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml) is a CPU-only version of OpenRAG for systems without GPU support. Use this Docker compose file for environments where GPU drivers aren't available.
1. Clone the OpenRAG repository.
-```bash
-git clone https://github.com/langflow-ai/openrag.git
-cd openrag
-```
+ ```bash
+ git clone https://github.com/langflow-ai/openrag.git
+ cd openrag
+ ```
2. Build and start all services.
From c5b88b0201fbf65cd93072720627230353ef4a28 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 13:30:17 -0400
Subject: [PATCH 10/13] docling-requirement
---
README.md | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 47 insertions(+), 1 deletion(-)
diff --git a/README.md b/README.md
index bfccdb6a..7d643727 100644
--- a/README.md
+++ b/README.md
@@ -59,13 +59,42 @@ They deploy the same applications and containers, but to different environments.
- [`docker-compose-cpu.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml) is a CPU-only version of OpenRAG for systems without GPU support. Use this Docker compose file for environments where GPU drivers aren't available.
+Both Docker deployments depend on `docling serve` to be running on port `5001` on the host machine. This is required to take advantage of[Mac MLX](https://opensource.apple.com/projects/mlx/) support for document processing. Installing OpenRAG with the TUI starts `docling serve` automatically, but for a Docker deployment you must manually start the `docling serve` process.
+
+Alternatively, set `DISABLE_INGEST_WITH_LANGFLOW=true` in your `.env` to use OpenRAG's built-in pipeline, which uses docling directly without requiring `docling serve`.
+
+To deploy OpenRAG with Docker:
+
1. Clone the OpenRAG repository.
```bash
git clone https://github.com/langflow-ai/openrag.git
cd openrag
```
-2. Build and start all services.
+2. Install dependencies.
+ ```bash
+ uv sync
+ ```
+
+3. Start `docling serve` on the host machine.
+ ```bash
+ uv run python scripts/docling_ctl.py start --port 5001
+ ```
+
+4. Confirm `docling serve` is running.
+ ```
+ uv run python scripts/docling_ctl.py status
+ ```
+
+ Successful result:
+ ```bash
+ Status: running
+ Endpoint: http://127.0.0.1:5001
+ Docs: http://127.0.0.1:5001/docs
+ PID: 27746
+ ```
+
+5. Build and start all services.
For the GPU-accelerated deployment, run:
```bash
@@ -78,6 +107,23 @@ They deploy the same applications and containers, but to different environments.
docker compose -f docker-compose-cpu.yml up -d
```
+ The OpenRAG Docker Compose file starts five containers:
+ | Container Name | Default Address | Purpose |
+ |---|---|---|
+ | OpenRAG Backend | http://localhost:8000 | FastAPI server and core functionality. |
+ | OpenRAG Frontend | http://localhost:3000 | React web interface for users. |
+ | Langflow | http://localhost:7860 | AI workflow engine and flow management. |
+ | OpenSearch | http://localhost:9200 | Vector database for document storage. |
+ | OpenSearch Dashboards | http://localhost:5601 | Database administration interface. |
+
+ You can now access the OpenRAG application at `http://localhost:3000`.
+
+ To stop `docling serve`, run:
+
+ ```bash
+ uv run python scripts/docling_ctl.py stop
+ ```
+
For more information, see [Deploy with Docker](docs/docs/get-started/docker.mdx).
## Troubleshooting
From a2608d0281dc503fdae93ec6b27f622836639dbb Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 13:34:01 -0400
Subject: [PATCH 11/13] style
---
README.md | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index 7d643727..a237b7ed 100644
--- a/README.md
+++ b/README.md
@@ -59,7 +59,7 @@ They deploy the same applications and containers, but to different environments.
- [`docker-compose-cpu.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml) is a CPU-only version of OpenRAG for systems without GPU support. Use this Docker compose file for environments where GPU drivers aren't available.
-Both Docker deployments depend on `docling serve` to be running on port `5001` on the host machine. This is required to take advantage of[Mac MLX](https://opensource.apple.com/projects/mlx/) support for document processing. Installing OpenRAG with the TUI starts `docling serve` automatically, but for a Docker deployment you must manually start the `docling serve` process.
+Both Docker deployments depend on `docling serve` to be running on port `5001` on the host machine. This enables [Mac MLX](https://opensource.apple.com/projects/mlx/) support for document processing. Installing OpenRAG with the TUI starts `docling serve` automatically, but for a Docker deployment you must manually start the `docling serve` process.
Alternatively, set `DISABLE_INGEST_WITH_LANGFLOW=true` in your `.env` to use OpenRAG's built-in pipeline, which uses docling directly without requiring `docling serve`.
@@ -118,7 +118,7 @@ To deploy OpenRAG with Docker:
You can now access the OpenRAG application at `http://localhost:3000`.
- To stop `docling serve`, run:
+To stop `docling serve`, run:
```bash
uv run python scripts/docling_ctl.py stop
From 6b8ff56e6fbe7726822b0512e086458855c44282 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 13:37:00 -0400
Subject: [PATCH 12/13] shorten-sentence
---
README.md | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index a237b7ed..77ce3191 100644
--- a/README.md
+++ b/README.md
@@ -116,10 +116,10 @@ To deploy OpenRAG with Docker:
| OpenSearch | http://localhost:9200 | Vector database for document storage. |
| OpenSearch Dashboards | http://localhost:5601 | Database administration interface. |
- You can now access the OpenRAG application at `http://localhost:3000`.
-
-To stop `docling serve`, run:
+6. Access the OpenRAG application at `http://localhost:3000` and continue with the [Quickstart](docs/docs/get-started/quickstart.mdx).
+ To stop `docling serve`, run:
+
```bash
uv run python scripts/docling_ctl.py stop
```
From bd21001b6457ee9576a9d9eb4a6143d2e6c83590 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 13:45:45 -0400
Subject: [PATCH 13/13] remove-env-var-option
---
README.md | 2 --
1 file changed, 2 deletions(-)
diff --git a/README.md b/README.md
index 77ce3191..a7abbbe6 100644
--- a/README.md
+++ b/README.md
@@ -61,8 +61,6 @@ They deploy the same applications and containers, but to different environments.
Both Docker deployments depend on `docling serve` to be running on port `5001` on the host machine. This enables [Mac MLX](https://opensource.apple.com/projects/mlx/) support for document processing. Installing OpenRAG with the TUI starts `docling serve` automatically, but for a Docker deployment you must manually start the `docling serve` process.
-Alternatively, set `DISABLE_INGEST_WITH_LANGFLOW=true` in your `.env` to use OpenRAG's built-in pipeline, which uses docling directly without requiring `docling serve`.
-
To deploy OpenRAG with Docker:
1. Clone the OpenRAG repository.
+
@@ -23,9 +12,21 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
+
+ 
+