- 🚀 Quick Start |
- 💻 TUI Interface |
- 🐳 Docker Deployment |
- ⚙️ Development |
- 🔧 Troubleshooting
+ Quick Start |
+ TUI Interface |
+ Docker Deployment |
+ Development |
+ Troubleshooting
-
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration. [](https://deepwiki.com/phact/openrag)
@@ -27,12 +26,7 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
-
-
-
-
-
-## 🚀 Quick Start
+## Quick Start
### Prerequisites
@@ -62,7 +56,8 @@ LANGFLOW_CHAT_FLOW_ID=your_chat_flow_id
LANGFLOW_INGEST_FLOW_ID=your_ingest_flow_id
NUDGES_FLOW_ID=your_nudges_flow_id
```
-See extended configuration, including ingestion and optional variables: [docs/reference/configuration.md](docs/docs/reference/configuration.md)
+See extended configuration, including ingestion and optional variables: [docs/reference/configuration.mdx](docs/docs/reference/configuration.mdx)
+
### 3. Start OpenRAG
```bash
@@ -80,13 +75,17 @@ Access the services:
- **OpenSearch**: http://localhost:9200
- **OpenSearch Dashboards**: http://localhost:5601
-## 🖥️ TUI Interface
+With OpenRAG started, ingest and retrieve documents with the [OpenRAG Quickstart](/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.
-### Launching the TUI
+### Launch OpenRAG with the TUI
+
+From the repository root, run:
```bash
# Install dependencies first
@@ -96,66 +95,48 @@ uv sync
uv run openrag
```
-### TUI Features
+For the full TUI guide, see [docs/get-started/tui.mdx](docs/docs/get-started/tui.mdx)
-See the full TUI guide for features, navigation, and benefits: [docs/get-started/tui.mdx](docs/docs/get-started/tui.mdx)
+## Docker Deployment
+The repository includes two Docker Compose 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 with GPU support for accelerated AI processing.
+- [`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.
-## 🐳 Docker Deployment
-
-### Standard Deployment
-
+1. Clone the OpenRAG repository.
+```bash
+git clone https://github.com/langflow-ai/openrag.git
+cd openrag
+```
+
+2. Build and start all services.
+
+For the GPU-accelerated deployment, run:
```bash
-# Build and start all services
docker compose build
docker compose up -d
```
-### CPU-Only Deployment
-
-For environments without GPU support:
-
+For environments without GPU support, run:
```bash
docker compose -f docker-compose-cpu.yml up -d
```
-More deployment commands and tips: [docs/get-started/docker.mdx](docs/docs/get-started/docker.mdx)
+For more information, see [docs/get-started/docker.mdx](docs/docs/get-started/docker.mdx)
-## 🔧 Troubleshooting
+## Troubleshooting
-### Podman on macOS
+For common issues and fixes, see [docs/support/troubleshoot.mdx](docs/docs/support/troubleshoot.mdx).
-If using Podman on macOS, you may need to increase VM memory:
-
-```bash
-podman machine stop
-podman machine rm
-podman machine init --memory 8192 # 8 GB example
-podman machine start
-```
-
-### Common Issues
-
-See common issues and fixes: [docs/support/troubleshoot.mdx](docs/docs/reference/troubleshoot.mdx)
-
-
-
-## 🛠️ Development
+## 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)**
-The contributing guide includes:
-- Complete development environment setup
-- Local development workflows
-- Testing and debugging procedures
-- Code style guidelines
-- Architecture overview
-- Pull request guidelines
-
### Quick Development Commands
```bash
From 5a567a0b95e1d160951c993e1b9e052f0acdd1fa Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 11:29:00 -0400
Subject: [PATCH 05/17] add-release-badge
---
README.md | 27 ++++++++++++++-------------
1 file changed, 14 insertions(+), 13 deletions(-)
diff --git a/README.md b/README.md
index d15328d3..4487e522 100644
--- a/README.md
+++ b/README.md
@@ -2,20 +2,9 @@
# OpenRAG
-
-
-
-
-OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration. [](https://deepwiki.com/phact/openrag)
-
-
+ 
+
@@ -23,9 +12,21 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
+
+ 
+OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
+
+
+
## Quick Start
### Prerequisites
From 1769095581131a83ac777311aefa092078860f1a Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 11:33:14 -0400
Subject: [PATCH 06/17] include-prerelease
---
README.md | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/README.md b/README.md
index 4487e522..e7b1308f 100644
--- a/README.md
+++ b/README.md
@@ -3,8 +3,6 @@
# OpenRAG
+
@@ -23,9 +12,21 @@ OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables
+
+
-
-
@@ -14,7 +12,8 @@
-
+ 
+
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
From ebde493571dabb88386942711ae233ef9a15ebdb Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 11:33:50 -0400
Subject: [PATCH 07/17] remove-release-badge
---
README.md | 2 --
1 file changed, 2 deletions(-)
diff --git a/README.md b/README.md
index e7b1308f..e4f90d3d 100644
--- a/README.md
+++ b/README.md
@@ -12,8 +12,6 @@
-
@@ -14,7 +12,8 @@
-
+
+
-
-
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
From 52a48949fb7ecb3139a442cd66139f1253d8c105 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 11:44:55 -0400
Subject: [PATCH 08/17] changes-for-clarity
---
README.md | 30 ++++++++++++++++--------------
1 file changed, 16 insertions(+), 14 deletions(-)
diff --git a/README.md b/README.md
index e4f90d3d..3d15b53c 100644
--- a/README.md
+++ b/README.md
@@ -17,21 +17,24 @@
OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
-## Quick Start
+## Quickstart
+
### Prerequisites
- Docker or Podman with Compose installed
- Make (for development commands)
-### 1. Environment Setup
+### Install and start OpenRAG
+
+1. Set up development environment.
```bash
# Clone and setup environment
@@ -40,9 +43,7 @@ cd openrag
make setup # Creates .env and installs dependencies
```
-### 2. Configure Environment
-
-Edit `.env` with your API keys and credentials:
+2. Configure the `.env` file with your API keys and credentials.
```bash
# Required
@@ -54,9 +55,10 @@ LANGFLOW_CHAT_FLOW_ID=your_chat_flow_id
LANGFLOW_INGEST_FLOW_ID=your_ingest_flow_id
NUDGES_FLOW_ID=your_nudges_flow_id
```
-See extended configuration, including ingestion and optional variables: [docs/reference/configuration.mdx](docs/docs/reference/configuration.mdx)
-### 3. Start OpenRAG
+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
@@ -73,7 +75,7 @@ Access the services:
- **OpenSearch**: http://localhost:9200
- **OpenSearch Dashboards**: http://localhost:5601
-With OpenRAG started, ingest and retrieve documents with the [OpenRAG Quickstart](/docs/get-started/quickstart.mdx).
+With OpenRAG started, ingest and retrieve documents with the [OpenRAG Quickstart](docs/docs/get-started/quickstart.mdx).
## TUI interface
@@ -93,14 +95,14 @@ uv sync
uv run openrag
```
-For the full TUI guide, see [docs/get-started/tui.mdx](docs/docs/get-started/tui.mdx)
+For the full TUI guide, see [TUI](docs/docs/get-started/tui.mdx).
## Docker Deployment
-The repository includes two Docker Compose files.
+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 with GPU support for accelerated AI processing.
+- [`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.
- [`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.
@@ -123,11 +125,11 @@ For environments without GPU support, run:
docker compose -f docker-compose-cpu.yml up -d
```
-For more information, see [docs/get-started/docker.mdx](docs/docs/get-started/docker.mdx)
+For more information, see [Deploy with Docker](docs/docs/get-started/docker.mdx).
## Troubleshooting
-For common issues and fixes, see [docs/support/troubleshoot.mdx](docs/docs/support/troubleshoot.mdx).
+For common issues and fixes, see [Troubleshoot](docs/docs/support/troubleshoot.mdx).
## Development
From 4720dc6d4affb7ebc287f89401eb694f2263ee30 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Wed, 8 Oct 2025 11:59:36 -0400
Subject: [PATCH 09/17] tui-quickstart
---
CONTRIBUTING.md | 42 ++++++++++++++++++++++-----
README.md | 77 ++++++-------------------------------------------
2 files changed, 44 insertions(+), 75 deletions(-)
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 19b01709..6b8cd832 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -11,20 +11,48 @@ Thank you for your interest in contributing to OpenRAG! This guide will help you
- Python 3.13+ with uv package manager
- Node.js 18+ and npm
-### Environment Setup
+### Set up OpenRAG for development
+
+1. Set up your development environment.
```bash
-# Clone the repository
-git clone
-OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
+OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations. Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience. Built with Starlette, Next.js, OpenSearch, and Langflow integration.
+
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 10/17] 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 11/17] 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 12/17] 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 13/17] 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 14/17] 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 15/17] 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 16/17] 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.
From 64512c79bedb12ac0612b8ca0e357567e23c5f58 Mon Sep 17 00:00:00 2001
From: Alex Leventer <3254549+alexleventer@users.noreply.github.com>
Date: Wed, 8 Oct 2025 13:21:04 -0700
Subject: [PATCH 17/17] Do not check in .DS_Store
---
.DS_Store | Bin 8196 -> 0 bytes
1 file changed, 0 insertions(+), 0 deletions(-)
delete mode 100644 .DS_Store
diff --git a/.DS_Store b/.DS_Store
deleted file mode 100644
index ca39b6e347a514559b8ebc1e3e1057a1eda59931..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001
literal 8196
zcmeHMU2GIp6h7Zl=uF4L6k4`GSXYVxb%C}trTn`6LFKndTUyG`vfCNx$aJRc%_M#0P(ZPewg=?ku6DyeLtObCbDe
z?z!i?bI+OY%gC!VGG(sjh
z3RVY=@3{^LFv(D+Lpd&G0Od7h^?(qHu*86b^L$d6vrLC_TuKQiNH`&UGQtW4!P6O+
z49p2>DWg7$Koo)NBOq#bl?-xehzi%%@7`$6c5^&?E;njhp5NH`1!B`Grq8HUDiuxH
z*E8&vdi<jJz~`Bx^}L7pUv&E%u+_L?Q|VKYdK~<09b~}CVTrW$8bv>Zox6U
z0NW!c6jf0(di~f~%gW|dvZb}@L@GJ9y17x@x12bkDs>Gj*6z$4wnrTIlynB+2Z5?5
zIrsR~p4ncpQ+gKrt?b#QvS(_Qc3Zr+s!yvLu!dZx$2x9i^jRJ|w~2>4@@A2p>K}6L
z!ieK#^qQfpJyfu>zS(Zu!kBflg-Q3QZ@G@Q%glQ$2YmCWFQx}QH}7`_=!~uxJaebX
zV5?|$@eaNlo
z6=l#H&gRYT64R=T*rX`It75%?Y&0z2El(!4DavlKSi52HIyJNOnceXRbG(4$tESyoj@S8|Uy2KEwrlf=}@czQ<+!fM4-PY<6r;tS&Y;7LP5BEt5XP
z%GuFB(WlsQ9#4_?oE>4_#|l$sN8EAblcrDObW#IsOCqJ|P~@OZTcha}oLF+WUb|P*N#wK~cO<$J
zx=541LfE(HUHXU#dx;5qnSP`zs6aL5U?J1<9xTIhG@%)5u^tlkr^&}o;x}L&QcpA^(G@iv7yo^`yDqh3uIFI)x(Q@-dTH^hw
zX<6*aJGSc_;#ooH>2#26KC(*Uhvt9xplWSel}fH``@09#H6Bg!bz*>S>S&r=tzOjs
z8*lvk|4n^nv{)2@C<3=u1W?h{)78OyD*v%Cd3&PPPV#ktFVTeExRe2eyPzCr8I