Merge remote-tracking branch 'origin/main' into lfx-openrag-update-flows
This commit is contained in:
Lucas Oliveira
commit
7d53242eaa
16 changed files with 553 additions and 382 deletions
59
.github/workflows/build-langflow-responses.yml
vendored
Normal file
59
.github/workflows/build-langflow-responses.yml
vendored
Normal file
|
|
@ -0,0 +1,59 @@
|
||||||
|
name: Build Langflow Responses Multi-Arch
|
||||||
|
|
||||||
|
on:
|
||||||
|
workflow_dispatch:
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
build:
|
||||||
|
strategy:
|
||||||
|
fail-fast: false
|
||||||
|
matrix:
|
||||||
|
include:
|
||||||
|
- platform: linux/amd64
|
||||||
|
arch: amd64
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
- platform: linux/arm64
|
||||||
|
arch: arm64
|
||||||
|
runs-on: [self-hosted, linux, ARM64, langflow-ai-arm64-2]
|
||||||
|
|
||||||
|
runs-on: ${{ matrix.runs-on }}
|
||||||
|
|
||||||
|
steps:
|
||||||
|
- name: Checkout
|
||||||
|
uses: actions/checkout@v4
|
||||||
|
|
||||||
|
- name: Set up Docker Buildx
|
||||||
|
uses: docker/setup-buildx-action@v3
|
||||||
|
|
||||||
|
- name: Login to Docker Hub
|
||||||
|
uses: docker/login-action@v3
|
||||||
|
with:
|
||||||
|
username: ${{ secrets.DOCKER_USERNAME }}
|
||||||
|
password: ${{ secrets.DOCKER_PASSWORD }}
|
||||||
|
|
||||||
|
- name: Build and push langflow (${{ matrix.arch }})
|
||||||
|
uses: docker/build-push-action@v5
|
||||||
|
with:
|
||||||
|
context: .
|
||||||
|
file: ./Dockerfile.langflow
|
||||||
|
platforms: ${{ matrix.platform }}
|
||||||
|
push: true
|
||||||
|
tags: phact/langflow:responses-${{ matrix.arch }}
|
||||||
|
cache-from: type=gha,scope=langflow-responses-${{ matrix.arch }}
|
||||||
|
cache-to: type=gha,mode=max,scope=langflow-responses-${{ matrix.arch }}
|
||||||
|
|
||||||
|
manifest:
|
||||||
|
needs: build
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- name: Login to Docker Hub
|
||||||
|
uses: docker/login-action@v3
|
||||||
|
with:
|
||||||
|
username: ${{ secrets.DOCKER_USERNAME }}
|
||||||
|
password: ${{ secrets.DOCKER_PASSWORD }}
|
||||||
|
|
||||||
|
- name: Create and push multi-arch manifest
|
||||||
|
run: |
|
||||||
|
docker buildx imagetools create -t phact/langflow:responses \
|
||||||
|
phact/langflow:responses-amd64 \
|
||||||
|
phact/langflow:responses-arm64
|
||||||
|
|
@ -138,7 +138,7 @@ podman machine start
|
||||||
|
|
||||||
### Common Issues
|
### Common Issues
|
||||||
|
|
||||||
See common issues and fixes: [docs/reference/troubleshooting.mdx](docs/docs/reference/troubleshooting.mdx)
|
See common issues and fixes: [docs/support/troubleshoot.mdx](docs/docs/reference/troubleshoot.mdx)
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1,40 +1,88 @@
|
||||||
---
|
---
|
||||||
title: Docker Deployment
|
title: Docker deployment
|
||||||
slug: /get-started/docker
|
slug: /get-started/docker
|
||||||
---
|
---
|
||||||
|
|
||||||
# Docker Deployment
|
There are two different Docker Compose files.
|
||||||
|
They deploy the same applications and containers, but to different environments.
|
||||||
|
|
||||||
## Standard Deployment
|
- [`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.
|
||||||
|
|
||||||
```bash
|
- [`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.
|
||||||
# Build and start all services
|
|
||||||
docker compose build
|
|
||||||
docker compose up -d
|
|
||||||
```
|
|
||||||
|
|
||||||
## CPU-Only Deployment
|
To install OpenRAG with Docker Compose:
|
||||||
|
|
||||||
For environments without GPU support:
|
1. Clone the OpenRAG repository.
|
||||||
|
```bash
|
||||||
|
git clone https://github.com/langflow-ai/openrag.git
|
||||||
|
cd openrag
|
||||||
|
```
|
||||||
|
|
||||||
```bash
|
2. Copy the example `.env` file that is included in the repository root.
|
||||||
docker compose -f docker-compose-cpu.yml up -d
|
The example file includes all environment variables with comments to guide you in finding and setting their values.
|
||||||
```
|
```bash
|
||||||
|
cp .env.example .env
|
||||||
|
```
|
||||||
|
|
||||||
## Force Rebuild
|
Alternatively, create a new `.env` file in the repository root.
|
||||||
|
```
|
||||||
|
touch .env
|
||||||
|
```
|
||||||
|
|
||||||
If you need to reset state or rebuild everything:
|
3. Set environment variables. The Docker Compose files are populated with values from your `.env`, so the following values are **required** to be set:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
OPENSEARCH_PASSWORD=your_secure_password
|
||||||
|
OPENAI_API_KEY=your_openai_api_key
|
||||||
|
|
||||||
|
LANGFLOW_SUPERUSER=admin
|
||||||
|
LANGFLOW_SUPERUSER_PASSWORD=your_langflow_password
|
||||||
|
LANGFLOW_SECRET_KEY=your_secret_key
|
||||||
|
```
|
||||||
|
For more information on configuring OpenRAG with environment variables, see [Environment variables](/configure/configuration).
|
||||||
|
For additional configuration values, including `config.yaml`, see [Configuration](/configure/configuration).
|
||||||
|
|
||||||
|
4. Deploy OpenRAG with Docker Compose based on your deployment type.
|
||||||
|
|
||||||
|
For GPU-enabled systems, run the following command:
|
||||||
|
```bash
|
||||||
|
docker compose up -d
|
||||||
|
```
|
||||||
|
|
||||||
|
For CPU-only systems, run the following command:
|
||||||
|
```bash
|
||||||
|
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. |
|
||||||
|
|
||||||
|
5. Verify installation by confirming all services are running.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
docker compose ps
|
||||||
|
```
|
||||||
|
|
||||||
|
You can now access the application at:
|
||||||
|
|
||||||
|
- **Frontend**: http://localhost:3000
|
||||||
|
- **Backend API**: http://localhost:8000
|
||||||
|
- **Langflow**: http://localhost:7860
|
||||||
|
|
||||||
|
Continue with the [Quickstart](/quickstart).
|
||||||
|
|
||||||
|
## Rebuild all Docker containers
|
||||||
|
|
||||||
|
If you need to reset state and rebuild all of your containers, run the following command.
|
||||||
|
Your OpenSearch and Langflow databases will be lost.
|
||||||
|
Documents stored in the `./documents` directory will persist, since the directory is mounted as a volume in the OpenRAG backend container.
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
docker compose up --build --force-recreate --remove-orphans
|
docker compose up --build --force-recreate --remove-orphans
|
||||||
```
|
```
|
||||||
|
|
||||||
## Service URLs
|
|
||||||
|
|
||||||
After deployment, services are available at:
|
|
||||||
|
|
||||||
- Frontend: http://localhost:3000
|
|
||||||
- Backend API: http://localhost:8000
|
|
||||||
- Langflow: http://localhost:7860
|
|
||||||
- OpenSearch: http://localhost:9200
|
|
||||||
- OpenSearch Dashboards: http://localhost:5601
|
|
||||||
|
|
|
||||||
|
|
@ -10,7 +10,7 @@ OpenRAG can be installed in multiple ways:
|
||||||
|
|
||||||
* [**Python wheel**](#install-python-wheel): Install the OpenRAG Python wheel and use the [OpenRAG Terminal User Interface (TUI)](/get-started/tui) to install, run, and configure your OpenRAG deployment without running Docker commands.
|
* [**Python wheel**](#install-python-wheel): Install the OpenRAG Python wheel and use the [OpenRAG Terminal User Interface (TUI)](/get-started/tui) to install, run, and configure your OpenRAG deployment without running Docker commands.
|
||||||
|
|
||||||
* [**Docker Compose**](#install-and-run-docker): Clone the OpenRAG repository and deploy OpenRAG with Docker Compose, including all services and dependencies.
|
* [**Docker Compose**](get-started/docker): Clone the OpenRAG repository and deploy OpenRAG with Docker Compose, including all services and dependencies.
|
||||||
|
|
||||||
## Prerequisites
|
## Prerequisites
|
||||||
|
|
||||||
|
|
@ -139,79 +139,3 @@ The `LANGFLOW_PUBLIC_URL` controls where the Langflow web interface can be acces
|
||||||
The `WEBHOOK_BASE_URL` controls where the endpoint for `/connectors/CONNECTOR_TYPE/webhook` will be available.
|
The `WEBHOOK_BASE_URL` controls where the endpoint for `/connectors/CONNECTOR_TYPE/webhook` will be available.
|
||||||
This connection enables real-time document synchronization with external services.
|
This connection enables real-time document synchronization with external services.
|
||||||
For example, for Google Drive file synchronization the webhook URL is `/connectors/google_drive/webhook`.
|
For example, for Google Drive file synchronization the webhook URL is `/connectors/google_drive/webhook`.
|
||||||
|
|
||||||
## Docker {#install-and-run-docker}
|
|
||||||
|
|
||||||
There are two different 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.
|
|
||||||
|
|
||||||
To install OpenRAG with Docker Compose:
|
|
||||||
|
|
||||||
1. Clone the OpenRAG repository.
|
|
||||||
```bash
|
|
||||||
git clone https://github.com/langflow-ai/openrag.git
|
|
||||||
cd openrag
|
|
||||||
```
|
|
||||||
|
|
||||||
2. Copy the example `.env` file that is included in the repository root.
|
|
||||||
The example file includes all environment variables with comments to guide you in finding and setting their values.
|
|
||||||
```bash
|
|
||||||
cp .env.example .env
|
|
||||||
```
|
|
||||||
|
|
||||||
Alternatively, create a new `.env` file in the repository root.
|
|
||||||
```
|
|
||||||
touch .env
|
|
||||||
```
|
|
||||||
|
|
||||||
3. Set environment variables. The Docker Compose files are populated with values from your `.env`, so the following values are **required** to be set:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
OPENSEARCH_PASSWORD=your_secure_password
|
|
||||||
OPENAI_API_KEY=your_openai_api_key
|
|
||||||
|
|
||||||
LANGFLOW_SUPERUSER=admin
|
|
||||||
LANGFLOW_SUPERUSER_PASSWORD=your_langflow_password
|
|
||||||
LANGFLOW_SECRET_KEY=your_secret_key
|
|
||||||
```
|
|
||||||
For more information on configuring OpenRAG with environment variables, see [Environment variables](/configure/configuration).
|
|
||||||
For additional configuration values, including `config.yaml`, see [Configuration](/configure/configuration).
|
|
||||||
|
|
||||||
4. Deploy OpenRAG with Docker Compose based on your deployment type.
|
|
||||||
|
|
||||||
For GPU-enabled systems, run the following command:
|
|
||||||
```bash
|
|
||||||
docker compose up -d
|
|
||||||
```
|
|
||||||
|
|
||||||
For CPU-only systems, run the following command:
|
|
||||||
```bash
|
|
||||||
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. |
|
|
||||||
|
|
||||||
5. Verify installation by confirming all services are running.
|
|
||||||
|
|
||||||
```bash
|
|
||||||
docker compose ps
|
|
||||||
```
|
|
||||||
|
|
||||||
You can now access the application at:
|
|
||||||
|
|
||||||
- **Frontend**: http://localhost:3000
|
|
||||||
- **Backend API**: http://localhost:8000
|
|
||||||
- **Langflow**: http://localhost:7860
|
|
||||||
|
|
||||||
Continue with the Quickstart.
|
|
||||||
|
|
@ -1,66 +1,94 @@
|
||||||
---
|
---
|
||||||
title: Terminal Interface (TUI)
|
title: Terminal User Interface (TUI) commands
|
||||||
slug: /get-started/tui
|
slug: /get-started/tui
|
||||||
---
|
---
|
||||||
|
|
||||||
# OpenRAG TUI Guide
|
# OpenRAG TUI Guide
|
||||||
|
|
||||||
The OpenRAG Terminal User Interface (TUI) provides a streamlined way to set up, configure, and monitor your OpenRAG deployment directly from the terminal.
|
The OpenRAG Terminal User Interface (TUI) provides a streamlined way to set up, configure, and monitor your OpenRAG deployment directly from the terminal, on any operating system.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## Launch
|
The TUI offers an easier way to use OpenRAG without sacrificing control.
|
||||||
|
Instead of starting OpenRAG using Docker commands and manually editing values in the `.env` file, the TUI walks you through the setup. It prompts for variables where required, creates a `.env` file for you, and then starts OpenRAG.
|
||||||
|
|
||||||
|
Once OpenRAG is running, use the TUI to monitor your application, control your containers, and retrieve logs.
|
||||||
|
|
||||||
|
## Start the TUI
|
||||||
|
|
||||||
|
To start the TUI, run the following commands from the directory where you installed OpenRAG.
|
||||||
|
For more information, see [Install OpenRAG](/install).
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
uv sync
|
uv sync
|
||||||
uv run openrag
|
uv run openrag
|
||||||
```
|
```
|
||||||
|
|
||||||
## Features
|
The TUI Welcome Screen offers basic and advanced setup options.
|
||||||
|
For more information on setup values during installation, see [Install OpenRAG](/install).
|
||||||
### Welcome Screen
|
|
||||||
- Quick setup options: basic (no auth) or advanced (OAuth)
|
|
||||||
- Service monitoring: container status at a glance
|
|
||||||
- Quick actions: diagnostics, logs, configuration
|
|
||||||
|
|
||||||
### Configuration Screen
|
|
||||||
- Environment variables: guided forms for required settings
|
|
||||||
- API keys: secure input with validation
|
|
||||||
- OAuth setup: Google and Microsoft
|
|
||||||
- Document paths: configure ingestion directories
|
|
||||||
- Auto-save: generates and updates `.env`
|
|
||||||
|
|
||||||
### Service Monitor
|
|
||||||
- Container status: real-time state of services
|
|
||||||
- Resource usage: CPU, memory, network
|
|
||||||
- Service control: start/stop/restart
|
|
||||||
- Health checks: health indicators for all components
|
|
||||||
|
|
||||||
### Log Viewer
|
|
||||||
- Live logs: stream logs across services
|
|
||||||
- Filtering: by service (backend, frontend, Langflow, OpenSearch)
|
|
||||||
- Levels: DEBUG/INFO/WARNING/ERROR
|
|
||||||
- Export: save logs for later analysis
|
|
||||||
|
|
||||||
### Diagnostics
|
|
||||||
- System checks: Docker/Podman availability and configuration
|
|
||||||
- Environment validation: verify required variables
|
|
||||||
- Network tests: connectivity between services
|
|
||||||
- Performance metrics: system capacity and recommendations
|
|
||||||
|
|
||||||
## Navigation
|
## Navigation
|
||||||
- Arrow keys: move between options
|
|
||||||
- Tab/Shift+Tab: switch fields and buttons
|
|
||||||
- Enter: select/confirm
|
|
||||||
- Escape: back
|
|
||||||
- Q: quit
|
|
||||||
- Number keys (1-4): quick access to main screens
|
|
||||||
|
|
||||||
## Benefits
|
The TUI accepts mouse input or keyboard commands.
|
||||||
1. Simplified setup without manual file edits
|
|
||||||
2. Clear visual feedback and error messages
|
|
||||||
3. Integrated monitoring and control
|
|
||||||
4. Cross-platform: Linux, macOS, Windows
|
|
||||||
5. Fully terminal-based; no browser required
|
|
||||||
|
|
||||||
|
- <kbd>Arrow keys</kbd>: move between options
|
||||||
|
- <kbd>Tab</kbd>/<kbd>Shift+Tab</kbd>: switch fields and buttons
|
||||||
|
- <kbd>Enter</kbd>: select/confirm
|
||||||
|
- <kbd>Escape</kbd>: back
|
||||||
|
- <kbd>Q</kbd>: quit
|
||||||
|
- <kbd>Number keys (1-4)</kbd>: quick access to main screens
|
||||||
|
|
||||||
|
## Container management
|
||||||
|
|
||||||
|
The TUI can deploy, manage, and upgrade your OpenRAG containers.
|
||||||
|
|
||||||
|
### Start container services
|
||||||
|
|
||||||
|
Click **Start Container Services** to start the OpenRAG containers.
|
||||||
|
The TUI automatically detects your container runtime, and then checks if your machine has compatible GPU support by checking for `CUDA`, `NVIDIA_SMI`, and Docker/Podman runtime support. This check determines which Docker Compose file OpenRAG uses.
|
||||||
|
The TUI then pulls the images and deploys the containers with the following command.
|
||||||
|
```bash
|
||||||
|
docker compose up -d
|
||||||
|
```
|
||||||
|
If images are missing, the TUI runs `docker compose pull`, then runs `docker compose up -d`.
|
||||||
|
|
||||||
|
### Start native services
|
||||||
|
|
||||||
|
A "native" service in OpenRAG refers to a service run natively on your machine, and not within a container.
|
||||||
|
The `docling-serve` process is a native service in OpenRAG, because it's a document processing service that is run on your local machine, and controlled separately from the containers.
|
||||||
|
|
||||||
|
To start or stop `docling-serve` or any other native services, in the TUI main menu, click **Start Native Services** or **Stop Native Services**.
|
||||||
|
|
||||||
|
To view the status, port, or PID of a native service, in the TUI main menu, click [Status](#status).
|
||||||
|
|
||||||
|
### Status
|
||||||
|
|
||||||
|
The **Status** menu displays information on your container deployment.
|
||||||
|
Here you can check container health, find your service ports, view logs, and upgrade your containers.
|
||||||
|
|
||||||
|
To view streaming logs, select the container you want to view, and press <kbd>l</kbd>.
|
||||||
|
To copy your logs, click **Copy to Clipboard**.
|
||||||
|
|
||||||
|
To **upgrade** your containers, click **Upgrade**.
|
||||||
|
**Upgrade** runs `docker compose pull` and then `docker compose up -d --force-recreate`.
|
||||||
|
The first command pulls the latest images of OpenRAG.
|
||||||
|
The second command recreates the containers with your data persisted.
|
||||||
|
|
||||||
|
To **reset** your containers, click **Reset**.
|
||||||
|
Reset gives you a completely fresh start.
|
||||||
|
Reset deletes all of your data, including OpenSearch data, uploaded documents, and authentication.
|
||||||
|
**Reset** runs two commands.
|
||||||
|
It first stops and removes all containers, volumes, and local images.
|
||||||
|
```
|
||||||
|
docker compose down --volumes --remove-orphans --rmi local
|
||||||
|
```
|
||||||
|
|
||||||
|
When the first command is complete, OpenRAG removes any additional Docker objects with `prune`.
|
||||||
|
|
||||||
|
```
|
||||||
|
docker system prune -f
|
||||||
|
```
|
||||||
|
|
||||||
|
## Diagnostics
|
||||||
|
|
||||||
|
The **Diagnostics** menu provides health monitoring for your container runtimes and monitoring of your OpenSearch security.
|
||||||
|
|
@ -1,24 +0,0 @@
|
||||||
---
|
|
||||||
title: Troubleshooting
|
|
||||||
slug: /reference/troubleshooting
|
|
||||||
---
|
|
||||||
|
|
||||||
# Troubleshooting
|
|
||||||
|
|
||||||
## Podman on macOS
|
|
||||||
|
|
||||||
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
|
|
||||||
|
|
||||||
1. OpenSearch fails to start: Check that `OPENSEARCH_PASSWORD` is set and meets requirements
|
|
||||||
2. Langflow connection issues: Verify `LANGFLOW_SUPERUSER` credentials are correct
|
|
||||||
3. Out of memory errors: Increase Docker memory allocation or use CPU-only mode
|
|
||||||
4. Port conflicts: Ensure ports 3000, 7860, 8000, 9200, 5601 are available
|
|
||||||
107
docs/docs/support/troubleshoot.mdx
Normal file
107
docs/docs/support/troubleshoot.mdx
Normal file
|
|
@ -0,0 +1,107 @@
|
||||||
|
---
|
||||||
|
title: Troubleshoot
|
||||||
|
slug: /support/troubleshoot
|
||||||
|
---
|
||||||
|
|
||||||
|
import Tabs from '@theme/Tabs';
|
||||||
|
import TabItem from '@theme/TabItem';
|
||||||
|
|
||||||
|
This page provides troubleshooting advice for issues you might encounter when using OpenRAG or contributing to OpenRAG.
|
||||||
|
|
||||||
|
## OpenSearch fails to start
|
||||||
|
|
||||||
|
Check that `OPENSEARCH_PASSWORD` is set and meets requirements.
|
||||||
|
The password must contain at least 8 characters, and must contain at least one uppercase letter, one lowercase letter, one digit, and one special character that is strong.
|
||||||
|
|
||||||
|
## Langflow connection issues
|
||||||
|
|
||||||
|
Verify the `LANGFLOW_SUPERUSER` credentials are correct.
|
||||||
|
|
||||||
|
## Memory errors
|
||||||
|
|
||||||
|
### Container out of memory errors
|
||||||
|
|
||||||
|
Increase Docker memory allocation or use [docker-compose-cpu.yml](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml) to deploy OpenRAG.
|
||||||
|
|
||||||
|
### Podman on macOS memory issues
|
||||||
|
|
||||||
|
If you're using Podman on macOS, you may need to increase VM memory on your Podman machine.
|
||||||
|
This example increases the machine size to 8 GB of RAM, which should be sufficient to run OpenRAG.
|
||||||
|
```bash
|
||||||
|
podman machine stop
|
||||||
|
podman machine rm
|
||||||
|
podman machine init --memory 8192 # 8 GB example
|
||||||
|
podman machine start
|
||||||
|
```
|
||||||
|
|
||||||
|
## Port conflicts
|
||||||
|
|
||||||
|
Ensure ports 3000, 7860, 8000, 9200, 5601 are available.
|
||||||
|
|
||||||
|
## Langflow container already exists
|
||||||
|
|
||||||
|
If you are running other versions of Langflow containers on your machine, you may encounter an issue where Docker or Podman thinks Langflow is already up.
|
||||||
|
|
||||||
|
Remove just the problem container, or clean up all containers and start fresh.
|
||||||
|
|
||||||
|
To reset your local containers and pull new images, do the following:
|
||||||
|
|
||||||
|
1. Stop your containers and completely remove them.
|
||||||
|
|
||||||
|
<Tabs groupId="Container software">
|
||||||
|
<TabItem value="Docker" label="Docker" default>
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Stop all running containers
|
||||||
|
docker stop $(docker ps -q)
|
||||||
|
|
||||||
|
# Remove all containers (including stopped ones)
|
||||||
|
docker rm --force $(docker ps -aq)
|
||||||
|
|
||||||
|
# Remove all images
|
||||||
|
docker rmi --force $(docker images -q)
|
||||||
|
|
||||||
|
# Remove all volumes
|
||||||
|
docker volume prune --force
|
||||||
|
|
||||||
|
# Remove all networks (except default)
|
||||||
|
docker network prune --force
|
||||||
|
|
||||||
|
# Clean up any leftover data
|
||||||
|
docker system prune --all --force --volumes
|
||||||
|
```
|
||||||
|
|
||||||
|
</TabItem>
|
||||||
|
<TabItem value="Podman" label="Podman">
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Stop all running containers
|
||||||
|
podman stop --all
|
||||||
|
|
||||||
|
# Remove all containers (including stopped ones)
|
||||||
|
podman rm --all --force
|
||||||
|
|
||||||
|
# Remove all images
|
||||||
|
podman rmi --all --force
|
||||||
|
|
||||||
|
# Remove all volumes
|
||||||
|
podman volume prune --force
|
||||||
|
|
||||||
|
# Remove all networks (except default)
|
||||||
|
podman network prune --force
|
||||||
|
|
||||||
|
# Clean up any leftover data
|
||||||
|
podman system prune --all --force --volumes
|
||||||
|
```
|
||||||
|
|
||||||
|
</TabItem>
|
||||||
|
</Tabs>
|
||||||
|
|
||||||
|
2. Restart OpenRAG and upgrade to get the latest images for your containers.
|
||||||
|
```bash
|
||||||
|
uv run openrag
|
||||||
|
```
|
||||||
|
|
||||||
|
3. In the OpenRAG TUI, click **Status**, and then click **Upgrade**.
|
||||||
|
When the **Close** button is active, the upgrade is complete.
|
||||||
|
Close the window and open the OpenRAG appplication.
|
||||||
|
|
@ -76,12 +76,12 @@ const sidebars = {
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
type: "category",
|
type: "category",
|
||||||
label: "Reference",
|
label: "Support",
|
||||||
items: [
|
items: [
|
||||||
{
|
{
|
||||||
type: "doc",
|
type: "doc",
|
||||||
id: "reference/troubleshooting",
|
id: "support/troubleshoot",
|
||||||
label: "Troubleshooting"
|
label: "Troubleshoot"
|
||||||
},
|
},
|
||||||
],
|
],
|
||||||
},
|
},
|
||||||
|
|
|
||||||
|
|
@ -1,29 +1,29 @@
|
||||||
"use client"
|
"use client";
|
||||||
|
|
||||||
import * as React from "react"
|
import * as SwitchPrimitives from "@radix-ui/react-switch";
|
||||||
import * as SwitchPrimitives from "@radix-ui/react-switch"
|
import * as React from "react";
|
||||||
|
|
||||||
import { cn } from "@/lib/utils"
|
import { cn } from "@/lib/utils";
|
||||||
|
|
||||||
const Switch = React.forwardRef<
|
const Switch = React.forwardRef<
|
||||||
React.ElementRef<typeof SwitchPrimitives.Root>,
|
React.ElementRef<typeof SwitchPrimitives.Root>,
|
||||||
React.ComponentPropsWithoutRef<typeof SwitchPrimitives.Root>
|
React.ComponentPropsWithoutRef<typeof SwitchPrimitives.Root>
|
||||||
>(({ className, ...props }, ref) => (
|
>(({ className, ...props }, ref) => (
|
||||||
<SwitchPrimitives.Root
|
<SwitchPrimitives.Root
|
||||||
className={cn(
|
className={cn(
|
||||||
"peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-input",
|
"peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-muted",
|
||||||
className
|
className,
|
||||||
)}
|
)}
|
||||||
{...props}
|
{...props}
|
||||||
ref={ref}
|
ref={ref}
|
||||||
>
|
>
|
||||||
<SwitchPrimitives.Thumb
|
<SwitchPrimitives.Thumb
|
||||||
className={cn(
|
className={cn(
|
||||||
"pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0"
|
"pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0 data-[state=unchecked]:bg-primary",
|
||||||
)}
|
)}
|
||||||
/>
|
/>
|
||||||
</SwitchPrimitives.Root>
|
</SwitchPrimitives.Root>
|
||||||
))
|
));
|
||||||
Switch.displayName = SwitchPrimitives.Root.displayName
|
Switch.displayName = SwitchPrimitives.Root.displayName;
|
||||||
|
|
||||||
export { Switch }
|
export { Switch };
|
||||||
|
|
|
||||||
|
|
@ -8,7 +8,9 @@ interface UpdateFlowSettingVariables {
|
||||||
llm_model?: string;
|
llm_model?: string;
|
||||||
system_prompt?: string;
|
system_prompt?: string;
|
||||||
embedding_model?: string;
|
embedding_model?: string;
|
||||||
doclingPresets?: string;
|
table_structure?: boolean;
|
||||||
|
ocr?: boolean;
|
||||||
|
picture_descriptions?: boolean;
|
||||||
chunk_size?: number;
|
chunk_size?: number;
|
||||||
chunk_overlap?: number;
|
chunk_overlap?: number;
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -13,7 +13,9 @@ export interface KnowledgeSettings {
|
||||||
embedding_model?: string;
|
embedding_model?: string;
|
||||||
chunk_size?: number;
|
chunk_size?: number;
|
||||||
chunk_overlap?: number;
|
chunk_overlap?: number;
|
||||||
doclingPresets?: string;
|
table_structure?: boolean;
|
||||||
|
ocr?: boolean;
|
||||||
|
picture_descriptions?: boolean;
|
||||||
}
|
}
|
||||||
|
|
||||||
export interface Settings {
|
export interface Settings {
|
||||||
|
|
|
||||||
|
|
@ -1,10 +1,5 @@
|
||||||
"use client";
|
"use client";
|
||||||
|
|
||||||
import {
|
|
||||||
Tooltip,
|
|
||||||
TooltipContent,
|
|
||||||
TooltipTrigger,
|
|
||||||
} from "@radix-ui/react-tooltip";
|
|
||||||
import { ArrowUpRight, Loader2, PlugZap, RefreshCw } from "lucide-react";
|
import { ArrowUpRight, Loader2, PlugZap, RefreshCw } from "lucide-react";
|
||||||
import { useSearchParams } from "next/navigation";
|
import { useSearchParams } from "next/navigation";
|
||||||
import { Suspense, useCallback, useEffect, useState } from "react";
|
import { Suspense, useCallback, useEffect, useState } from "react";
|
||||||
|
|
@ -30,13 +25,13 @@ import {
|
||||||
import { Checkbox } from "@/components/ui/checkbox";
|
import { Checkbox } from "@/components/ui/checkbox";
|
||||||
import { Input } from "@/components/ui/input";
|
import { Input } from "@/components/ui/input";
|
||||||
import { Label } from "@/components/ui/label";
|
import { Label } from "@/components/ui/label";
|
||||||
import { RadioGroup, RadioGroupItem } from "@/components/ui/radio-group";
|
|
||||||
import {
|
import {
|
||||||
Select,
|
Select,
|
||||||
SelectContent,
|
SelectContent,
|
||||||
SelectTrigger,
|
SelectTrigger,
|
||||||
SelectValue,
|
SelectValue,
|
||||||
} from "@/components/ui/select";
|
} from "@/components/ui/select";
|
||||||
|
import { Switch } from "@/components/ui/switch";
|
||||||
import { Textarea } from "@/components/ui/textarea";
|
import { Textarea } from "@/components/ui/textarea";
|
||||||
import { useAuth } from "@/contexts/auth-context";
|
import { useAuth } from "@/contexts/auth-context";
|
||||||
import { useTask } from "@/contexts/task-context";
|
import { useTask } from "@/contexts/task-context";
|
||||||
|
|
@ -116,7 +111,10 @@ function KnowledgeSourcesPage() {
|
||||||
const [systemPrompt, setSystemPrompt] = useState<string>("");
|
const [systemPrompt, setSystemPrompt] = useState<string>("");
|
||||||
const [chunkSize, setChunkSize] = useState<number>(1024);
|
const [chunkSize, setChunkSize] = useState<number>(1024);
|
||||||
const [chunkOverlap, setChunkOverlap] = useState<number>(50);
|
const [chunkOverlap, setChunkOverlap] = useState<number>(50);
|
||||||
const [processingMode, setProcessingMode] = useState<string>("standard");
|
const [tableStructure, setTableStructure] = useState<boolean>(false);
|
||||||
|
const [ocr, setOcr] = useState<boolean>(false);
|
||||||
|
const [pictureDescriptions, setPictureDescriptions] =
|
||||||
|
useState<boolean>(false);
|
||||||
|
|
||||||
// Fetch settings using React Query
|
// Fetch settings using React Query
|
||||||
const { data: settings = {} } = useGetSettingsQuery({
|
const { data: settings = {} } = useGetSettingsQuery({
|
||||||
|
|
@ -200,12 +198,24 @@ function KnowledgeSourcesPage() {
|
||||||
}
|
}
|
||||||
}, [settings.knowledge?.chunk_overlap]);
|
}, [settings.knowledge?.chunk_overlap]);
|
||||||
|
|
||||||
// Sync processing mode with settings data
|
// Sync docling settings with settings data
|
||||||
useEffect(() => {
|
useEffect(() => {
|
||||||
if (settings.knowledge?.doclingPresets) {
|
if (settings.knowledge?.table_structure !== undefined) {
|
||||||
setProcessingMode(settings.knowledge.doclingPresets);
|
setTableStructure(settings.knowledge.table_structure);
|
||||||
}
|
}
|
||||||
}, [settings.knowledge?.doclingPresets]);
|
}, [settings.knowledge?.table_structure]);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
if (settings.knowledge?.ocr !== undefined) {
|
||||||
|
setOcr(settings.knowledge.ocr);
|
||||||
|
}
|
||||||
|
}, [settings.knowledge?.ocr]);
|
||||||
|
|
||||||
|
useEffect(() => {
|
||||||
|
if (settings.knowledge?.picture_descriptions !== undefined) {
|
||||||
|
setPictureDescriptions(settings.knowledge.picture_descriptions);
|
||||||
|
}
|
||||||
|
}, [settings.knowledge?.picture_descriptions]);
|
||||||
|
|
||||||
// Update model selection immediately
|
// Update model selection immediately
|
||||||
const handleModelChange = (newModel: string) => {
|
const handleModelChange = (newModel: string) => {
|
||||||
|
|
@ -236,11 +246,20 @@ function KnowledgeSourcesPage() {
|
||||||
debouncedUpdate({ chunk_overlap: numValue });
|
debouncedUpdate({ chunk_overlap: numValue });
|
||||||
};
|
};
|
||||||
|
|
||||||
// Update processing mode
|
// Update docling settings
|
||||||
const handleProcessingModeChange = (mode: string) => {
|
const handleTableStructureChange = (checked: boolean) => {
|
||||||
setProcessingMode(mode);
|
setTableStructure(checked);
|
||||||
// Update the configuration setting (backend will also update the flow automatically)
|
updateFlowSettingMutation.mutate({ table_structure: checked });
|
||||||
debouncedUpdate({ doclingPresets: mode });
|
};
|
||||||
|
|
||||||
|
const handleOcrChange = (checked: boolean) => {
|
||||||
|
setOcr(checked);
|
||||||
|
updateFlowSettingMutation.mutate({ ocr: checked });
|
||||||
|
};
|
||||||
|
|
||||||
|
const handlePictureDescriptionsChange = (checked: boolean) => {
|
||||||
|
setPictureDescriptions(checked);
|
||||||
|
updateFlowSettingMutation.mutate({ picture_descriptions: checked });
|
||||||
};
|
};
|
||||||
|
|
||||||
// Helper function to get connector icon
|
// Helper function to get connector icon
|
||||||
|
|
@ -574,7 +593,9 @@ function KnowledgeSourcesPage() {
|
||||||
// Only reset form values if the API call was successful
|
// Only reset form values if the API call was successful
|
||||||
setChunkSize(DEFAULT_KNOWLEDGE_SETTINGS.chunk_size);
|
setChunkSize(DEFAULT_KNOWLEDGE_SETTINGS.chunk_size);
|
||||||
setChunkOverlap(DEFAULT_KNOWLEDGE_SETTINGS.chunk_overlap);
|
setChunkOverlap(DEFAULT_KNOWLEDGE_SETTINGS.chunk_overlap);
|
||||||
setProcessingMode(DEFAULT_KNOWLEDGE_SETTINGS.processing_mode);
|
setTableStructure(false);
|
||||||
|
setOcr(false);
|
||||||
|
setPictureDescriptions(false);
|
||||||
closeDialog(); // Close after successful completion
|
closeDialog(); // Close after successful completion
|
||||||
})
|
})
|
||||||
.catch((error) => {
|
.catch((error) => {
|
||||||
|
|
@ -1068,76 +1089,62 @@ function KnowledgeSourcesPage() {
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div className="space-y-3">
|
<div className="">
|
||||||
<Label className="text-base font-medium">Ingestion presets</Label>
|
<div className="flex items-center justify-between py-3 border-b border-border">
|
||||||
<RadioGroup
|
<div className="flex-1">
|
||||||
value={processingMode}
|
<Label
|
||||||
onValueChange={handleProcessingModeChange}
|
htmlFor="table-structure"
|
||||||
className="space-y-3"
|
className="text-base font-medium cursor-pointer pb-3"
|
||||||
>
|
>
|
||||||
<div className="flex items-center space-x-3">
|
Table Structure
|
||||||
<RadioGroupItem value="standard" id="standard" />
|
</Label>
|
||||||
<div className="flex-1">
|
<div className="text-sm text-muted-foreground">
|
||||||
<Label
|
Capture table structure during ingest.
|
||||||
htmlFor="standard"
|
|
||||||
className="text-base font-medium cursor-pointer"
|
|
||||||
>
|
|
||||||
No OCR
|
|
||||||
</Label>
|
|
||||||
<div className="text-sm text-muted-foreground">
|
|
||||||
Fast ingest for documents with selectable text. Images are
|
|
||||||
ignored.
|
|
||||||
</div>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div className="flex items-center space-x-3">
|
<Switch
|
||||||
<RadioGroupItem value="ocr" id="ocr" />
|
id="table-structure"
|
||||||
<div className="flex-1">
|
checked={tableStructure}
|
||||||
<Label
|
onCheckedChange={handleTableStructureChange}
|
||||||
htmlFor="ocr"
|
/>
|
||||||
className="text-base font-medium cursor-pointer"
|
</div>
|
||||||
>
|
<div className="flex items-center justify-between py-3 border-b border-border">
|
||||||
OCR
|
<div className="flex-1">
|
||||||
</Label>
|
<Label
|
||||||
<div className="text-sm text-muted-foreground">
|
htmlFor="ocr"
|
||||||
Extracts text from images and scanned pages.
|
className="text-base font-medium cursor-pointer pb-3"
|
||||||
</div>
|
>
|
||||||
|
OCR
|
||||||
|
</Label>
|
||||||
|
<div className="text-sm text-muted-foreground">
|
||||||
|
Extracts text from images/PDFs. Ingest is slower when
|
||||||
|
enabled.
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div className="flex items-center space-x-3">
|
<Switch
|
||||||
<RadioGroupItem
|
id="ocr"
|
||||||
value="picture_description"
|
checked={ocr}
|
||||||
id="picture_description"
|
onCheckedChange={handleOcrChange}
|
||||||
/>
|
/>
|
||||||
<div className="flex-1">
|
</div>
|
||||||
<Label
|
<div className="flex items-center justify-between py-3">
|
||||||
htmlFor="picture_description"
|
<div className="flex-1">
|
||||||
className="text-base font-medium cursor-pointer"
|
<Label
|
||||||
>
|
htmlFor="picture-descriptions"
|
||||||
OCR + Captions
|
className="text-base font-medium cursor-pointer pb-3"
|
||||||
</Label>
|
>
|
||||||
<div className="text-sm text-muted-foreground">
|
Picture Descriptions
|
||||||
Extracts text from images and scanned pages. Generates
|
</Label>
|
||||||
short image captions.
|
<div className="text-sm text-muted-foreground">
|
||||||
</div>
|
Adds captions for images. Ingest is slower when enabled.
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
<div className="flex items-center space-x-3">
|
<Switch
|
||||||
<RadioGroupItem value="VLM" id="VLM" />
|
id="picture-descriptions"
|
||||||
<div className="flex-1">
|
checked={pictureDescriptions}
|
||||||
<Label
|
onCheckedChange={handlePictureDescriptionsChange}
|
||||||
htmlFor="VLM"
|
/>
|
||||||
className="text-base font-medium cursor-pointer"
|
</div>
|
||||||
>
|
|
||||||
VLM
|
|
||||||
</Label>
|
|
||||||
<div className="text-sm text-muted-foreground">
|
|
||||||
Extracts text from layout-aware parsing of text, tables,
|
|
||||||
and sections.
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
</div>
|
|
||||||
</RadioGroup>
|
|
||||||
</div>
|
</div>
|
||||||
</div>
|
</div>
|
||||||
</CardContent>
|
</CardContent>
|
||||||
|
|
|
||||||
|
|
@ -1,29 +0,0 @@
|
||||||
"use client"
|
|
||||||
|
|
||||||
import * as React from "react"
|
|
||||||
import * as SwitchPrimitives from "@radix-ui/react-switch"
|
|
||||||
|
|
||||||
import { cn } from "@/lib/utils"
|
|
||||||
|
|
||||||
const Switch = React.forwardRef<
|
|
||||||
React.ElementRef<typeof SwitchPrimitives.Root>,
|
|
||||||
React.ComponentPropsWithoutRef<typeof SwitchPrimitives.Root>
|
|
||||||
>(({ className, ...props }, ref) => (
|
|
||||||
<SwitchPrimitives.Root
|
|
||||||
className={cn(
|
|
||||||
"peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-input",
|
|
||||||
className
|
|
||||||
)}
|
|
||||||
{...props}
|
|
||||||
ref={ref}
|
|
||||||
>
|
|
||||||
<SwitchPrimitives.Thumb
|
|
||||||
className={cn(
|
|
||||||
"pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0"
|
|
||||||
)}
|
|
||||||
/>
|
|
||||||
</SwitchPrimitives.Root>
|
|
||||||
))
|
|
||||||
Switch.displayName = SwitchPrimitives.Root.displayName
|
|
||||||
|
|
||||||
export { Switch }
|
|
||||||
|
|
@ -12,7 +12,9 @@ export const DEFAULT_AGENT_SETTINGS = {
|
||||||
export const DEFAULT_KNOWLEDGE_SETTINGS = {
|
export const DEFAULT_KNOWLEDGE_SETTINGS = {
|
||||||
chunk_size: 1000,
|
chunk_size: 1000,
|
||||||
chunk_overlap: 200,
|
chunk_overlap: 200,
|
||||||
processing_mode: "standard"
|
table_structure: false,
|
||||||
|
ocr: false,
|
||||||
|
picture_descriptions: false
|
||||||
} as const;
|
} as const;
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
|
||||||
|
|
@ -16,35 +16,30 @@ logger = get_logger(__name__)
|
||||||
|
|
||||||
|
|
||||||
# Docling preset configurations
|
# Docling preset configurations
|
||||||
def get_docling_preset_configs():
|
def get_docling_preset_configs(table_structure=False, ocr=False, picture_descriptions=False):
|
||||||
"""Get docling preset configurations with platform-specific settings"""
|
"""Get docling preset configurations based on toggle settings
|
||||||
|
|
||||||
|
Args:
|
||||||
|
table_structure: Enable table structure parsing (default: False)
|
||||||
|
ocr: Enable OCR for text extraction from images (default: False)
|
||||||
|
picture_descriptions: Enable picture descriptions/captions (default: False)
|
||||||
|
"""
|
||||||
is_macos = platform.system() == "Darwin"
|
is_macos = platform.system() == "Darwin"
|
||||||
|
|
||||||
return {
|
config = {
|
||||||
"standard": {"do_ocr": False},
|
"do_ocr": ocr,
|
||||||
"ocr": {"do_ocr": True, "ocr_engine": "ocrmac" if is_macos else "easyocr"},
|
"ocr_engine": "ocrmac" if is_macos else "easyocr",
|
||||||
"picture_description": {
|
"do_table_structure": table_structure,
|
||||||
"do_ocr": True,
|
"do_picture_classification": picture_descriptions,
|
||||||
"ocr_engine": "ocrmac" if is_macos else "easyocr",
|
"do_picture_description": picture_descriptions,
|
||||||
"do_picture_classification": True,
|
"picture_description_local": {
|
||||||
"do_picture_description": True,
|
"repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct",
|
||||||
"picture_description_local": {
|
"prompt": "Describe this image in a few sentences.",
|
||||||
"repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct",
|
}
|
||||||
"prompt": "Describe this image in a few sentences.",
|
|
||||||
},
|
|
||||||
},
|
|
||||||
"VLM": {
|
|
||||||
"pipeline": "vlm",
|
|
||||||
"vlm_pipeline_model_local": {
|
|
||||||
"repo_id": "ds4sd/SmolDocling-256M-preview-mlx-bf16"
|
|
||||||
if is_macos
|
|
||||||
else "ds4sd/SmolDocling-256M-preview",
|
|
||||||
"response_format": "doctags",
|
|
||||||
"inference_framework": "mlx",
|
|
||||||
},
|
|
||||||
},
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
return config
|
||||||
|
|
||||||
|
|
||||||
async def get_settings(request, session_manager):
|
async def get_settings(request, session_manager):
|
||||||
"""Get application settings"""
|
"""Get application settings"""
|
||||||
|
|
@ -70,7 +65,9 @@ async def get_settings(request, session_manager):
|
||||||
"embedding_model": knowledge_config.embedding_model,
|
"embedding_model": knowledge_config.embedding_model,
|
||||||
"chunk_size": knowledge_config.chunk_size,
|
"chunk_size": knowledge_config.chunk_size,
|
||||||
"chunk_overlap": knowledge_config.chunk_overlap,
|
"chunk_overlap": knowledge_config.chunk_overlap,
|
||||||
"doclingPresets": knowledge_config.doclingPresets,
|
"table_structure": knowledge_config.table_structure,
|
||||||
|
"ocr": knowledge_config.ocr,
|
||||||
|
"picture_descriptions": knowledge_config.picture_descriptions,
|
||||||
},
|
},
|
||||||
"agent": {
|
"agent": {
|
||||||
"llm_model": agent_config.llm_model,
|
"llm_model": agent_config.llm_model,
|
||||||
|
|
@ -177,7 +174,9 @@ async def update_settings(request, session_manager):
|
||||||
"system_prompt",
|
"system_prompt",
|
||||||
"chunk_size",
|
"chunk_size",
|
||||||
"chunk_overlap",
|
"chunk_overlap",
|
||||||
"doclingPresets",
|
"table_structure",
|
||||||
|
"ocr",
|
||||||
|
"picture_descriptions",
|
||||||
"embedding_model",
|
"embedding_model",
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -256,32 +255,68 @@ async def update_settings(request, session_manager):
|
||||||
# Don't fail the entire settings update if flow update fails
|
# Don't fail the entire settings update if flow update fails
|
||||||
# The config will still be saved
|
# The config will still be saved
|
||||||
|
|
||||||
if "doclingPresets" in body:
|
if "table_structure" in body:
|
||||||
preset_configs = get_docling_preset_configs()
|
if not isinstance(body["table_structure"], bool):
|
||||||
valid_presets = list(preset_configs.keys())
|
|
||||||
if body["doclingPresets"] not in valid_presets:
|
|
||||||
return JSONResponse(
|
return JSONResponse(
|
||||||
{
|
{"error": "table_structure must be a boolean"}, status_code=400
|
||||||
"error": f"doclingPresets must be one of: {', '.join(valid_presets)}"
|
|
||||||
},
|
|
||||||
status_code=400,
|
|
||||||
)
|
)
|
||||||
current_config.knowledge.doclingPresets = body["doclingPresets"]
|
current_config.knowledge.table_structure = body["table_structure"]
|
||||||
config_updated = True
|
config_updated = True
|
||||||
|
|
||||||
# Also update the flow with the new docling preset
|
# Also update the flow with the new docling settings
|
||||||
try:
|
try:
|
||||||
flows_service = _get_flows_service()
|
flows_service = _get_flows_service()
|
||||||
await flows_service.update_flow_docling_preset(
|
preset_config = get_docling_preset_configs(
|
||||||
body["doclingPresets"], preset_configs[body["doclingPresets"]]
|
table_structure=body["table_structure"],
|
||||||
)
|
ocr=current_config.knowledge.ocr,
|
||||||
logger.info(
|
picture_descriptions=current_config.knowledge.picture_descriptions
|
||||||
f"Successfully updated docling preset in flow to '{body['doclingPresets']}'"
|
|
||||||
)
|
)
|
||||||
|
await flows_service.update_flow_docling_preset("custom", preset_config)
|
||||||
|
logger.info(f"Successfully updated table_structure setting in flow")
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.error(f"Failed to update docling preset in flow: {str(e)}")
|
logger.error(f"Failed to update docling settings in flow: {str(e)}")
|
||||||
# Don't fail the entire settings update if flow update fails
|
|
||||||
# The config will still be saved
|
if "ocr" in body:
|
||||||
|
if not isinstance(body["ocr"], bool):
|
||||||
|
return JSONResponse(
|
||||||
|
{"error": "ocr must be a boolean"}, status_code=400
|
||||||
|
)
|
||||||
|
current_config.knowledge.ocr = body["ocr"]
|
||||||
|
config_updated = True
|
||||||
|
|
||||||
|
# Also update the flow with the new docling settings
|
||||||
|
try:
|
||||||
|
flows_service = _get_flows_service()
|
||||||
|
preset_config = get_docling_preset_configs(
|
||||||
|
table_structure=current_config.knowledge.table_structure,
|
||||||
|
ocr=body["ocr"],
|
||||||
|
picture_descriptions=current_config.knowledge.picture_descriptions
|
||||||
|
)
|
||||||
|
await flows_service.update_flow_docling_preset("custom", preset_config)
|
||||||
|
logger.info(f"Successfully updated ocr setting in flow")
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Failed to update docling settings in flow: {str(e)}")
|
||||||
|
|
||||||
|
if "picture_descriptions" in body:
|
||||||
|
if not isinstance(body["picture_descriptions"], bool):
|
||||||
|
return JSONResponse(
|
||||||
|
{"error": "picture_descriptions must be a boolean"}, status_code=400
|
||||||
|
)
|
||||||
|
current_config.knowledge.picture_descriptions = body["picture_descriptions"]
|
||||||
|
config_updated = True
|
||||||
|
|
||||||
|
# Also update the flow with the new docling settings
|
||||||
|
try:
|
||||||
|
flows_service = _get_flows_service()
|
||||||
|
preset_config = get_docling_preset_configs(
|
||||||
|
table_structure=current_config.knowledge.table_structure,
|
||||||
|
ocr=current_config.knowledge.ocr,
|
||||||
|
picture_descriptions=body["picture_descriptions"]
|
||||||
|
)
|
||||||
|
await flows_service.update_flow_docling_preset("custom", preset_config)
|
||||||
|
logger.info(f"Successfully updated picture_descriptions setting in flow")
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"Failed to update docling settings in flow: {str(e)}")
|
||||||
|
|
||||||
if "chunk_size" in body:
|
if "chunk_size" in body:
|
||||||
if not isinstance(body["chunk_size"], int) or body["chunk_size"] <= 0:
|
if not isinstance(body["chunk_size"], int) or body["chunk_size"] <= 0:
|
||||||
|
|
@ -625,48 +660,56 @@ def _get_flows_service():
|
||||||
|
|
||||||
|
|
||||||
async def update_docling_preset(request, session_manager):
|
async def update_docling_preset(request, session_manager):
|
||||||
"""Update docling preset in the ingest flow"""
|
"""Update docling settings in the ingest flow - deprecated endpoint, use /settings instead"""
|
||||||
try:
|
try:
|
||||||
# Parse request body
|
# Parse request body
|
||||||
body = await request.json()
|
body = await request.json()
|
||||||
|
|
||||||
# Validate preset parameter
|
# Support old preset-based API for backwards compatibility
|
||||||
if "preset" not in body:
|
if "preset" in body:
|
||||||
return JSONResponse(
|
# Map old presets to new toggle settings
|
||||||
{"error": "preset parameter is required"}, status_code=400
|
preset_map = {
|
||||||
)
|
"standard": {"table_structure": False, "ocr": False, "picture_descriptions": False},
|
||||||
|
"ocr": {"table_structure": False, "ocr": True, "picture_descriptions": False},
|
||||||
|
"picture_description": {"table_structure": False, "ocr": True, "picture_descriptions": True},
|
||||||
|
"VLM": {"table_structure": False, "ocr": False, "picture_descriptions": False},
|
||||||
|
}
|
||||||
|
|
||||||
preset = body["preset"]
|
preset = body["preset"]
|
||||||
preset_configs = get_docling_preset_configs()
|
if preset not in preset_map:
|
||||||
|
return JSONResponse(
|
||||||
|
{"error": f"Invalid preset '{preset}'. Valid presets: {', '.join(preset_map.keys())}"},
|
||||||
|
status_code=400,
|
||||||
|
)
|
||||||
|
|
||||||
if preset not in preset_configs:
|
settings = preset_map[preset]
|
||||||
valid_presets = list(preset_configs.keys())
|
else:
|
||||||
return JSONResponse(
|
# Support new toggle-based API
|
||||||
{
|
settings = {
|
||||||
"error": f"Invalid preset '{preset}'. Valid presets: {', '.join(valid_presets)}"
|
"table_structure": body.get("table_structure", False),
|
||||||
},
|
"ocr": body.get("ocr", False),
|
||||||
status_code=400,
|
"picture_descriptions": body.get("picture_descriptions", False),
|
||||||
)
|
}
|
||||||
|
|
||||||
# Get the preset configuration
|
# Get the preset configuration
|
||||||
preset_config = preset_configs[preset]
|
preset_config = get_docling_preset_configs(**settings)
|
||||||
|
|
||||||
# Use the helper function to update the flow
|
# Use the helper function to update the flow
|
||||||
flows_service = _get_flows_service()
|
flows_service = _get_flows_service()
|
||||||
await flows_service.update_flow_docling_preset(preset, preset_config)
|
await flows_service.update_flow_docling_preset("custom", preset_config)
|
||||||
|
|
||||||
logger.info(f"Successfully updated docling preset to '{preset}' in ingest flow")
|
logger.info(f"Successfully updated docling settings in ingest flow")
|
||||||
|
|
||||||
return JSONResponse(
|
return JSONResponse(
|
||||||
{
|
{
|
||||||
"message": f"Successfully updated docling preset to '{preset}'",
|
"message": f"Successfully updated docling settings",
|
||||||
"preset": preset,
|
"settings": settings,
|
||||||
"preset_config": preset_config,
|
"preset_config": preset_config,
|
||||||
}
|
}
|
||||||
)
|
)
|
||||||
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
logger.error("Failed to update docling preset", error=str(e))
|
logger.error("Failed to update docling settings", error=str(e))
|
||||||
return JSONResponse(
|
return JSONResponse(
|
||||||
{"error": f"Failed to update docling preset: {str(e)}"}, status_code=500
|
{"error": f"Failed to update docling settings: {str(e)}"}, status_code=500
|
||||||
)
|
)
|
||||||
|
|
|
||||||
|
|
@ -27,7 +27,9 @@ class KnowledgeConfig:
|
||||||
embedding_model: str = "text-embedding-3-small"
|
embedding_model: str = "text-embedding-3-small"
|
||||||
chunk_size: int = 1000
|
chunk_size: int = 1000
|
||||||
chunk_overlap: int = 200
|
chunk_overlap: int = 200
|
||||||
doclingPresets: str = "standard"
|
table_structure: bool = False
|
||||||
|
ocr: bool = False
|
||||||
|
picture_descriptions: bool = False
|
||||||
|
|
||||||
|
|
||||||
@dataclass
|
@dataclass
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue