gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

slight-cleanup

Browse source
This commit is contained in:
Mendon Kissling 2025-09-29 17:09:53 -04:00
parent 19bb003b01
commit f45441a9e5
1 changed files with 80 additions and 47 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

127
docs/docs/configure/configuration.md
View file

@ -1,48 +1,20 @@
--- ---
title: Configuration title: Environment variables and configuration values
slug: /configure/configuration slug: /configure/configuration
--- ---
# Configuration
OpenRAG supports multiple configuration methods with the following priority: OpenRAG supports multiple configuration methods with the following priority:
1. **Environment Variables** (highest priority) 1. **Environment Variables** (highest priority)
2. **Configuration File** (`config.yaml`) 2. **Configuration File** (`config.yaml`)
3. **Langflow Flow Settings** (runtime override) 3. **Default Values** (fallback)
4. **Default Values** (fallback)
## Configuration File ## Environment variables
Create a `config.yaml` file in the project root to configure OpenRAG: Environment variables will override configuration file settings.
You can create a `.env` file in the project root to set these variables.
```yaml ## Required variables
# OpenRAG Configuration File
provider:
model_provider: "openai" # openai, anthropic, azure, etc.
api_key: "your-api-key" # or use OPENAI_API_KEY env var
knowledge:
embedding_model: "text-embedding-3-small"
chunk_size: 1000
chunk_overlap: 200
ocr: true
picture_descriptions: false
agent:
llm_model: "gpt-4o-mini"
system_prompt: "You are a helpful AI assistant..."
```
## Environment Variables
Environment variables will override configuration file settings. You can still use `.env` files:
```bash
cp .env.example .env
```
## Required Variables
| Variable | Description | | Variable | Description |
| ----------------------------- | ------------------------------------------- | | ----------------------------- | ------------------------------------------- |
@ -54,7 +26,7 @@ cp .env.example .env
| `LANGFLOW_INGEST_FLOW_ID` | ID of your Langflow ingestion flow | | `LANGFLOW_INGEST_FLOW_ID` | ID of your Langflow ingestion flow |
| `NUDGES_FLOW_ID` | ID of your Langflow nudges/suggestions flow | | `NUDGES_FLOW_ID` | ID of your Langflow nudges/suggestions flow |
## Ingestion Configuration ## Ingestion configuration
| Variable | Description | | Variable | Description |
| ------------------------------ | ------------------------------------------------------ | | ------------------------------ | ------------------------------------------------------ |
@ -63,10 +35,14 @@ cp .env.example .env
- `false` or unset: Uses Langflow pipeline (upload → ingest → delete) - `false` or unset: Uses Langflow pipeline (upload → ingest → delete)
- `true`: Uses traditional OpenRAG processor for document ingestion - `true`: Uses traditional OpenRAG processor for document ingestion
## Optional Variables ## Optional variables
| Variable | Description | | Variable | Description |
| ------------------------------------------------------------------------- | ------------------------------------------------------------------ | | ------------------------------------------------------------------------- | ------------------------------------------------------------------ |
| `OPENSEARCH_HOST` | OpenSearch host (default: `localhost`) |
| `OPENSEARCH_PORT` | OpenSearch port (default: `9200`) |
| `OPENSEARCH_USERNAME` | OpenSearch username (default: `admin`) |
| `LANGFLOW_URL` | Langflow URL (default: `http://localhost:7860`) |
| `LANGFLOW_PUBLIC_URL` | Public URL for Langflow (default: `http://localhost:7860`) | | `LANGFLOW_PUBLIC_URL` | Public URL for Langflow (default: `http://localhost:7860`) |
| `GOOGLE_OAUTH_CLIENT_ID` / `GOOGLE_OAUTH_CLIENT_SECRET` | Google OAuth authentication | | `GOOGLE_OAUTH_CLIENT_ID` / `GOOGLE_OAUTH_CLIENT_SECRET` | Google OAuth authentication |
| `MICROSOFT_GRAPH_OAUTH_CLIENT_ID` / `MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET` | Microsoft OAuth | | `MICROSOFT_GRAPH_OAUTH_CLIENT_ID` / `MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET` | Microsoft OAuth |
@ -75,20 +51,27 @@ cp .env.example .env
| `SESSION_SECRET` | Session management (default: auto-generated, change in production) | | `SESSION_SECRET` | Session management (default: auto-generated, change in production) |
| `LANGFLOW_KEY` | Explicit Langflow API key (auto-generated if not provided) | | `LANGFLOW_KEY` | Explicit Langflow API key (auto-generated if not provided) |
| `LANGFLOW_SECRET_KEY` | Secret key for Langflow internal operations | | `LANGFLOW_SECRET_KEY` | Secret key for Langflow internal operations |
| `DOCLING_OCR_ENGINE` | OCR engine for document processing |
| `LANGFLOW_AUTO_LOGIN` | Enable auto-login for Langflow (default: `False`) |
| `LANGFLOW_NEW_USER_IS_ACTIVE` | New users are active by default (default: `False`) |
| `LANGFLOW_ENABLE_SUPERUSER_CLI` | Enable superuser CLI (default: `False`) |
| `OPENRAG_DOCUMENTS_PATHS` | Document paths for ingestion (default: `./documents`) |
## OpenRAG Configuration Variables ## OpenRAG configuration variables
These environment variables override settings in `config.yaml`: These environment variables override settings in `config.yaml`:
### Provider Settings ### Provider settings
| Variable | Description | Default | | Variable | Description | Default |
| ------------------ | ---------------------------------------- | -------- | | -------------------- | ---------------------------------------- | -------- |
| `MODEL_PROVIDER` | Model provider (openai, anthropic, etc.) | `openai` | | `MODEL_PROVIDER` | Model provider (openai, anthropic, etc.) | `openai` |
| `PROVIDER_API_KEY` | API key for the model provider | | | `PROVIDER_API_KEY` | API key for the model provider | |
| `OPENAI_API_KEY` | OpenAI API key (backward compatibility) | | | `PROVIDER_ENDPOINT` | Custom provider endpoint (e.g., Watson) | |
| `PROVIDER_PROJECT_ID`| Project ID for providers (e.g., Watson) | |
| `OPENAI_API_KEY` | OpenAI API key (backward compatibility) | |
### Knowledge Settings ### Knowledge settings
| Variable | Description | Default | | Variable | Description | Default |
| ------------------------------ | --------------------------------------- | ------------------------ | | ------------------------------ | --------------------------------------- | ------------------------ |
@ -98,11 +81,61 @@ These environment variables override settings in `config.yaml`:
| `OCR_ENABLED` | Enable OCR for image processing | `true` | | `OCR_ENABLED` | Enable OCR for image processing | `true` |
| `PICTURE_DESCRIPTIONS_ENABLED` | Enable picture descriptions | `false` | | `PICTURE_DESCRIPTIONS_ENABLED` | Enable picture descriptions | `false` |
### Agent Settings ### Agent settings
| Variable | Description | Default | | Variable | Description | Default |
| --------------- | --------------------------------- | ------------------------ | | --------------- | --------------------------------- | ------------------------ |
| `LLM_MODEL` | Language model for the chat agent | `gpt-4o-mini` | | `LLM_MODEL` | Language model for the chat agent | `gpt-4o-mini` |
| `SYSTEM_PROMPT` | System prompt for the agent | Default assistant prompt | | `SYSTEM_PROMPT` | System prompt for the agent | "You are a helpful AI assistant with access to a knowledge base. Answer questions based on the provided context." |
See `.env.example` for a complete list with descriptions, and `docker-compose*.yml` for runtime usage. See `docker-compose-*.yml` files for runtime usage examples.
## Configuration file
Create a `config.yaml` file in the project root to configure OpenRAG:
```yaml
# OpenRAG Configuration File
provider:
model_provider: "openai" # openai, anthropic, azure, etc.
api_key: "your-api-key" # or use OPENAI_API_KEY env var
endpoint: "" # For custom provider endpoints (e.g., Watson/IBM)
project_id: "" # For providers that need project IDs (e.g., Watson/IBM)
knowledge:
embedding_model: "text-embedding-3-small"
chunk_size: 1000
chunk_overlap: 200
doclingPresets: "standard" # standard, ocr, picture_description, VLM
ocr: true
picture_descriptions: false
agent:
llm_model: "gpt-4o-mini"
system_prompt: "You are a helpful AI assistant with access to a knowledge base. Answer questions based on the provided context."
```
## Default Values and Fallbacks
When no environment variables or configuration file values are provided, OpenRAG uses default values.
These values can be found in the code base at the following locations.
### OpenRAG configuration defaults
These values are are defined in `src/config/config_manager.py`.
### System configuration defaults
These fallback values are defined in `src/config/settings.py`.
### TUI default values
These values are defined in `src/tui/managers/env_manager.py`.
### Frontend default values
These values are defined in `frontend/src/lib/constants.ts`.
### Docling preset configurations
These values are defined in `src/api/settings.py`.