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

no-static-default-onboarding-behavior

Browse source
This commit is contained in:
Mendon Kissling 2025-09-26 13:35:42 -04:00
parent 2c68c5e554
commit 8d400e9c7d
1 changed files with 6 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
docs/docs/core-components/knowledge.mdx
View file

@ -134,15 +134,14 @@ A new filter is created with default settings that match everything.
## OpenRAG default configuration
OpenRAG creates a specialized OpenSearch index called `documents` with the values defined at `src/config/settings.py`.
* **Vector Dimensions**: 1536-dimensional embeddings using OpenAI's `text-embedding-3-small` model.
* **KNN Vector Type**: Uses `knn_vector` field type with `disk_ann` method and `jvector` engine.
* **Distance Metric**: L2 (Euclidean) distance for vector similarity.
* **Performance Optimization**: Configured with `ef_construction: 100` and `m: 16` parameters.
OpenRAG supports hybrid search, which combines semantic and keyword search.
OpenRAG automatically detects and configures the correct vector dimensions for embedding models, ensuring optimal search performance and compatibility.
The complete list of supported models is available at [/src/services/models_service.py](https://github.com/langflow-ai/openrag/blob/main/src/services/models_service.py).
You can use custom embedding models by specifying them in your configuration.
If you use an unknown embedding model, OpenRAG will automatically fall back to `1536` dimensions and log a warning. The system will continue to work, but search quality may be affected if the actual model dimensions differ from `1536`.
The default embedding dimension is `1536` and the default model is `text-embedding-3-small`.
For models with known vector dimensions, see [/src/config/settings.py](https://github.com/langflow-ai/openrag/blob/main/src/config/settings.py).