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

direct-file-upload

Browse source
This commit is contained in:
Mendon Kissling 2025-09-25 14:56:22 -04:00
parent 85b1ec33a2
commit 0288f36655
1 changed files with 27 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
docs/docs/core-components/knowledge.mdx
View file

@ -11,23 +11,14 @@ import PartialModifyFlows from '@site/docs/_partial-modify-flows.mdx';
OpenRAG uses [OpenSearch](https://docs.opensearch.org/latest/) for its vector-backed knowledge store.
OpenSearch provides powerful hybrid search capabilities with enterprise-grade security and multi-tenancy support.
## 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.
## Explore knowledge
To explore your current knowledge, click <Icon name="Library" aria-hidden="true"/> **Knowledge**.
The Knowledge page lists the documents OpenRAG has ingested into the OpenSearch vector database's `documents` index.
To explore your current knowledge, click <Icon name="Library" aria-hidden="true"/> **Knowledge**.
Click on a document to display the chunks derived from splitting the default documents into the vector database.
Documents are processed with the **Knowledge Ingest** flow, so to split your documents differently, edit the **Knowledge Ingest** flow.
Documents are processed with the default **Knowledge Ingest** flow, so if you want to split your documents differently, edit the **Knowledge Ingest** flow.
<PartialModifyFlows />
@ -35,12 +26,19 @@ Documents are processed with the **Knowledge Ingest** flow, so to split your doc
OpenRAG supports knowledge ingestion through direct file uploads and OAuth connectors.
### Upload files
### Direct file ingestion
- Files uploaded directly through the web interface
- Processed immediately using the standard pipeline
The **Knowledge Ingest** flow uses Langflow's [**File** component](https://docs.langflow.org/components-data#file) to split and embed files loaded from your local machine into the OpenSearch database.
### Upload files through OAuth connectors
The default path to your local folder is mounted from the `./documents` folder in your OpenRAG project directory to the `/app/documents/` directory inside the Docker container. Files added to the host or the container will be visible in both locations. To configure this location, modify the **Documents Paths** variable in either the TUI's [Advanced Setup](/install#advanced-setup) or in the `.env` used by Docker Compose. Add multiple paths in a comma-separated list with no spaces. For example, `./documents,/Users/username/Documents`.
To load and process a single file from the mapped location, click <Icon name="Plus" aria-hidden="true"/> **Add Knowledge**, and then click **Add File**.
The file is loaded into your OpenSearch database, and appears in the Knowledge page.
To load and process a directory from the mapped location, click <Icon name="Plus" aria-hidden="true"/> **Add Knowledge**, and then click **Process Folder**.
The files are loaded into your OpenSearch database, and appear in the Knowledge page.
### Ingest files through OAuth connectors
OpenRAG supports the following enterprise-grade OAuth connectors for seamless document synchronization.
@ -98,4 +96,17 @@ OpenRAG includes a knowledge filter system for organizing and managing document
## 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.