From cb61a48c2b16300a3de6364b91c11d8dfbff7b0c Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 11:04:17 -0400
Subject: [PATCH 1/9] init
---
config.yaml | 31 -------------------------
docs/docs/core-components/knowledge.mdx | 4 ++++
docs/sidebars.js | 5 ++++
3 files changed, 9 insertions(+), 31 deletions(-)
delete mode 100644 config.yaml
create mode 100644 docs/docs/core-components/knowledge.mdx
diff --git a/config.yaml b/config.yaml
deleted file mode 100644
index 3bafb8bd..00000000
--- a/config.yaml
+++ /dev/null
@@ -1,31 +0,0 @@
-# OpenRAG Configuration File
-# This file allows you to configure OpenRAG settings.
-# Environment variables will override these settings unless edited is true.
-
-# Track if this config has been manually edited (prevents env var overrides)
-edited: false
-
-# Model provider configuration
-provider:
- # Supported providers: "openai", "anthropic", "azure", etc.
- model_provider: "openai"
- # API key for the model provider (can also be set via OPENAI_API_KEY env var)
- api_key: ""
-
-# Knowledge base and document processing configuration
-knowledge:
- # Embedding model for vector search
- embedding_model: "text-embedding-3-small"
- # Text chunk size for document processing
- chunk_size: 1000
- # Overlap between chunks
- chunk_overlap: 200
- # Docling preset setting
- doclingPresets: standard
-
-# AI agent configuration
-agent:
- # Language model for the chat agent
- llm_model: "gpt-4o-mini"
- # System prompt for the agent
- system_prompt: "You are a helpful AI assistant with access to a knowledge base. Answer questions based on the provided context."
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
new file mode 100644
index 00000000..67f1ef24
--- /dev/null
+++ b/docs/docs/core-components/knowledge.mdx
@@ -0,0 +1,4 @@
+---
+title: Knowledge stored with OpenSearch
+slug: /knowledge
+---
\ No newline at end of file
diff --git a/docs/sidebars.js b/docs/sidebars.js
index f76fdcda..c4226946 100644
--- a/docs/sidebars.js
+++ b/docs/sidebars.js
@@ -56,6 +56,11 @@ const sidebars = {
id: "core-components/agents",
label: "Langflow Agents"
},
+ {
+ type: "doc",
+ id: "core-components/knowledge",
+ label: "Knowledge stored with OpenSearch"
+ }
],
},
{
From 85b1ec33a28d981e0fa20070f25ee88fa028b138 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 14:27:09 -0400
Subject: [PATCH 2/9] oauth-connector-knowledge-ingest
---
docs/docs/_partial-modify-flows.mdx | 5 ++
docs/docs/core-components/agents.mdx | 11 ++-
docs/docs/core-components/knowledge.mdx | 99 ++++++++++++++++++++++++-
docs/docs/get-started/quickstart.mdx | 4 +-
4 files changed, 112 insertions(+), 7 deletions(-)
create mode 100644 docs/docs/_partial-modify-flows.mdx
diff --git a/docs/docs/_partial-modify-flows.mdx b/docs/docs/_partial-modify-flows.mdx
new file mode 100644
index 00000000..852777e5
--- /dev/null
+++ b/docs/docs/_partial-modify-flows.mdx
@@ -0,0 +1,5 @@
+import Icon from "@site/src/components/icon/icon";
+
+All flows included with OpenRAG are designed to be modular, performant, and provider-agnostic.
+To modify a flow, click **Settings**, and click **Edit in Langflow**.
+Flows are edited in the same way as in the [Langflow visual editor](https://docs.langflow.org/concepts-overview).
\ No newline at end of file
diff --git a/docs/docs/core-components/agents.mdx b/docs/docs/core-components/agents.mdx
index 121ca3d5..8388bd60 100644
--- a/docs/docs/core-components/agents.mdx
+++ b/docs/docs/core-components/agents.mdx
@@ -3,6 +3,11 @@ title: Agents powered by Langflow
slug: /agents
---
+import Icon from "@site/src/components/icon/icon";
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+import PartialModifyFlows from '@site/docs/_partial-modify-flows.mdx';
+
OpenRAG leverages Langflow's Agent component to power the OpenRAG Open Search Agent flow.
This flow intelligently chats with your knowledge by embedding your query, comparing it the vector database embeddings, and generating a response with the LLM.
@@ -25,7 +30,7 @@ In an agentic context, tools are functions that the agent can run to perform tas
## Use the OpenRAG Open Search Agent flow
If you've chatted with your knowledge in OpenRAG, you've already experienced the OpenRAG Open Search Agent chat flow.
-To view the flow, click **Settings**, and then click **Edit in Langflow**.
+To view the flow, click **Settings**, and then click **Edit in Langflow**.
This flow contains seven components:
* The Agent component orchestrates the entire flow by deciding when to search the knowledge base, how to formulate search queries, and how to combine retrieved information with the user's question to generate a comprehensive response.
@@ -38,9 +43,7 @@ The Agent behaves according to the prompt in the **Agent Instructions** field.
This filter is the Knowledge filter, and filters which knowledge sources to search through.
* The Agent component's Output port is connected to the Chat Output component, which returns the final response to the user or application.
-All flows included with OpenRAG are designed to be modular, performant, and provider-agnostic.
-To modify a flow, click **Settings**, and click **Edit in Langflow**.
-Flows are edited in the same way as in the [Langflow visual editor](https://docs.langflow.org/concepts-overview).
+
For an example of changing out the agent's LLM in OpenRAG, see the [Quickstart](/quickstart#change-components).
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index 67f1ef24..5e003880 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -1,4 +1,101 @@
---
title: Knowledge stored with OpenSearch
slug: /knowledge
----
\ No newline at end of file
+---
+
+import Icon from "@site/src/components/icon/icon";
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+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 **Knowledge**.
+The Knowledge page lists the documents OpenRAG has ingested into the OpenSearch vector database's `documents` index.
+
+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.
+
+
+
+## Ingest knowledge
+
+OpenRAG supports knowledge ingestion through direct file uploads and OAuth connectors.
+
+### Upload files
+
+- Files uploaded directly through the web interface
+- Processed immediately using the standard pipeline
+
+### Upload files through OAuth connectors
+
+OpenRAG supports the following enterprise-grade OAuth connectors for seamless document synchronization.
+
+- **Google Drive**
+- **OneDrive**
+- **AWS**
+
+OAuth integration allows your OpenRAG server to authenticate users and applications through any OAuth 2.0 compliant service. When users or applications connect to your server, they are redirected to your chosen OAuth provider to authenticate. Upon successful authentication, they are granted access to the connector.
+
+Before configuring OAuth in OpenRAG, you must first set up an OAuth application with an external OAuth 2.0 service provider. You must register your OpenRAG server as an OAuth client, and then obtain the `client` and `secret` keys to complete the configuration in OpenRAG.
+
+To add an OAuth connector to OpenRAG, do the following.
+This example uses Google OAuth.
+If you wish to use another provider, add the secrets to another provider.
+
+
+
+ 1. If OpenRAG is running, stop it with **Status** > **Stop Services**.
+ 2. Click **Advanced Setup**.
+ 3. Add the OAuth provider's client and secret key in the [Advanced Setup](/install#advanced-setup) menu.
+ 4. Click **Save Configuration**.
+ The TUI generates a new `.env` file with your OAuth values.
+ 5. Click **Start Container Services**.
+
+
+ 1. Stop the Docker deployment.
+ 2. Add the OAuth provider's client and secret key in the `.env` file for Docker Compose.
+ ```bash
+ GOOGLE_OAUTH_CLIENT_ID='YOUR_OAUTH_CLIENT_ID'
+ GOOGLE_OAUTH_CLIENT_SECRET='YOUR_OAUTH_CLIENT_SECRET'
+ ```
+ 3. Save your `.env`. file.
+ 4. Start the Docker deployment.
+
+
+
+The OpenRAG frontend at `http://localhost:3000` now redirects to an OAuth callback login page for your OAuth provider.
+A successful authentication opens OpenRAG with the required scopes for your connected storage.
+
+To add knowledge from an OAuth-connected storage provider, do the following:
+
+1. Click **Add Knowledge**, and then select the storage provider, for example, **Google Drive**.
+The **Add Cloud Knowledge** page opens.
+2. To add files or folders from the connected storage, click **Add Files**.
+Select the files or folders you want and click **Select**.
+You can select multiples.
+3. When your files are selected, click **Ingest Files**.
+The ingestion process may take some time, depending on the size of your documents.
+4. When ingestion is complete, your documents are available in the Knowledge screen.
+
+## Knowledge Filter System
+
+OpenRAG includes a knowledge filter system for organizing and managing document collections:
+
+
+
+
+
diff --git a/docs/docs/get-started/quickstart.mdx b/docs/docs/get-started/quickstart.mdx
index fe039859..0e53534f 100644
--- a/docs/docs/get-started/quickstart.mdx
+++ b/docs/docs/get-started/quickstart.mdx
@@ -35,9 +35,9 @@ Get started with OpenRAG by loading your knowledge, swapping out your language m
These events log the agent's request to the tool and the tool's response, so you have direct visibility into your agent's functionality.
If you aren't getting the results you need, you can further tune the knowledge ingestion and agent behavior in the next section.
-## Swap out the language model to modify agent behavior {change-components}
+## Swap out the language model to modify agent behavior {#change-components}
-To modify the knowledge ingestion or Agent behavior, click **Settings**.
+To modify the knowledge ingestion or Agent behavior, click **Settings**.
In this example, you'll try a different LLM to demonstrate how the Agent's response changes.
From 0288f366550a22fb5357269d45b04e2218debfde Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 14:56:22 -0400
Subject: [PATCH 3/9] direct-file-upload
---
docs/docs/core-components/knowledge.mdx | 43 ++++++++++++++++---------
1 file changed, 27 insertions(+), 16 deletions(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index 5e003880..ff8a3bd5 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -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 **Knowledge**.
The Knowledge page lists the documents OpenRAG has ingested into the OpenSearch vector database's `documents` index.
+To explore your current knowledge, click **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.
@@ -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 **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 **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.
+
+
+
+
From acc3a0adf8a01118e2a0d8cd2ba00cbc1b325ad6 Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 15:15:22 -0400
Subject: [PATCH 4/9] sync-cloud-conns
---
docs/docs/core-components/knowledge.mdx | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index ff8a3bd5..92a285d3 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -89,12 +89,22 @@ You can select multiples.
The ingestion process may take some time, depending on the size of your documents.
4. When ingestion is complete, your documents are available in the Knowledge screen.
-## Knowledge Filter System
+### Sync cloud connectors
-OpenRAG includes a knowledge filter system for organizing and managing document collections:
+Your connected data sources are found in the **Settings** page.
+When you click **Sync Now** for a connected cloud service like Google Drive, OpenRAG scans your connected Google Drive account to find files that match your sync criteria. Sync criteria are controlled in **Sync Settings** on the same page. You can sync all files, or select a maximum number of files to sync.
+For each file found, OpenRAG downloads, converts, and embeds the processed content into OpenSearch.
+You can monitor the sync progress in the **Tasks** sidebar.
+
+Once processing is complete, the synced documents become available in your knowledge base and can be searched through the chat interface or Knowledge page.
+
+## Knowledge filters
+
+OpenRAG includes a knowledge filter system for organizing and managing document collections.
+Knowledge filters are saved search configurations that allow you to create custom views of your document collection. They store search queries, filter criteria, and display settings that can be reused across different parts of the application.
## OpenRAG default configuration
From 13b54eb44317711b663a85b7394aaa1d59b005aa Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 16:23:44 -0400
Subject: [PATCH 5/9] filter-knowledge
---
docs/docs/core-components/knowledge.mdx | 44 ++++++++++++++++++++-----
docs/sidebars.js | 2 +-
2 files changed, 36 insertions(+), 10 deletions(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index 92a285d3..7c5105b2 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -1,5 +1,5 @@
---
-title: Knowledge stored with OpenSearch
+title: OpenSearch Knowledge
slug: /knowledge
---
@@ -46,9 +46,9 @@ OpenRAG supports the following enterprise-grade OAuth connectors for seamless do
- **OneDrive**
- **AWS**
-OAuth integration allows your OpenRAG server to authenticate users and applications through any OAuth 2.0 compliant service. When users or applications connect to your server, they are redirected to your chosen OAuth provider to authenticate. Upon successful authentication, they are granted access to the connector.
+OAuth integration allows individual users to connect their personal cloud storage accounts to OpenRAG. Each user must separately authorize OpenRAG to access their own cloud storage files. When a user connects a cloud service, they are redirected to authenticate with that service provider and grant OpenRAG permission to sync documents from their personal cloud storage.
-Before configuring OAuth in OpenRAG, you must first set up an OAuth application with an external OAuth 2.0 service provider. You must register your OpenRAG server as an OAuth client, and then obtain the `client` and `secret` keys to complete the configuration in OpenRAG.
+Before users can connect their cloud storage accounts, you must configure OAuth credentials in OpenRAG. This requires registering OpenRAG as an OAuth application with a cloud provider and obtaining client ID and secret keys for each service you want to support.
To add an OAuth connector to OpenRAG, do the following.
This example uses Google OAuth.
@@ -101,18 +101,44 @@ You can monitor the sync progress in the
Once processing is complete, the synced documents become available in your knowledge base and can be searched through the chat interface or Knowledge page.
-## Knowledge filters
+## Create knowledge filters
OpenRAG includes a knowledge filter system for organizing and managing document collections.
-Knowledge filters are saved search configurations that allow you to create custom views of your document collection. They store search queries, filter criteria, and display settings that can be reused across different parts of the application.
+Knowledge filters are saved search configurations that allow you to create custom views of your document collection. They store search queries, filter criteria, and display settings that can be reused across different parts of OpenRAG.
+
+Knowledge filters help agents work more efficiently with large document collections by focusing their context within relevant documents sets.
+
+To create a knowledge filter, do the following:
+
+1. Click **All Knowledge**, and then click **Create New Filter**.
+ The **Create New Knowledge Filter** pane appears.
+2. Enter a **Name** and **Description**, and then click **Create Filter**.
+A new filter is created with default settings that match everything.
+3. To modify the default filter, click **All Knowledge**, and then click your new filter to edit it in the **Knowledge Filter** pane.
+
+ The following filter options are configurable.
+
+ * **Search Query**: Enter text for semantic search, such as "financial reports from Q4".
+ * **Data Sources**: Select specific data sources or folders to include.
+ * **Document Types**: Filter by file type.
+ * **Owners**: Filter by who uploaded the documents.
+ * **Sources**: Filter by connector types, such as local upload or Google Drive.
+ * **Result Limit**: Set maximum number of results. The default is `10`.
+ * **Score Threshold**: Set minimum relevance score. The default score is `0`.
+
+4. When you're done editing the filter, click **Save Configuration**.
+
+5. To apply the filter to OpenRAG globally, click **All Knowledge**, and then select the filter to apply.
+
+ To apply the filter to a single chat session, in the **Chat** window, click **@**, and then select the filter to apply.
## 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.
+* **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.
diff --git a/docs/sidebars.js b/docs/sidebars.js
index c4226946..3048cb70 100644
--- a/docs/sidebars.js
+++ b/docs/sidebars.js
@@ -59,7 +59,7 @@ const sidebars = {
{
type: "doc",
id: "core-components/knowledge",
- label: "Knowledge stored with OpenSearch"
+ label: "OpenSearch Knowledge"
}
],
},
From b8e5937d0940cbd46c72ac72ad547dbd20bb7c5d Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Thu, 25 Sep 2025 17:08:19 -0400
Subject: [PATCH 6/9] oauth-ingestion-anchor
---
docs/docs/core-components/knowledge.mdx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index 7c5105b2..d8160f8b 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -38,7 +38,7 @@ The file is loaded into your OpenSearch database, and appears in the Knowledge p
To load and process a directory from the mapped location, click **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
+### Ingest files through OAuth connectors (#oauth-ingestion)
OpenRAG supports the following enterprise-grade OAuth connectors for seamless document synchronization.
From 220ab93214f04960acba96fc9a19c92051c0622d Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:36:28 -0400
Subject: [PATCH 7/9] opensearch-syntax
---
docs/docs/core-components/agents.mdx | 8 ++++----
docs/docs/get-started/quickstart.mdx | 6 +++---
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/docs/docs/core-components/agents.mdx b/docs/docs/core-components/agents.mdx
index a5bfbb31..1ecdb1cc 100644
--- a/docs/docs/core-components/agents.mdx
+++ b/docs/docs/core-components/agents.mdx
@@ -9,7 +9,7 @@ import TabItem from '@theme/TabItem';
import PartialModifyFlows from '@site/docs/_partial-modify-flows.mdx';
-OpenRAG leverages Langflow's Agent component to power the OpenRAG Open Search Agent flow.
+OpenRAG leverages Langflow's Agent component to power the OpenRAG OpenSearch Agent flow.
This flow intelligently chats with your knowledge by embedding your query, comparing it the vector database embeddings, and generating a response with the LLM.
@@ -28,9 +28,9 @@ In an agentic context, tools are functions that the agent can run to perform tas
-## Use the OpenRAG Open Search Agent flow
+## Use the OpenRAG OpenSearch Agent flow
-If you've chatted with your knowledge in OpenRAG, you've already experienced the OpenRAG Open Search Agent chat flow.
+If you've chatted with your knowledge in OpenRAG, you've already experienced the OpenRAG OpenSearch Agent chat flow.
To view the flow, click **Settings**, and then click **Edit in Langflow**.
This flow contains seven components:
@@ -39,7 +39,7 @@ The Agent behaves according to the prompt in the **Agent Instructions** field.
* The Chat Input component is connected to the Agent component's Input port. This allows to flow to be triggered by an incoming prompt from a user or application.
* The OpenSearch component is connected to the Agent component's Tools port. The agent may not use this database for every request; the agent only uses this connection if it decides the knowledge can help respond to the prompt.
* The Language Model component is connected to the Agent component's Language Model port. The agent uses the connected LLM to reason through the request sent through Chat Input.
-* The Embedding Model component is connected to the Open Search component's Embedding port. This component converts text queries into vector representations that are compared with document embeddings stored in OpenSearch for semantic similarity matching. This gives your Agent's queries context.
+* The Embedding Model component is connected to the OpenSearch component's Embedding port. This component converts text queries into vector representations that are compared with document embeddings stored in OpenSearch for semantic similarity matching. This gives your Agent's queries context.
* The Text Input component is populated with the global variable `OPENRAG-QUERY-FILTER`.
This filter is the Knowledge filter, and filters which knowledge sources to search through.
* The Agent component's Output port is connected to the Chat Output component, which returns the final response to the user or application.
diff --git a/docs/docs/get-started/quickstart.mdx b/docs/docs/get-started/quickstart.mdx
index 0e53534f..748a8078 100644
--- a/docs/docs/get-started/quickstart.mdx
+++ b/docs/docs/get-started/quickstart.mdx
@@ -16,7 +16,7 @@ Get started with OpenRAG by loading your knowledge, swapping out your language m
## Find your way around
1. In OpenRAG, click **Chat**.
- The chat is powered by the OpenRAG Open Search Agent.
+ The chat is powered by the OpenRAG OpenSearch Agent.
For more information, see [Langflow Agents](/agents).
2. Ask `What documents are available to you?`
The agent responds with a message summarizing the documents that OpenRAG loads by default, which are PDFs about evaluating data quality when using LLMs in health care.
@@ -43,9 +43,9 @@ In this example, you'll try a different LLM to demonstrate how the Agent's respo
1. To edit the Agent's behavior, click **Edit in Langflow**.
2. OpenRAG warns you that you're entering Langflow. Click **Proceed**.
-3. The OpenRAG Open Search Agent flow appears.
+3. The OpenRAG OpenSearch Agent flow appears.
-
+
4. In the **Language Model** component, under **Model Provider**, select **Anthropic**.
:::note
From 0c6d20ef388db9bd446845383a5dea634a4cf42e Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Fri, 26 Sep 2025 12:14:42 -0400
Subject: [PATCH 8/9] remove-multiple-map
---
docs/docs/core-components/knowledge.mdx | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index d8160f8b..b5507eef 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -30,7 +30,7 @@ OpenRAG supports knowledge ingestion through direct file uploads and OAuth conne
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.
-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`.
+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.
To load and process a single file from the mapped location, click **Add Knowledge**, and then click **Add File**.
The file is loaded into your OpenSearch database, and appears in the Knowledge page.
From 8d400e9c7d9fa999eb053376573fe8a6005fddee Mon Sep 17 00:00:00 2001
From: Mendon Kissling <59585235+mendonk@users.noreply.github.com>
Date: Fri, 26 Sep 2025 13:35:42 -0400
Subject: [PATCH 9/9] no-static-default-onboarding-behavior
---
docs/docs/core-components/knowledge.mdx | 13 ++++++-------
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/docs/docs/core-components/knowledge.mdx b/docs/docs/core-components/knowledge.mdx
index b5507eef..255b0b68 100644
--- a/docs/docs/core-components/knowledge.mdx
+++ b/docs/docs/core-components/knowledge.mdx
@@ -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).
\ No newline at end of file