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

langflow functionality

Browse source
This commit is contained in:
April M 2025-11-25 10:49:03 -08:00
parent bf3224e709
commit b00e6e9c98
3 changed files with 65 additions and 41 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

85
docs/docs/core-components/agents.mdx
View file

@ -7,45 +7,56 @@ import Icon from "@site/src/components/icon/icon";
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
OpenRAG leverages Langflow's Agent component to power the OpenRAG OpenSearch Agent flow.
OpenRAG includes a built-in [Langflow](https://docs.langflow.org/) instance for creating and managing application workflows called [_flows_](https://docs.langflow.org/concepts-overview).
In a flow, the individual workflow steps are represented by [_components_](https://docs.langflow.org/concepts-components) that are connected together to form a complete process.
[Flows](https://docs.langflow.org/concepts-overview) in Langflow are functional representations of application workflows, with multiple [component](https://docs.langflow.org/concepts-components) nodes connected as single steps in a workflow.
OpenRAG includes several built-in flows:
In the OpenRAG OpenSearch Agent flow, components like the Langflow [**Agent** component](https://docs.langflow.org/agents) and [**OpenSearch** component](https://docs.langflow.org/bundles-elastic#opensearch) are connected to intelligently chat with your knowledge by embedding your query, comparing it the vector database embeddings, and generating a response with the LLM.
* The [**OpenRAG OpenSearch Agent** flow](/agents#flow) powers the **Chat** feature in OpenRAG.
* The [**OpenSearch Ingestion** and **OpenSearch URL Ingestion** flows](/ingestion#knowledge-ingestion-flows) process documents and web content for storage in your OpenSearch knowledge bases.
You can customize the built-in flows or create your own flows using OpenRAG's embedded Langflow visual editor.
## About the OpenRAG Chat flow (OpenRAG OpenSearch Agent flow) {#flow}
When you **Chat** with your knowledge in OpenRAG, the **OpenRAG OpenSearch Agent** flow runs in the background.
If you [inspect the flow in Langflow](#inspect-and-modify-flows), you'll see that it is comprised of eight components that work together to ingest chat messages, retrieve relevant information from your knowledge base, and then generate responses.
![OpenRAG Open Search Agent Flow](/img/opensearch-agent-flow.png)
The Agent component shines here in its ability to make decisions on not only what query should be sent, but when a query is necessary to solve the problem at hand.
<details closed>
<summary>How do agents work?</summary>
Agents extend Large Language Models (LLMs) by integrating tools, which are functions that provide additional context and enable autonomous task execution. These integrations make agents more specialized and powerful than standalone LLMs.
Whereas an LLM might generate acceptable, inert responses to general queries and tasks, an agent can leverage the integrated context and tools to provide more relevant responses and even take action. For example, you might create an agent that can access your company's documentation, repositories, and other resources to help your team with tasks that require knowledge of your specific products, customers, and code.
Agents use LLMs as a reasoning engine to process input, determine which actions to take to address the query, and then generate a response. The response could be a typical text-based LLM response, or it could involve an action, like editing a file, running a script, or calling an external API.
In an agentic context, tools are functions that the agent can run to perform tasks or access external resources. A function is wrapped as a Tool object with a common interface that the agent understands. Agents become aware of tools through tool registration, which is when the agent is provided a list of available tools typically at agent initialization. The Tool object's description tells the agent what the tool can do so that it can decide whether the tool is appropriate for a given request.
</details>
## Use the OpenRAG Chat (OpenRAG OpenSearch Agent flow) {#flow}
If you've chatted with your knowledge in OpenRAG, you've already experienced the OpenRAG OpenSearch Agent chat flow.
To switch OpenRAG over to the [Langflow visual editor](https://docs.langflow.org/concepts-overview) and view the OpenRAG OpenSearch Agentflow, click <Icon name="Settings2" aria-hidden="true"/> **Settings**, and then click **Edit in Langflow**.
This flow contains eight components connected together to chat with your data:
* The [**Agent** component](https://docs.langflow.org/agents) 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.
The **Agent** behaves according to the prompt in the **Agent Instructions** field.
The Agent component is the star of this flow because it powers decision making, tool calling, and an LLM-driven conversational experience.
<details>
<summary>How do agents work?</summary>
Agents extend Large Language Models (LLMs) by integrating tools, which are functions that provide additional context and enable autonomous task execution. These integrations make agents more specialized and powerful than standalone LLMs.
Whereas an LLM might generate acceptable, inert responses to general queries and tasks, an agent can leverage the integrated context and tools to provide more relevant responses and even take action. For example, you might create an agent that can access your company's documentation, repositories, and other resources to help your team with tasks that require knowledge of your specific products, customers, and code.
Agents use LLMs as a reasoning engine to process input, determine which actions to take to address the query, and then generate a response. The response could be a typical text-based LLM response, or it could involve an action, like editing a file, running a script, or calling an external API.
In an agentic context, tools are functions that the agent can run to perform tasks or access external resources. A function is wrapped as a Tool object with a common interface that the agent understands. Agents become aware of tools through tool registration, which is when the agent is provided a list of available tools typically at agent initialization. The Tool object's description tells the agent what the tool can do so that it can decide whether the tool is appropriate for a given request.
</details>
* The [**Chat Input** component](https://docs.langflow.org/components-io) 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](https://docs.langflow.org/bundles-elastic#opensearch) is connected to the Agent component's Tools port. The agent might 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](https://docs.langflow.org/components-models) 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](https://docs.langflow.org/components-embedding-models) 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](https://docs.langflow.org/components-io) is populated with the global variable `OPENRAG-QUERY-FILTER`.
* The [**Text Input** component](https://docs.langflow.org/components-io) is populated with the global variable `OPENRAG-QUERY-FILTER`.
This filter is the [Knowledge filter](/knowledge#create-knowledge-filters), and filters which knowledge sources to search through.
* The **Agent** component's Output port is connected to the [**Chat Output** component](https://docs.langflow.org/components-io), which returns the final response to the user or application.
* An [**MCP Tools** component](https://docs.langflow.org/mcp-client) is connected to the Agent's **Tools** port. This component calls the [OpenSearch URL Ingestion flow](/ingestion#url-flow), which Langflow uses as an MCP server to fetch content from URLs and store in OpenSearch.
* An [**MCP Tools** component](https://docs.langflow.org/mcp-client) is connected to the Agent's **Tools** port. This component calls the [**OpenSearch URL Ingestion** flow](/ingestion#url-flow), which Langflow uses as a [Model Context Protocol (MCP) server](https://docs.langflow.org/mcp-server) to fetch content from URLs and store in OpenSearch.
## Inspect and modify flows {#inspect-and-modify-flows}
@ -79,17 +90,29 @@ For example, to view and edit the built-in **Chat** flow (the **OpenRAG OpenSear
If you modify the built-in **Chat** flow, make sure you click <Icon name="Plus" aria-hidden="true"/> in the **Conversations** tab to start a new conversation. This ensures that the chat doesn't persist any context from the previous conversation with the original model.
:::
### Revert a built-in flow to the default state
## Revert a built-in flow to the default state
After you edit a built-in flow, you can click **Restore flow** on the **Settings** page to revert the flow to its original state when you first installed OpenRAG.
This is a destructive action that discards all customizations to the flow.
## Additional Langflow functionality
Langflow includes features beyond Agents to help you integrate OpenRAG into your application, and all Langflow features are included in OpenRAG.
In addition to OpenRAG's built-in flows, all Langflow features are available through OpenRAG, including popular extensibility features such as the following:
* Langflow can serve your flows as an [MCP server](https://docs.langflow.org/mcp-server), or consume other MCP servers as an [MCP client](https://docs.langflow.org/mcp-client). Get started with the [MCP tutorial](https://docs.langflow.org/mcp-tutorial).
* [Create custom components](https://docs.langflow.org/components-custom-components).
* Integrate with many third-party services through [bundles](https://docs.langflow.org/components-bundle-components).
* Use [MCP clients](https://docs.langflow.org/mcp-client) and [MCP servers](https://docs.langflow.org/mcp-server), and serve flows as MCP tools for your agentic flows.
* If you don't see the component you need, extend Langflow's functionality by creating [custom Python components](https://docs.langflow.org/components-custom-components).
Explore the [Langflow documentation](https://docs.langflow.org/) to learn more about the Langflow platform, features, and visual editor.
* Langflow offers component [bundles](https://docs.langflow.org/components-bundle-components) to integrate with many popular vector stores, AI/ML providers, and search APIs.
## Set the Langflow version
By default, OpenRAG is pinned to the latest Langflow Docker image for stability.
You can set a specific Langflow version with the [`LANGFLOW_VERSION`](/reference/configuration). However, there are risks to changing this setting:
* The [Langflow documentation](https://docs.langflow.org/) describes the functionality present in the latest release of the Langflow OSS Python package. If your `LANGFLOW_VERSION` is different, the Langflow documentation might not align with the features and default settings in your OpenRAG installation.
* Components might break, including components in OpenRAG's built-in flows.
* Default settings and behaviors might change causing unexpected results when OpenRAG expects a newer default.

20
docs/docs/core-components/ingestion.mdx
View file

@ -6,7 +6,6 @@ slug: /ingestion
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 [Docling](https://docling-project.github.io/docling/) for document ingestion.
More specifically, OpenRAG uses [Docling Serve](https://github.com/docling-project/docling-serve), which starts a `docling serve` process on your local machine and runs Docling ingestion through an API service.
@ -45,13 +44,15 @@ If OpenRAG detects that the local machine is running on macOS, OpenRAG uses the
**Picture descriptions** adds image descriptions generated by the [SmolVLM-256M-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct) model to OCR processing. Enabling picture descriptions can slow ingestion performance.
## Knowledge ingestion flows
## Knowledge ingestion flows {#knowledge-ingestion-flows}
[Flows](https://docs.langflow.org/concepts-overview) in Langflow are functional representations of application workflows, with multiple [component](https://docs.langflow.org/concepts-components) nodes connected as single steps in a workflow.
The **OpenSearch Ingestion** flow is the default knowledge ingestion flow in OpenRAG: when you **Add Knowledge** in OpenRAG, you run the OpenSearch Ingestion flow in the background. The flow ingests documents using **Docling Serve** to import and process documents.
### OpenSearch Ingestion flow
This flow contains ten components connected together to process and store documents in your knowledge base.
The **OpenSearch Ingestion** flow is the default knowledge ingestion flow in OpenRAG. When you **Add Knowledge** in OpenRAG, the OpenSearch Ingestion flow runs in the background. The flow ingests documents using Docling Serve to import and process documents.
If you [inspect the flow in Langflow](/agents#inspect-and-modify-flows), you'll see that it is comprised of ten components that work together to process and store documents in your knowledge base:
* The [**Docling Serve** component](https://docs.langflow.org/bundles-docling) processes input documents by connecting to your instance of Docling Serve.
* The [**Export DoclingDocument** component](https://docs.langflow.org/components-docling) exports the processed DoclingDocument to markdown format with image export mode set to placeholder. This conversion makes the structured document data into a standardized format for further processing.
@ -62,15 +63,16 @@ This flow contains ten components connected together to process and store docume
* The [**Embedding Model** component](https://docs.langflow.org/components-embedding-models) generates vector embeddings using OpenAI's `text-embedding-3-small` model. The embedding model is selected at [Application onboarding] and cannot be changed.
* The [**OpenSearch** component](https://docs.langflow.org/bundles-elastic#opensearch) stores the processed documents and their embeddings in the `documents` index at `https://opensearch:9200`. By default, the component is authenticated with a JWT token, but you can also select `basic` auth mode, and enter your OpenSearch admin username and password.
<PartialModifyFlows />
To customize this flow, see [Inspect and modify flows](/agents#inspect-and-modify-flows).
### OpenSearch URL Ingestion flow {#url-flow}
An additional knowledge ingestion flow is included in OpenRAG, where it is used as an MCP tool by the [**Open Search Agent flow**](/agents#flow).
The agent calls this component to fetch web content, and the results are ingested into OpenSearch.
The **OpenSearch URL Ingestion** flow is used to ingest web content from URLs.
This flow isn't directly accessible from the OpenRAG user interface.
Instead, this flow is called by the [**OpenRAG OpenSearch Agent** flow](/agents#flow) as a Model Context Protocol (MCP) tool.
The agent can call this component to fetch web content from a given URL, and then ingest that content into your OpenSearch knowledge base.
For more on using MCP clients in Langflow, see [MCP clients](https://docs.langflow.org/mcp-client).\
To connect additional MCP servers to the MCP client, see [Connect to MCP servers from your application](https://docs.langflow.org/mcp-tutorial).
For more information about MCP in Langflow, see the Langflow documentation on [MCP clients](https://docs.langflow.org/mcp-client) and [MCP servers](https://docs.langflow.org/mcp-tutorial).
## Use OpenRAG default ingestion instead of Docling serve

1
docs/docs/core-components/knowledge.mdx
View file

@ -6,7 +6,6 @@ slug: /knowledge
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.
This is a specialized database for storing and retrieving embeddings, which helps your Agent efficiently find relevant information.