Skip to content

OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.

Python

model providers, removing and changing models

April M4f5450ba5cc3
diff --git a/docs/docs/_partial-edit-agent-flow.mdx b/docs/docs/_partial-edit-agent-flow.mdx
index 1074247a0..881d65a93 100644
--- a/docs/docs/_partial-edit-agent-flow.mdx
+++ b/docs/docs/_partial-edit-agent-flow.mdx
@@ -2,11 +2,24 @@ import Icon from "@site/src/components/icon/icon";
1. In OpenRAG, click <Icon name="Settings2" aria-hidden="true"/> **Settings**, and then find the **Agent** section.
-2. If you only need to edit the language model or agent instructions, edit those fields directly on the **Settings** page.
+2. To change the active language model or agent instructions, edit those fields directly on the **Settings** page.
Language model changes are saved automatically.
To apply new instructions, click **Save Agent Instructions**.
-3. To edit all flow settings and components with full customization capabilities, edit the flow in the Langflow visual editor:
+3. To add a new language model, edit the model provider settings or configure an additional provider on the **Settings** page, and then select the new model in the **Agent** section.
+
+ :::info
+ On the **Settings** page, you can add, edit, and remove model providers.
+
+ OpenRAG functionality requires at least one language model and one embedding model.
+ If you remove all providers, most OpenRAG functionality will be non-functional until you reconfigure at least one provider.
+
+ If you remove providers or models that you previously used for chat or ingestion, you might experience errors or unexpected behaviors.
+ For example, if you remove all embedding models, the chat cannot generate an embedding from your query to retrieve relevant documents from the knowledge base.
+ Similarly, if you change the embedding model, the chat might return incorrect or no results due to differences between the original and new embedding models.
+ :::
+
+4. To edit all flow settings and components with full customization capabilities, edit the flow in the Langflow visual editor:
1. Click **Edit in Langflow** to launch the Langflow visual editor in a new browser tab.
diff --git a/docs/docs/core-components/chat.mdx b/docs/docs/core-components/chat.mdx
index a29214667..6ee554d9c 100644
--- a/docs/docs/core-components/chat.mdx
+++ b/docs/docs/core-components/chat.mdx
@@ -7,6 +7,7 @@ import Icon from "@site/src/components/icon/icon";
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import PartialTempKnowledge from '@site/docs/_partial-temp-knowledge.mdx';
+import PartialEditAgentFlow from '@site/docs/_partial-edit-agent-flow.mdx';
After you [upload documents to your knowledge base](/ingestion), you can use the OpenRAG <Icon name="MessageSquare" aria-hidden="true"/> **Chat** feature to interact with your knowledge through natural language queries.
@@ -97,6 +98,10 @@ If documents in your knowledge base seem to be missing or interpreted incorrectl
If tool calls and knowledge appear normal, but the agent's responses seem off-topic or incorrect, consider changing the agent's language model or prompt, as explained in [Inspect and modify flows](/agents#inspect-and-modify-flows).
+## Change language models, embedding models, and agent instructions
+
+<PartialEditAgentFlow />
+
## Integrate OpenRAG chat into an application
You can integrate OpenRAG flows into your applications using the OpenRAG SDKs (recommended) or the Langflow API.
diff --git a/docs/docs/core-components/ingestion-configure.mdx b/docs/docs/core-components/ingestion-configure.mdx
index 4bc4b5200..9d612f394 100644
--- a/docs/docs/core-components/ingestion-configure.mdx
+++ b/docs/docs/core-components/ingestion-configure.mdx
@@ -59,14 +59,13 @@ Because the OpenRAG UI validates model availability and compatibility, setting m
For ingestion, OpenRAG allows only one active embedding model at a time.
-OpenRAG _doesn't_ reprocess existing documents when you change the embedding model.
+OpenRAG _doesn't_ reprocess existing documents when you change, add, or remove embedding models.
+
If you want to generate new embeddings for existing documents, you must reupload the documents after enabling the new embedding model.
To remove previously generated embeddings, you must delete the existing document from the knowledge base.
If you use different embedding models for different documents, you can create [filters](/knowledge-filters) to separate documents that were embedded with different models.
-If you use multiple embeddings models, be aware that similarity search (in **Chat**) can take longer as the agent searches each model's embeddings separately.
-
## Set the chunking strategy
You can edit the following settings on the OpenRAG <Icon name="Settings2" aria-hidden="true"/> **Settings** page in the **Knowledge Ingest** section: