OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.
Python
multi-embedding search
April M00c09187f448
diff --git a/docs/docs/core-components/ingestion-configure.mdx b/docs/docs/core-components/ingestion-configure.mdxindex 9d612f394..c65ad18cc 100644--- a/docs/docs/core-components/ingestion-configure.mdx+++ b/docs/docs/core-components/ingestion-configure.mdx@@ -48,23 +48,42 @@ When you install OpenRAG, you select at least one embedding model during the [apOpenRAG automatically detects and configures the appropriate vector dimensions for your selected embedding model, ensuring optimal search performance and compatibility.After onboarding, you can change the embedding model on the OpenRAG <Icon name="Settings2" aria-hidden="true"/> **Settings** page.-OpenRAG automatically updates all relevant [OpenRAG flows](/agents) to use the new embedding model and dimensions.+OpenRAG automatically updates all relevant [OpenRAG flows](/agents) to use the selected embedding model and dimensions when ingesting documents.You can only select models that are available from your configured model providers, such as an Ollama instance or an OpenAI account.For more information, see [Troubleshoot model availability and performance issues](/support/troubleshoot#model-availability-and-performance-issues).Because the OpenRAG UI validates model availability and compatibility, setting models directly in the [OpenRAG `.env` file](/reference/configuration) isn't recommended.-### Best practices for multiple embedding models--For ingestion, OpenRAG allows only one active embedding model at a time.+### Documents aren't reingested after changing the embedding modelOpenRAG _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.+To remove previously generated embeddings, you must remove the existing documents from the knowledge base.++### Best practices for multiple embedding models++* **Make sure the active embedding model is correct before ingesting documents**: For ingestion, OpenRAG allows only one active embedding model at a time.+The active model is set on the <Icon name="Settings2" aria-hidden="true"/> **Settings** page.++* **Chat searches take longer with multiple embedding models**: OpenRAG **Chat** can use multiple embedding models, regardless of the active model for ingestion.+If your OpenRAG knowledge base has documents with embeddings from different embedding models, the agent runs a separate similarity search against each model's embeddings, and then prepares a unified set of search results.+Be aware that this can increase processing time for chat responses.++* **Use filters to exclude unrelated models**: You can create [filters](/knowledge-filters) to separate documents that were embedded with different models.+For example, if you use a specific model for financial reports, and a different model for corporate policy documents, you can use a filter to exclude the financial reports when chatting about corporate policies.+This can save time and improve the relevance of search results because the agent doesn't need to search both sets of embeddings and then unify them into one set of results.++* **Unavailable embedding models can cause errors**: Errors can occur in **Chat** if you an embedding model is unavailable _and_ your knowledge base contains documents with embeddings generated by that model.+Similarly, errors can occur with ingestion if the active embedding model (on the <Icon name="Settings2" aria-hidden="true"/> **Settings** page) is unavailable.++Models become unavailable when you remove an embedding model or provider from the OpenRAG <Icon name="Settings2" aria-hidden="true"/> **Settings** page, your model provider credentials are expired or invalid, or there are network issues preventing access to the model.++If you remove a model or provider that you don't want to use anymore, it is recommended that you [remove documents](/knowledge-browse#delete-documents) that were embedded with the unavailable model.+If you don't remove or [filters](/knowledge-filters) these documents, then **Chat** responses can fail or return incomplete results.+This is because the agent cannot access the model to generate a query embedding for comparison with the document embeddings.## Set the chunking strategy