RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
docs: add DemonRoute to supported model providers (#20548)
Harsh Rajf13a34b96a95
diff --git a/docs/guides/models/supported_models.mdx b/docs/guides/models/supported_models.mdxindex 6833351863..622514a471 100644--- a/docs/guides/models/supported_models.mdx+++ b/docs/guides/models/supported_models.mdx@@ -37,6 +37,7 @@ A complete list of model providers supported by RAGFlow, which will continue to| DaoXE | `https://daoxe.com` || DeepInfra | `https://deepinfra.com` || DeepSeek | `https://www.deepseek.com` |+| DemonRoute | `https://demonroute.com` || DeerAPI | `https://deerapi.com` || Fish Audio | `https://fish.audio` || FunASR | `https://github.com/modelscope/FunASR` |@@ -118,6 +119,19 @@ To configure AI Badgr:AI Badgr implements OpenAI-compatible endpoints for `/v1/chat/completions`, `/v1/embeddings`, and `/v1/models`, so no additional code changes in RAGFlow are required.+## Example: DemonRoute (OpenAI-Compatible)++You can use **DemonRoute** with RAGFlow via the existing OpenAI-API-Compatible provider. DemonRoute offers access to uncensored models.++To configure DemonRoute:++- **Provider**: `OpenAI-API-Compatible`+- **Base URL**: `https://api.demonroute.com/v1`+- **API Key**: your DemonRoute API key+- **Model**: any DemonRoute model ID, as exposed by DemonRoute's OpenAI-compatible APIs++DemonRoute implements OpenAI-compatible endpoints for `/v1/chat/completions`, `/v1/embeddings`, and `/v1/models`, so no additional code changes in RAGFlow are required.+:::noteThe list of supported models is extracted from [this source](https://github.com/infiniflow/ragflow/blob/main/rag/llm/__init__.py) and may not be the most current. For the latest supported model list, please refer to the Python file.:::