RAGFlow
Connect RAGFlow to AICredits for OpenAI-compatible chat and embedding models in document RAG workflows.
Use this page with an AI assistant
Opens a new chat with this docs URL and the correct AICredits base URLs.
RAGFlow is an open-source RAG engine for document parsing, retrieval, agents, and knowledge workflows. Use AICredits as an OpenAI-compatible model provider for chat generation and embeddings.
Model Provider
In RAGFlow model settings, add an OpenAI-compatible provider:
| Setting | Value |
|---|---|
| Provider name | AICredits |
| API base URL | https://api.aicredits.in/v1 |
| API key | sk-your-aicredits-key |
| Chat model | Pick from Models |
Recommended chat models:
openai/gpt-4o-mini
anthropic/claude-sonnet-4.5
google/gemini-2.5-flashEmbeddings
If your RAGFlow deployment lets you configure OpenAI-compatible embeddings separately, use:
| Setting | Value |
|---|---|
| Embedding base URL | https://api.aicredits.in/v1 |
| Embedding API key | sk-your-aicredits-key |
| Embedding model | text-embedding-3-small |
Keep chat and embedding usage visible by using a dedicated AICredits key for each RAGFlow environment.
Verify
Create a small knowledge base, ingest one short document, and ask:
Reply with "AICredits via RAGFlow" and nothing else.Then confirm chat and embedding calls in Dashboard -> Usage.
Troubleshooting
Knowledge base ingests but chat fails - Check the chat model provider separately from the embedding provider.
Embedding errors - Confirm the embedding model is available and the base URL includes /v1.
High ingestion cost - Start with text-embedding-3-small and avoid re-ingesting unchanged documents.