Context sources
Bring your RAG context to Maxim
To integrate RAG context into Maxim, you need to create a context source and add your RAG context API endpoint. This context source can then be utilized in prompts and workflows for inferencing, enabling the model to access and use the relevant context during processing.
You can create a new context source by clicking on the left navigation and then the plus icon.
Provide a name
Enter the API endpoint. When we pass a query to this endpoint, it should return the retrieved context for that query as would be the real world scenario.
Add necessary headers and parameters to your request and save the context source
You can now use this in prompts and workflows.