OptionalAIMON_OptionalBM25_The average length of the chunks in the index for BM25
OptionalBM25_The BM25 B parameter
OptionalBM25_Whether to use BM25
OptionalBM25_The BM25 K parameter
OptionalDISABLE_Whether to disable analytics
OptionalDISTANCE_OptionalEMBEDDING_The base URL for the embedding API
OptionalEMBEDDING_The name of the embedding model to use
OptionalEMBEDDING_The prefix to use for the embedding query
OptionalEMBEDDING_The size of the embeddings
OptionalFREQUENCY_The frequency penalty to use
OptionalFULLTEXT_Whether to use fulltext search
OptionalINDEXED_Whether to only use indexed chunks
OptionalLLM_The API version for the LLM API
OptionalLLM_The base URL for the LLM API
OptionalLLM_The default model to use for the LLM
OptionalLOCKED?: boolean | nullWhether the dataset is locked to prevent changes or deletion
OptionalMAX_The maximum limit for the number of chunks for counting
OptionalMAX_The maximum number of tokens to use in LLM Response
OptionalMESSAGE_The prompt to use for converting a message to a query
OptionalN_The number of retrievals to include with the RAG model
OptionalPAGEFIND_Whether to enable pagefind indexing
OptionalPRESENCE_The presence penalty to use
OptionalPUBLIC_OptionalQDRANT_Whether or not to insert chunks into Postgres
OptionalRAG_The prompt to use for the RAG model
OptionalRERANKER_The base URL for the reranker API
OptionalRERANKER_The model name for the Reranker API
OptionalSEMANTIC_Whether to use semantic search
OptionalSTOP_The stop tokens to use
OptionalSYSTEM_The system prompt to use for the LLM
OptionalTEMPERATURE?: number | nullThe temperature to use
OptionalTOOL_OptionalUSE_Whether to use the message to query prompt
Lets you specify the configuration for a dataset