--- title: "Save Config" method: POST path: "/api/configs/" tags: ["configs"] --- # Save Config `POST /api/configs/` Save a new configuration. ## Request body - ConfigUpdateData — Configuration update - only changed parameters need to be provided with proper validation - `QueryLLM` QueryLLMConfig - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `MODEL_NAME` string — The name of the non-reasoning model to be used. - `SYSTEM_INSTRUCTION` string — The system instruction string. - `MAX_CHAR_SIZE_TO_ANSWER` integer — Maximum character size to answer. - `TEMPERATURE` number — Temperature value for randomness. - `MAX_TOKENS` integer — Maximum number of tokens allowed. - `Agents` AgentsConfig - `ENABLED` boolean — Whether to use agents mode for queries. - `AGENT_MODEL_NAME` string — The name of the model to be used for the agent. - `AGENT_PROMPT` string - `LLM_AGENT_TEMPERATURE` number — Temperature value for randomness. - `LLM_PAGE_FILTER_MODEL_NAME` string — The name of the model to be used for the llm page filter model. - `LLM_PAGE_FILTER_TEMPERATURE` number — Temperature value for randomness. - `LLM_PAGE_FILTER_PROMPT` string - `LLM_SUMMARISE_MODEL_NAME` string — The name of the model to be used for the llm summarise model. - `LLM_SUMMARISE_TEMPERATURE` number — Temperature value for randomness. - `LLM_SUMMARISE_PROMPT` string - `AgentLLM` AgentLLMConfig - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `MODEL_NAME` string — The name of the model to be used. - `ENABLED` boolean — Whether to use agent mode for queries. - `MAX_ITERATIONS` integer — Maximum agent loop iterations. - `SHOW_INTERIM_STEPS` boolean — Whether to show agent's intermediate steps. - `MAX_CONTEXT_TOKENS` integer — Maximum tokens for gathered context (applies to evidence buffer and final query). - `SYSTEM_INSTRUCTION` string — The system instruction for agent planning. - `TEMPERATURE` number — Temperature for agent decisions. - `MAX_TOKENS` integer — Maximum tokens for planning decisions. - `MAX_CHAR_SIZE_TO_ANSWER` integer — Maximum character size for history. - `EvaluatorLLM` EvaluatorLLMConfig - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `MODEL_NAME` string — The name of the non-reasoning model to be used. - `SYSTEM_INSTRUCTION` string — The system instruction for chunk evaluation. - `TEMPERATURE` number — Low temperature for consistent evaluation. - `MAX_TOKENS` integer — Maximum tokens for evaluation response. - `MAX_CHAR_SIZE_TO_ANSWER` integer — Maximum character size for evaluation context. - `TitleLLM` TitleLLMConfig - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `MODEL_NAME` string — The name of the non-reasoning model to be used. - `SYSTEM_INSTRUCTION` string - `MAX_CHAR_SIZE_TO_ANSWER` integer — Maximum character size to answer. - `TEMPERATURE` number — Temperature value for randomness. - `MAX_TOKENS` integer — Maximum number of tokens allowed. - `DoctagLLM` DoctagLLMConfigInput — Configuration for DoctagLLM - extracts information from documents based on tag instructions. - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `MODEL_NAME` string — The name of the non-reasoning model to be used. - `SYSTEM_INSTRUCTION` string - `MAX_CHAR_CONTEXT_TO_ANSWER` integer — Maximum characters in document for context. - `TEMPERATURE` number — Temperature for factual answers. - `MAX_TOKENS` integer — Maximum number of tokens allowed for all answers. - `MAX_CONCURRENT_DOCS` integer — Maximum concurrent documents for doctag generation. - `DEFAULT_METADATA_TAGS` TagTemplate[] — Metadata templates used for automatic document metadata extraction during indexing. - `name` string, required - `instruction` string, nullable - `tag_type` TagFormat — Tag format configuration stored as JSONB. Type-specific fields: - select: options (list of choices, can be single or multi-select) - search: tag name is the query, chunks include relevance scores - checkbox, text, number, folder: type only - `type` 'checkbox' | 'text' | 'number' | 'select' | 'folder' | 'search' | 'date' - `options` string[] - `ModelCitation` ModelCitationConfig - `SIM_THREASHOLD` number — How similar does the statement needs to be to be considered as citation. - `MIN_CHAR_SIZE_TO_ANSWER` integer — Minimum character length to be considered as a statement for citation. - `MAX_NUMB_CITATIONS` integer — Maximum number of citations to return per statement. - `Parser` ParserConfig - `Chunker` ChunkerConfig - `Embedder` EmbedderConfig - `MODEL_NAME` string — The name of the embedder model. - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `BATCH_SIZE` integer — Smaller batch size for better parallelization. - `MAX_CONCURRENT_REQUESTS` integer — Adjust concurrency level as needed. - `EMBED_PREFIX` string — How to embed the sentence for retrieval. - `QUERY_PREFIX` string — How to embed the sentence for query. - `Retriever` RetrieverConfig - `MIN_RETRIEVAL_SIM_SCORE` number — Minimum similarity score for retrieval of a chunk. - `MAX_DISTINCT_DOCUMENTS` integer — Maximum number of distinct documents to search for. - `MAX_TOTAL_CHUNKS_TO_RETRIEVE` integer — Maximum total number of chunks to retrieve for all documents retrieved. - `GROUP_SIZE` integer — Maximum number of chunks per document for retrieval. - `SEARCH_MODE` 'semantic' | 'keyword' | 'hybrid' — Search mode for retrieval. - `HYBRID_DENSE_WEIGHT` number — Weight for dense vectors in hybrid mode - `HYBRID_SPARSE_WEIGHT` number — Weight for sparse vectors in hybrid mode - `HYBRID_RERANKER_WEIGHT` number — Weight for reranker score in hybrid mode score blending (0-1). RRF weight = 1 - this value - `Reranker` RerankerConfig - `MAX_NUMB_OF_CHUNKS` integer — Maximum number of chunks to return after reranking. - `MAX_CONCURRENT_REQUESTS` integer — Maximum number of concurrent reranking requests. - `MODEL_NAME` string — Name of the reranking model to use. - `API_TYPE` 'local' | 'remote' — The inference type (local or remote). - `KeywordEmbedder` KeywordEmbedderConfig — Configuration for keyword embedder with BM25 scoring. - `DIMENSION_SPACE` integer — Total dimension space for hash trick (1,048,576 dimensions) - `FILTER_STOPWORDS` boolean — Remove common stopwords to reduce noise - `BM25_K1` number — BM25 term frequency saturation (1.2-2.0). Higher = more weight on term repetition. Default 1.5 works for most cases. - `BM25_B` number — BM25 document length normalization (0.0-1.0). 0=ignore length, 1=full penalty for long docs. Default 0.75 is standard. - `BM25_AVGDL` number — Average document length in tokens. Adjust based on your documents: chat messages ~20-50, articles ~100-300, papers ~1000+ - `title` string - `parent_message_ext_id` string, nullable ## Response `200` Successful Response - ConfigSaveResponse — Response model for configuration save endpoint - `external_id` string, required - `title` string, nullable, required - `created_at` string, required ## Other responses - `422` — Validation Error --- [API](https://skmtc.net/arbicity/apis/arbi.md) · [All operations](https://skmtc.net/arbicity/apis/arbi/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/arbicity/arbi/versions/1f956ac3d1c1/schema)