Save Collection Config

DeepDoc processing mode (e.g., 'pipeline', 'default').

DeepDoc parallel threads (DEEPDOC_PARALLEL_THREADS).

DeepDoc reserved CPU cores (DEEPDOC_RESERVE_CPU).

DeepDoc CapacityLimiter capacity (DEEPDOC_LIMITER_CAPACITY).

Enable DeepDoc pipeline monitor (DEEPDOC_PIPELINE_MONITOR).

DeepDoc S1 worker count (DEEPDOC_PIPELINE_S1_WORKERS).

DeepDoc GPU sessions count/preference (DEEPDOC_GPU_SESSIONS).

Override DashScope base URL for embedding requests.

Override DashScope API key for embedding requests.

Override embedding request timeout (seconds).

Bound rerank model ID for this collection (user-scoped).

Available parsing methods

Available chunk strategies

Custom chunk method identifier. If provided, takes precedence over chunk_strategy

Chunk size passed to chunk_document; must be a positive integer. If None, semantic splitting is used without size limits.

Chunk overlap passed to chunk_document; must be non-negative

If True, chunk_size and chunk_overlap are in tokens (tiktoken); only applies to RECURSIVE strategy

tiktoken encoding name when use_token_count=True (e.g. cl100k_base for GPT-4/3.5). Should align with config.DEFAULT_TIKTOKEN_ENCODING.

If True, do not split inside code blocks, formulas, tables (P1).

Chars from prev/next chunk to attach to table chunks; 0 = off (P2).

Chars from prev/next chunk to attach to image chunks; 0 = off (P2).

Embedding model identifier registered in AgentOS model hub. If omitted, the pipeline attempts to auto-detect a single available embedding model.

Whether to lock collection configuration. When True, enforces strict config validation.

Whether to allow mixed parse methods within the collection. When False, enforces type-based parse method consistency.

Skip collection configuration validation. Use with caution.

Batch size for embedding provider requests; must be positive

Maximum concurrent requests for embedding computation when using async mode (for models that don't support batch processing, e.g., text-embedding-v4). Must be positive. Adjust based on machine configuration and API rate limits.

Whether to use async concurrent processing for embeddings. Set to True for models that don't support batch processing (e.g., text-embedding-v4). When True, embeddings are processed concurrently using asyncio instead of batch API calls.

Maximum number of retries for embedding provider failures; must be non-negative

Delay in seconds between embedding retries; must be non-negative

Operation status: success|partial_success|error

Collection identifier affected by the operation

Human-readable summary of the collection operation