deepdoc_processing_modestring nullable
DeepDoc processing mode (e.g., 'pipeline', 'default').
deepdoc_parallel_threadsinteger nullable
DeepDoc parallel threads (DEEPDOC_PARALLEL_THREADS).
deepdoc_reserve_cpuinteger nullable
DeepDoc reserved CPU cores (DEEPDOC_RESERVE_CPU).
deepdoc_limiter_capacityinteger nullable
DeepDoc CapacityLimiter capacity (DEEPDOC_LIMITER_CAPACITY).
deepdoc_pipeline_monitorboolean nullable
Enable DeepDoc pipeline monitor (DEEPDOC_PIPELINE_MONITOR).
deepdoc_pipeline_s1_workersinteger nullable
DeepDoc S1 worker count (DEEPDOC_PIPELINE_S1_WORKERS).
deepdoc_gpu_sessionsinteger nullable
DeepDoc GPU sessions count/preference (DEEPDOC_GPU_SESSIONS).
embedding_base_urlstring nullable
Override DashScope base URL for embedding requests.
embedding_api_keystring nullable
Override DashScope API key for embedding requests.
embedding_timeout_secnumber nullable
Override embedding request timeout (seconds).
rerank_model_idstring nullable
Bound rerank model ID for this collection (user-scoped).
parse_method'default' | 'pypdf' | 'pdfplumber' | 'unstructured' | 'pymupdf' | 'deepdoc'
Available parsing methods
chunk_strategy'recursive' | 'fixed_size' | 'markdown'
Available chunk strategies
chunk_methodstring nullable
Custom chunk method identifier. If provided, takes precedence over chunk_strategy
chunk_sizeinteger nullable
Chunk size passed to chunk_document; must be a positive integer. If None, semantic splitting is used without size limits.
chunk_overlapinteger
Chunk overlap passed to chunk_document; must be non-negative
separatorsstring[] nullable
Custom separators for recursive/markdown strategies
use_token_countboolean
If True, chunk_size and chunk_overlap are in tokens (tiktoken); only applies to RECURSIVE strategy
tiktoken_encodingstring
tiktoken encoding name when use_token_count=True (e.g. cl100k_base for GPT-4/3.5). Should align with config.DEFAULT_TIKTOKEN_ENCODING.
enable_protected_contentboolean
If True, do not split inside code blocks, formulas, tables (P1).
protected_patternsstring[] nullable
Optional regex patterns for protected regions; None uses config default.
table_context_sizeinteger
Chars from prev/next chunk to attach to table chunks; 0 = off (P2).
image_context_sizeinteger
Chars from prev/next chunk to attach to image chunks; 0 = off (P2).
embedding_model_idstring nullable
Embedding model identifier registered in AgentOS model hub. If omitted, the pipeline attempts to auto-detect a single available embedding model.
collection_lockedboolean
Whether to lock collection configuration. When True, enforces strict config validation.
allow_mixed_parse_methodsboolean
Whether to allow mixed parse methods within the collection. When False, enforces type-based parse method consistency.
skip_config_validationboolean
Skip collection configuration validation. Use with caution.
embedding_batch_sizeinteger
Batch size for embedding provider requests; must be positive
embedding_concurrentinteger
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.
embedding_use_asyncboolean
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.
max_retriesinteger
Maximum number of retries for embedding provider failures; must be non-negative
retry_delaynumber
Delay in seconds between embedding retries; must be non-negative