AIDB 7.4.0 release notes v7

Released: 06 Jul 2026

AIDB 7.4.0 includes the following enhancements and bug fixes:

TypeDescription
EnhancementVolumes as queryable foreign tables: Each AIDB volume is now exposed as a PGFS-backed foreign table, so the objects it contains can be listed, read, written, and deleted with standard SQL — including INSERT, UPDATE, and DELETE on objects, and SELECT body FROM my_volume WHERE key = '...' to fetch a single object. See External storage.
EnhancementEgress allowlist: Optional outbound HTTP allowlist for model calls and model downloads, configured via the aidb.egress_allowlist parameter (with edb.egress_allowlist as a shared fallback). Accepts host and CIDR entries; when unset, no check is applied.
EnhancementMore reliable HuggingFace model downloads: Downloads now resume across unstable connections, verify size and SHA-256, emit progress notices, and respond to Ctrl-C between retries. Corrupt cached snapshots self-heal on the next load.
EnhancementStrict pipeline option validation: Unknown keys and wrong types in step_N_options, knowledge-base configs, and standalone helpers (chunk_text, summarize_text, parse_html, parse_pdf, pdf_to_image, perform_ocr) now raise a clear error instead of being silently dropped.
EnhancementClearer model error messages: HTTP errors from model providers now include the request URL. Large input values are truncated in error output. OCR responses are only parsed as JSON on HTTP 200.
EnhancementBatch summarization: SummarizeText pipeline steps now process records in batches, with per-input retry on rate-limit errors.
EnhancementClearer permission errors on pipeline creation: Creating a pipeline against a source table without SELECT privilege now returns an explicit "permission denied" error instead of an opaque internal failure.
Bug fixEmpty retrieve returns empty result: retrieve_text on an empty knowledge base now returns no rows with a warning instead of raising an error, matching standard SQL SELECT behavior.
Bug fixretrieve_text value column on non-text sources: Retrieval from pipelines whose original source is non-text (such as PDF or Image) now returns NULL in value instead of the raw bytes decoded as text. Match metadata is still returned.
Bug fixDeadlock with metrics collector: The background metrics collector no longer holds locks on every user table in a single transaction, removing a deadlock against delete_pipeline.
Bug fixBIGINT pipeline keys: Pipelines on source tables with BIGINT primary keys above the int4 range no longer fail with an "out of range for type integer" error.
Bug fixPipeline batch size respected across steps: Steps that explode records (such as chunking) now sub-batch their outputs before passing them to the next step, keeping memory and parallelism within the configured batch_size.
Bug fixOCR config validation: OCR model configurations are now validated at model creation time.