Release 0.9.2

ai4rag/__init__.py

@@ -5,7 +5,7 @@
 import logging
 import os
 
-__version__ = "0.9.1"
+__version__ = "0.9.2"
 
 logger = logging.getLogger("ai4rag")
 logger.setLevel(os.getenv("LOG_LEVEL", "INFO"))

docs/about/changelog.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [0.9.2](https://github.com/IBM/ai4rag/releases/tag/v0.9.2)
+
+### Added
+- `chunk_sizes` parameter on `prepare_search_space_report()` for constraining the chunk-size dimension of the search space (e.g. `[256, 512]`)
+
+### Changed
+- Chunking constraint validation (`chunking_methods`, `chunk_sizes`) now happens via Pydantic before any I/O, providing clearer error messages with exact field paths
+- Minimum allowed chunk size lowered from 512 to 128, enabling finer-grained chunking strategies
+- Duplicate values in `chunking_methods` and `chunk_sizes` are now automatically deduplicated
+
+---
+
 ## [0.9.1](https://github.com/IBM/ai4rag/releases/tag/v0.9.1)
 
 ### Fixed

docs/user-guide/pipeline-components.md

@@ -122,6 +122,8 @@ report = prepare_search_space_report(
     ogx_client=client,
     embedding_models=["ibm/slate-125m-english-rtrvr"],
     generation_models=["ibm/granite-3.1-8b-instruct"],
+    chunking_methods=["recursive"],   # optional: constrain chunking methods
+    chunk_sizes=[256, 512, 1024],     # optional: constrain chunk sizes
 )
 report.save_yaml("/tmp/search_space.yaml")
 ```