# LlamaIndex v0.14.24

- Product: LlamaIndex (https://whatsnew.fyi/product/llamaindex)
- Vendor: LlamaIndex
- Date: 2026-08-19
- Version: v0.14.24
- Original notes: https://github.com/run-llama/llama_index/releases/tag/v0.14.24
- Permalink: https://whatsnew.fyi/product/llamaindex/releases/v0.14.24

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **fixed** — Close HotpotQA evaluator file handles
- **fixed** — Preserve oversized leaf nodes in CodeSplitter
- **fixed** — Preserve multiblock chat history writes
- **fixed** — Skip empty nodes in HTMLNodeParser
- **fixed** — Respect mmr_threshold=0 in MMR embedding search
- **fixed** — Keep all nodes per document in IngestionPipeline upserts
- **fixed** — Don't mark *args/**kwargs as required tool parameters
- **fixed** — Default MetadataFilters condition to AND when None
- **fixed** — Honor agent structured_output_fn/output_cls inside AgentWorkflow
- **fixed** — Use word tokenization for stopword removal in SemanticDoubleMergingSplitterNodeParser
- **fixed** — Restore prompt helper fallback to supplied LLM metadata
- **fixed** — Populate response text on streaming chat response when writing to memory
- **added** — Add raise_on_error to LLM path extractors in property_graph
- **changed** — Clarify FactExtractionMemoryBlock condense prompt to return a full snapshot
- **fixed** — Give each CitationQueryEngine citation node its own id and offsets
- **fixed** — Persist SimpleChatStore without escaping non-ascii
- **added** — Allow Memory to accept any AsyncDBChatStore
- **added** — Implement async for LLMRerank
- **fixed** — Make aioboto3 optional in llama-index-embeddings-bedrock
- **fixed** — Validate non-empty Bedrock embedding payload before AWS call

#### Release Notes

##### [2026-08-19]

###### llama-index-core [0.14.24]

- fix: close HotpotQA evaluator file handles ([#22113](https://github.com/run-llama/llama_index/pull/22113))
- fix(core): preserve oversized leaf nodes in CodeSplitter ([#22119](https://github.com/run-llama/llama_index/pull/22119))
- fix: preserve multiblock chat history writes ([#22124](https://github.com/run-llama/llama_index/pull/22124))
- fix(core): skip empty nodes in HTMLNodeParser ([#22125](https://github.com/run-llama/llama_index/pull/22125))
- fix(core): respect mmr_threshold=0 in MMR embedding search ([#22126](https://github.com/run-llama/llama_index/pull/22126))
- fix: keep all nodes per document in IngestionPipeline upserts (re-submit of #22046, not a dup of #21456) ([#22133](https://github.com/run-llama/llama_index/pull/22133))
- fix: don't mark \*args/\*\*kwargs as required tool parameters ([#22135](https://github.com/run-llama/llama_index/pull/22135))
- fix(core): default MetadataFilters condition to AND when None ([#22155](https://github.com/run-llama/llama_index/pull/22155))
- fix: honor agent structured_output_fn/output_cls inside AgentWorkflow ([#22162](https://github.com/run-llama/llama_index/pull/22162))
- fix(core): use word tokenization for stopword removal in SemanticDoubleMergingSplitterNodeParser ([#22167](https://github.com/run-llama/llama_index/pull/22167))
- fix(core): restore prompt helper fallback to supplied LLM metadata ([#22177](https://github.com/run-llama/llama_index/pull/22177))
- populate response text on streaming chat response when writing to memory ([#22179](https://github.com/run-llama/llama_index/pull/22179))
- feat(property_graph): add raise_on_error to LLM path extractors ([#22195](https://github.com/run-llama/llama_index/pull/22195))
- Clarify FactExtractionMemoryBlock condense prompt to return a full snapshot ([#22213](https://github.com/run-llama/llama_index/pull/22213))
- fix a few typos ([#22512](https://github.com/run-llama/llama_index/pull/22512))
- fix(core): give each CitationQueryEngine citation node its own id and offsets ([#22537](https://github.com/run-llama/llama_index/pull/22537))
- fix(core): persist SimpleChatStore without escaping non-ascii ([#22538](https://github.com/run-llama/llama_index/pull/22538))
- feat(core): allow Memory to accept any AsyncDBChatStore ([#22541](https://github.com/run-llama/llama_index/pull/22541))
- test(node_parser): enable pytest discovery for sentence_window tests ([#22545](https://github.com/run-llama/llama_index/pull/22545))
- Implement async for LLMRerank ([#22597](https://github.com/run-llama/llama_index/pull/22597))

###### llama-index-embeddings-bedrock [0.8.3]

- fix: make aioboto3 optional in llama-index-embeddings-bedrock ([#21915](https://github.com/run-llama/llama_index/pull/21915))
- fix(embeddings): validate non-empty Bedrock embedding payload before AWS call ([#22527](https://github.com/run-llama/llama_index/pull/22527))

###### llama-index-embeddings-voyageai [0.6.1]

- fix: set chunk_size=32000 and fix input format for contextualizedembeddings ([#22144](https://github.com/run-llama/llama_index/pull/22144))

###### llama-index-graph-stores-falkordb [0.6.0]

- fix(falkordb): correct schema, vector ranking, filters and batching in property graph store ([#22522](https://github.com/run-llama/llama_index/pull/22522))

###### llama-index-indices-managed-dashscope [0.5.1]

- fix(dashscope): send query_history in retriever payload ([#22212](https://github.com/run-llama/llama_index/pull/22212))

###### llama-index-indices-managed-lancedb [0.3.2]

- fix(lancedb): repair image ingestion crash, embedding_model typo, and… ([#22544](https://github.com/run-llama/llama_index/pull/22544))
- lint ([#22572](https://github.com/run-llama/llama_index/pull/22572))

###### llama-index-llms-anthropic [0.11.10]

- feat(anthropic): Add support for Claude Sonnet 5 ([#22202](https://github.com/run-llama/llama_index/pull/22202))
- Fix/sonnet 5 function calling ([#22217](https:/

_[Truncated at 4000 characters — full notes: https://github.com/run-llama/llama_index/releases/tag/v0.14.24]_