mirror of
https://github.com/googleapis/genai-toolbox.git
synced 2026-01-23 14:28:15 -05:00
01ac3134c0
This PR contains the following updates: | Package | Change | Age | Confidence | |---|---|---|---| | [llama-index](https://redirect.github.com/run-llama/llama_index) | `==0.14.4` -> `==0.14.6` | [](https://docs.renovatebot.com/merge-confidence/) | [](https://docs.renovatebot.com/merge-confidence/) | --- ### Release Notes <details> <summary>run-llama/llama_index (llama-index)</summary> ### [`v0.14.6`](https://redirect.github.com/run-llama/llama_index/blob/HEAD/CHANGELOG.md#2025-10-26) [Compare Source](https://redirect.github.com/run-llama/llama_index/compare/v0.14.5...v0.14.6) ##### llama-index-core \[0.14.6] - Add allow\_parallel\_tool\_calls for non-streaming ([#​20117](https://redirect.github.com/run-llama/llama_index/pull/20117)) - Fix invalid use of field-specific metadata ([#​20122](https://redirect.github.com/run-llama/llama_index/pull/20122)) - update doc for SemanticSplitterNodeParser ([#​20125](https://redirect.github.com/run-llama/llama_index/pull/20125)) - fix rare cases when sentence splits are larger than chunk size ([#​20147](https://redirect.github.com/run-llama/llama_index/pull/20147)) ##### llama-index-embeddings-bedrock \[0.7.0] - Fix BedrockEmbedding to support Cohere v4 response format ([#​20094](https://redirect.github.com/run-llama/llama_index/pull/20094)) ##### llama-index-embeddings-isaacus \[0.1.0] - feat: Isaacus embeddings integration ([#​20124](https://redirect.github.com/run-llama/llama_index/pull/20124)) ##### llama-index-embeddings-oci-genai \[0.4.2] - Update OCI GenAI cohere models ([#​20146](https://redirect.github.com/run-llama/llama_index/pull/20146)) ##### llama-index-llms-anthropic \[0.9.7] - Fix double token stream in anthropic llm ([#​20108](https://redirect.github.com/run-llama/llama_index/pull/20108)) - Ensure anthropic content delta only has user facing response ([#​20113](https://redirect.github.com/run-llama/llama_index/pull/20113)) ##### llama-index-llms-baseten \[0.1.7] - add GLM ([#​20121](https://redirect.github.com/run-llama/llama_index/pull/20121)) ##### llama-index-llms-helicone \[0.1.0] - integrate helicone to llama-index ([#​20131](https://redirect.github.com/run-llama/llama_index/pull/20131)) ##### llama-index-llms-oci-genai \[0.6.4] - Update OCI GenAI cohere models ([#​20146](https://redirect.github.com/run-llama/llama_index/pull/20146)) ##### llama-index-llms-openai \[0.6.5] - chore: openai vbump ([#​20095](https://redirect.github.com/run-llama/llama_index/pull/20095)) ##### llama-index-readers-imdb-review \[0.4.2] - chore: Update selenium dependency in imdb-review reader ([#​20105](https://redirect.github.com/run-llama/llama_index/pull/20105)) ##### llama-index-retrievers-bedrock \[0.5.0] - feat(bedrock): add async support for AmazonKnowledgeBasesRetriever ([#​20114](https://redirect.github.com/run-llama/llama_index/pull/20114)) ##### llama-index-retrievers-superlinked \[0.1.3] - Update README.md ([#​19829](https://redirect.github.com/run-llama/llama_index/pull/19829)) ##### llama-index-storage-kvstore-postgres \[0.4.2] - fix: Replace raw SQL string interpolation with proper SQLAlchemy parameterized APIs in PostgresKVStore ([#​20104](https://redirect.github.com/run-llama/llama_index/pull/20104)) ##### llama-index-tools-mcp \[0.4.3] - Fix BasicMCPClient resource signatures ([#​20118](https://redirect.github.com/run-llama/llama_index/pull/20118)) ##### llama-index-vector-stores-postgres \[0.7.1] - Add GIN index support for text array metadata in PostgreSQL vector store ([#​20130](https://redirect.github.com/run-llama/llama_index/pull/20130)) ### [`v0.14.5`](https://redirect.github.com/run-llama/llama_index/blob/HEAD/CHANGELOG.md#2025-10-15) [Compare Source](https://redirect.github.com/run-llama/llama_index/compare/v0.14.4...v0.14.5) ##### llama-index-core \[0.14.5] - Remove debug print ([#​20000](https://redirect.github.com/run-llama/llama_index/pull/20000)) - safely initialize RefDocInfo in Docstore ([#​20031](https://redirect.github.com/run-llama/llama_index/pull/20031)) - Add progress bar for multiprocess loading ([#​20048](https://redirect.github.com/run-llama/llama_index/pull/20048)) - Fix duplicate node positions when identical text appears multiple times in document ([#​20050](https://redirect.github.com/run-llama/llama_index/pull/20050)) - chore: tool call block - part 1 ([#​20074](https://redirect.github.com/run-llama/llama_index/pull/20074)) ##### llama-index-instrumentation \[0.4.2] - update instrumentation package metadata ([#​20079](https://redirect.github.com/run-llama/llama_index/pull/20079)) ##### llama-index-llms-anthropic \[0.9.5] - ✨ feat(anthropic): add prompt caching model validation utilities ([#​20069](https://redirect.github.com/run-llama/llama_index/pull/20069)) - fix streaming thinking/tool calling with anthropic ([#​20077](https://redirect.github.com/run-llama/llama_index/pull/20077)) - Add haiku 4.5 support ([#​20092](https://redirect.github.com/run-llama/llama_index/pull/20092)) ##### llama-index-llms-baseten \[0.1.6] - Baseten provider Kimi K2 0711, Llama 4 Maverick and Llama 4 Scout Model APIs deprecation ([#​20042](https://redirect.github.com/run-llama/llama_index/pull/20042)) ##### llama-index-llms-bedrock-converse \[0.10.5] - feat: List Claude Sonnet 4.5 as a reasoning model ([#​20022](https://redirect.github.com/run-llama/llama_index/pull/20022)) - feat: Support global cross-region inference profile prefix ([#​20064](https://redirect.github.com/run-llama/llama_index/pull/20064)) - Update utils.py for opus 4.1 ([#​20076](https://redirect.github.com/run-llama/llama_index/pull/20076)) - 4.1 opus bedrockconverse missing in funcitoncalling models ([#​20084](https://redirect.github.com/run-llama/llama_index/pull/20084)) - Add haiku 4.5 support ([#​20092](https://redirect.github.com/run-llama/llama_index/pull/20092)) ##### llama-index-llms-fireworks \[0.4.4] - Add Support for Custom Models in Fireworks LLM ([#​20023](https://redirect.github.com/run-llama/llama_index/pull/20023)) - fix(llms/fireworks): Cannot use Fireworks Deepseek V3.1-20006 issue ([#​20028](https://redirect.github.com/run-llama/llama_index/pull/20028)) ##### llama-index-llms-oci-genai \[0.6.3] - Add support for xAI models in OCI GenAI ([#​20089](https://redirect.github.com/run-llama/llama_index/pull/20089)) ##### llama-index-llms-openai \[0.6.4] - Gpt 5 pro addition ([#​20029](https://redirect.github.com/run-llama/llama_index/pull/20029)) - fix collecting final response with openai responses streaming ([#​20037](https://redirect.github.com/run-llama/llama_index/pull/20037)) - Add support for GPT-5 models in utils.py (JSON\_SCHEMA\_MODELS) ([#​20045](https://redirect.github.com/run-llama/llama_index/pull/20045)) - chore: tool call block - part 1 ([#​20074](https://redirect.github.com/run-llama/llama_index/pull/20074)) ##### llama-index-llms-sglang \[0.1.0] - Added Sglang llm integration ([#​20020](https://redirect.github.com/run-llama/llama_index/pull/20020)) ##### llama-index-readers-gitlab \[0.5.1] - feat(gitlab): add pagination params for repository tree and issues ([#​20052](https://redirect.github.com/run-llama/llama_index/pull/20052)) ##### llama-index-readers-json \[0.4.2] - vbump the JSON reader ([#​20039](https://redirect.github.com/run-llama/llama_index/pull/20039)) ##### llama-index-readers-web \[0.5.5] - fix: ScrapflyReader Pydantic validation error ([#​19999](https://redirect.github.com/run-llama/llama_index/pull/19999)) ##### llama-index-storage-chat-store-dynamodb \[0.4.2] - bump dynamodb chat store deps ([#​20078](https://redirect.github.com/run-llama/llama_index/pull/20078)) ##### llama-index-tools-mcp \[0.4.2] - 🐛 fix(tools/mcp): Fix dict type handling and reference resolution in … ([#​20082](https://redirect.github.com/run-llama/llama_index/pull/20082)) ##### llama-index-tools-signnow \[0.1.0] - feat(signnow): SignNow mcp tools integration ([#​20057](https://redirect.github.com/run-llama/llama_index/pull/20057)) ##### llama-index-tools-tavily-research \[0.4.2] - feat: Add Tavily extract function for URL content extraction ([#​20038](https://redirect.github.com/run-llama/llama_index/pull/20038)) ##### llama-index-vector-stores-azurepostgresql \[0.2.0] - Add hybrid search to Azure PostgreSQL integration ([#​20027](https://redirect.github.com/run-llama/llama_index/pull/20027)) ##### llama-index-vector-stores-milvus \[0.9.3] - fix: Milvus get\_field\_kwargs() ([#​20086](https://redirect.github.com/run-llama/llama_index/pull/20086)) ##### llama-index-vector-stores-opensearch \[0.6.2] - fix(opensearch): Correct version check for efficient filtering ([#​20067](https://redirect.github.com/run-llama/llama_index/pull/20067)) ##### llama-index-vector-stores-qdrant \[0.8.6] - fix(qdrant): Allow async-only initialization with hybrid search ([#​20005](https://redirect.github.com/run-llama/llama_index/pull/20005)) </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR was generated by [Mend Renovate](https://mend.io/renovate/). View the [repository job log](https://developer.mend.io/github/googleapis/genai-toolbox). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0MS4xNTYuMSIsInVwZGF0ZWRJblZlciI6IjQxLjE1Ni4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6W119--> Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>