v0.14.5

Release Notes

[2025-10-15]

llama-index-core [0.14.5]

• Remove debug print (#20000)
• safely initialize RefDocInfo in Docstore (#20031)
• Add progress bar for multiprocess loading (#20048)
• Fix duplicate node positions when identical text appears multiple times in document (#20050)
• chore: tool call block - part 1 (#20074)

llama-index-instrumentation [0.4.2]

• update instrumentation package metadata (#20079)

llama-index-llms-anthropic [0.9.5]

• ✨ feat(anthropic): add prompt caching model validation utilities (#20069)
• fix streaming thinking/tool calling with anthropic (#20077)
• Add haiku 4.5 support (#20092)

llama-index-llms-baseten [0.1.6]

• Baseten provider Kimi K2 0711, Llama 4 Maverick and Llama 4 Scout Model APIs deprecation (#20042)

llama-index-llms-bedrock-converse [0.10.5]

• feat: List Claude Sonnet 4.5 as a reasoning model (#20022)
• feat: Support global cross-region inference profile prefix (#20064)
• Update utils.py for opus 4.1 (#20076)
• 4.1 opus bedrockconverse missing in funcitoncalling models (#20084)
• Add haiku 4.5 support (#20092)

llama-index-llms-fireworks [0.4.4]

• Add Support for Custom Models in Fireworks LLM (#20023)
• fix(llms/fireworks): Cannot use Fireworks Deepseek V3.1-20006 issue (#20028)

llama-index-llms-oci-genai [0.6.3]

• Add support for xAI models in OCI GenAI (#20089)

llama-index-llms-openai [0.6.4]

• Gpt 5 pro addition (#20029)
• fix collecting final response with openai responses streaming (#20037)
• Add support for GPT-5 models in utils.py (JSON_SCHEMA_MODELS) (#20045)
• chore: tool call block - part 1 (#20074)

llama-index-llms-sglang [0.1.0]

• Added Sglang llm integration (#20020)

llama-index-readers-gitlab [0.5.1]

• feat(gitlab): add pagination params for repository tree and issues (#20052)

llama-index-readers-json [0.4.2]

• vbump the JSON reader (#20039)

llama-index-readers-web [0.5.5]

• fix: ScrapflyReader Pydantic validation error (#19999)

llama-index-storage-chat-store-dynamodb [0.4.2]

• bump dynamodb chat store deps (#20078)

llama-index-tools-mcp [0.4.2]

• 🐛 fix(tools/mcp): Fix dict type handling and reference resolution in … (#20082)

llama-index-tools-signnow [0.1.0]

• feat(signnow): SignNow mcp tools integration (#20057)

llama-index-tools-tavily-research [0.4.2]

• feat: Add Tavily extract function for URL content extraction (#20038)

llama-index-vector-stores-azurepostgresql [0.2.0]

• Add hybrid search to Azure PostgreSQL integration (#20027)

llama-index-vector-stores-milvus [0.9.3]

• fix: Milvus get_field_kwargs() (#20086)

llama-index-vector-stores-opensearch [0.6.2]

• fix(opensearch): Correct version check for efficient filtering (#20067)

llama-index-vector-stores-qdrant [0.8.6]

• fix(qdrant): Allow async-only initialization with hybrid search (#20005)

v0.14.4

Release Notes

[2025-09-24]

llama-index-core [0.14.4]

• fix pre-release installs (#20010)

llama-index-embeddings-anyscale [0.4.2]

• fix llm deps for openai (#19944)

llama-index-embeddings-baseten [0.1.2]

• fix llm deps for openai (#19944)

llama-index-embeddings-fireworks [0.4.2]

• fix llm deps for openai (#19944)

llama-index-embeddings-opea [0.2.2]

• fix llm deps for openai (#19944)

llama-index-embeddings-text-embeddings-inference [0.4.2]

• Fix authorization header setup logic in text embeddings inference (#19979)

llama-index-llms-anthropic [0.9.3]

• feat: add anthropic sonnet 4.5 (#19977)

llama-index-llms-anyscale [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-azure-openai [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-baseten [0.1.5]

• fix llm deps for openai (#19944)

llama-index-llms-bedrock-converse [0.9.5]

• feat: Additional support for Claude Sonnet 4.5 (#19980)

llama-index-llms-deepinfra [0.5.2]

• fix llm deps for openai (#19944)

llama-index-llms-everlyai [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-fireworks [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-google-genai [0.6.2]

• Fix for ValueError: ChatMessage contains multiple blocks, use 'ChatMe… (#19954)

llama-index-llms-keywordsai [1.1.2]

• fix llm deps for openai (#19944)

llama-index-llms-localai [0.5.2]

• fix llm deps for openai (#19944)

llama-index-llms-mistralai [0.8.2]

• Update list of MistralAI LLMs (#19981)

llama-index-llms-monsterapi [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-nvidia [0.4.4]

• fix llm deps for openai (#19944)

llama-index-llms-ollama [0.7.4]

• Fix TypeError: unhashable type: 'dict' in Ollama stream chat with tools (#19938)

llama-index-llms-openai [0.6.1]

• feat(OpenAILike): support structured outputs (#19967)

llama-index-llms-openai-like [0.5.3]

• feat(OpenAILike): support structured outputs (#19967)

llama-index-llms-openrouter [0.4.2]

• chore(openrouter,anthropic): add py.typed (#19966)

llama-index-llms-perplexity [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-portkey [0.4.2]

• fix llm deps for openai (#19944)

llama-index-llms-sarvam [0.2.1]

• fixed Sarvam Integration and Typos (Fixes #19931) (#19932)

llama-index-llms-upstage [0.6.4]

• fix llm deps for openai (#19944)

llama-index-llms-yi [0.4.2]

• fix llm deps for openai (#19944)

llama-index-memory-bedrock-agentcore [0.1.0]

• feat: Bedrock AgentCore Memory integration (#19953)

llama-index-multi-modal-llms-openai [0.6.2]

• fix llm deps for openai (#19944)

llama-index-readers-confluence [0.4.4]

• Fix: Respect cloud parameter when fetching child pages in ConfluenceR… (#19983)

llama-index-readers-service-now [0.2.2]

• Bug Fix :- Not Able to Fetch Page whose latest is empty or null (#19916)

llama-index-selectors-notdiamond [0.4.0]

• fix llm deps for openai (#19944)

llama-index-tools-agentql [1.2.0]

• fix llm deps for openai (#19944)

llama-index-tools-playwright [0.3.1]

• chore: fix playwright tests (#19946)

llama-index-tools-scrapegraph [0.2.2]

• feat: update scrapegraphai (#19974)

llama-index-vector-stores-chroma [0.5.3]

• docs: fix query method docstring in ChromaVectorStore Fixes #19969 (#19973)

llama-index-vector-stores-mongodb [0.8.1]

• fix llm deps for openai (#19944)

llama-index-vector-stores-postgres [0.7.0]

• fix index creation in postgres vector store (#19955)

llama-index-vector-stores-solr [0.1.0]

• Add ApacheSolrVectorStore Integration (#19933)

v0.14.3

Release Notes

[2025-09-24]

llama-index-core [0.14.3]

• Fix Gemini thought signature serialization (#19891)
• Adding a ThinkingBlock among content blocks (#19919)

llama-index-llms-anthropic [0.9.0]

• Adding a ThinkingBlock among content blocks (#19919)

llama-index-llms-baseten [0.1.4]

• added kimik2 0905 and reordered list for validation (#19892)
• Baseten Dynamic Model APIs Validation (#19893)

llama-index-llms-google-genai [0.6.0]

• Add missing FileAPI support for documents (#19897)
• Adding a ThinkingBlock among content blocks (#19919)

llama-index-llms-mistralai [0.8.0]

• Adding a ThinkingBlock among content blocks (#19919)

llama-index-llms-openai [0.6.0]

• Adding a ThinkingBlock among content blocks (#19919)

llama-index-protocols-ag-ui [0.2.2]

• improve how state snapshotting works in AG-UI (#19934)

llama-index-readers-mongodb [0.5.0]

• Use PyMongo Asynchronous API instead of Motor (#19875)

llama-index-readers-paddle-ocr [0.1.0]

• [New Package] Add PaddleOCR Reader for extracting text from images in PDFs (#19827)

llama-index-readers-web [0.5.4]

• feat(readers/web-firecrawl): migrate to Firecrawl v2 SDK (#19773)

llama-index-storage-chat-store-mongo [0.3.0]

• Use PyMongo Asynchronous API instead of Motor (#19875)

llama-index-storage-kvstore-mongodb [0.5.0]

• Use PyMongo Asynchronous API instead of Motor (#19875)

llama-index-tools-valyu [0.5.0]

• Add Valyu Extractor and Fast mode (#19915)

llama-index-vector-stores-azureaisearch [0.4.2]

• Fix/llama index vector stores azureaisearch fix (#19800)

llama-index-vector-stores-azurepostgresql [0.1.0]

• Add support for Azure PostgreSQL (#19709)

llama-index-vector-stores-qdrant [0.8.5]

• Add proper compat for old sparse vectors (#19882)

llama-index-vector-stores-singlestoredb [0.4.2]

• Fix SQLi Vulnerability in SingleStore Db (#19914)

v0.14.2

Release Notes

v0.14.1.post1

Release Notes

v0.14.1

Release Notes

v0.14.0

Release Notes

[2025-09-08]

NOTE: All packages have been bumped to handle the latest llama-index-core version.

llama-index-core [0.14.0]

• breaking: bumped llama-index-workflows dependency to 2.0
  • Improve stacktraces clarity by avoiding wrapping errors in WorkflowRuntimeError
  • Remove deprecated checkpointer feature
  • Remove deprecated sub-workflows feature
  • Remove deprecated send_event method from Workflow class (still existing on the Context class)
  • Remove deprecated stream_events() methods from Workflow class (still existing on the Context class)
  • Remove deprecated support for stepwise execution

llama-index-llms-openai [0.5.6]

• feat: add support for document blocks in openai chat completions (#19809)

v0.13.6

Release Notes

v0.13.5

Release Notes

[2025-09-04]

llama-index-core [0.13.5]

• feat: add thinking delta field to AgentStream events to expose from LLM responses (#19785)
• fix: fix path handling in SimpleDirectoryReader and PDFReader path fix (#19794)

llama-index-llms-bedrock-converse [0.9.0]

• feat: add system prompt and tool caching config kwargs to BedrockConverse (#19737)

llama-index-llms-litellm [0.6.2]

• fix: Handle missing tool call IDs with UUID fallback (#19789)
• fix: Fix critical context window calculation (#19787)

llama-index-readers-file [0.5.3]

• fix: fix path handling in SimpleDirectoryReader and PDFReader path fix (#19794)

llama-index-storage-chat-store-yugabytedb [0.1.0]

• feat: add Yugabytedb chat store (#19768)

llama-index-vector-stores-milvus [0.9.1]

• fix: create TextNode if no '_node_content' set (#19772)

llama-index-vector-stores-postgres [0.6.5]

• fix: make postgres regex punctuation handling consistent with plainto_tsquery (#19781)

v0.13.4

Release Notes

[2025-09-01]

llama-index-core [0.13.4]

• feat: Add PostgreSQL schema support to Memory and SQLAlchemyChatStore (#19741)
• feat: add missing sync wrapper of put_messages in memory (#19746)
• feat: add option for an initial tool choice in FunctionAgent (#19738)
• fix: Calling ContextChatEngine with a QueryBundle (instead of a string) (#19714)

llama-index-embeddings-baseten [0.1.0]

• feat: baseten integration (#19710)

llama-index-embeddings-ibm [0.5.0]

• feat: Support for additional/external urls, make instance_id deprecated (#19749)

llama-index-llms-baseten [0.1.0]

• feat: baseten integration (#19710)

llama-index-llms-bedrock-converse [0.8.3]

• feat: add amazon.nova-premier-v1:0 to BEDROCK_MODELS (#19728)

llama-index-llms-ibm [0.6.0]

• feat: Support for additional/external urls, make instance_id deprecated (#19749)

llama-index-postprocessor-ibm [0.3.0]

• feat: Support for additional/external urls, make instance_id deprecated (#19749)

llama-index-postprocessor-sbert-rerank [0.4.1]

• fix: fix SentenceTransformerRerank init device (#19756)

llama-index-readers-google [0.7.1]

• feat: raise google drive errors (#19752)

llama-index-readers-web [0.5.1]

• feat: Add ZenRows web reader (#19699)

llama-index-vector-stores-chroma [0.5.2]

• feat: add mmr search to chroma (#19731)

llama-index-vector-stores-postgres [0.6.4]

• fix: Use the indexed metadata field 'ref_doc_id' instead of 'doc_id' during deletion (#19759)

llama-index-vector-stores-qdrant [0.8.2]

feat: Payload indexes support to QdrantVectorStore (#19743)