NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #1636 most downloaded on PyPI
Interface between LLMs and your data
Latest stable
0.14.25
Last release 2 months ago
21 Sep 2026
Ships fairly regularly
a new release about every 3 weeks
Most releases are documented
notes for 45 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
258 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Nothing published for this version
removed deprecated ServiceContext -- using this now will print an error with a link to the migration guide
llama-index-core [0.11.0]ServiceContext -- using this now will print an error with a link to the migration guideLLMPredictor -- using this now will print an error, any existing LLM is a drop-in replacementpandas an optional dependencyEverything Elsellama-index-coreNothing published for this version
remove nested progress bars in base element node parser
llama-index-core [0.10.68]llama-index-embeddings-mistralai [0.1.6]llama-index-embeddings-ollama [0.2.0]llama-index-embeddings-openvino [0.2.1]llama-index-graph-stores-neptune [0.1.8]llama-index-llms-ai21 [0.3.2]llama-index-llms-bedrock [0.1.13]llama-index-llms-cohere [0.2.2]llama-index-llms-gigachat [0.1.0]llama-index-llms-openai [0.1.31]llama-index-postprocessor-nvidia-rerank [0.2.1]llama-index-readers-bitbucket [0.1.4]llama-index-readers-google [0.3.1]llama-index-readers-remote [0.1.6]llama-index-vector-stores-qdrant [0.2.17]Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Introduce Workflows for event-driven orchestration
llama-index-core [0.10.59]Workflows for event-driven orchestration (#15067)asyncio_run() (#14970)llama-index-embeddings-ollama [0.1.3]llama-index-embeddings-textembed [0.0.1]llama-index-graph-stores-falkordb [0.1.5]llama-index-llms-azure-inference [0.1.1]llama-index-llms-fireworks [0.1.7]llama-index-llms-ollama [0.2.2]llama-index-llms-openllm [0.2.0]llama-index-packs-longrag [0.1.0]llama-index-postprocessor-tei-rerank [0.1.0]llama-index-readers-confluence [0.1.7]llama-index-readers-file [0.1.31]llama-index-readers-gitlab [0.1.0]llama-index-readers-google [0.2.11]llama-index-retrievers-bm25 [0.2.2]llama-index-vector-stores-azureaisearch [0.1.13]llama-index-vector-stores-elasticsearch [0.2.5]llama-index-vector-stores-kdbai [0.2.0]llama-index-vector-stores-milvus [0.1.22]llama-index-vector-stores-postgres [0.1.13]Nothing published for this version
Nothing published for this version
Nothing published for this version
Add an optional parameter similarity_score to VectorContextRetrieve…
llama-index-core [v0.10.57]llama-index-llms-azure-openai [0.1.10]llama-index-llms-bedrock-converse [0.1.5]llama-index-llms-langchain [0.3.0]llama-index-llms-ollama [0.1.6]llama-index-multi-modal-llms-anthropic [0.1.5]llama-index-readers-notion [0.1.10]llama-index-vector-stores-milvus [0.1.21]llama-index-vector-stores-mongodb [0.1.8]llama-index-vector-stores-opensearch [0.1.13]llama-index-vector-stores-pinecone [0.1.8]llama-index-vector-stores-postgres [0.1.12]llama-index-vector-stores-weaviate [1.0.2]Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
deprecate query pipeline agent in favor of FnAgentWorker (#14525O)
llama-index-core [0.10.52]llama-index-callbacks-arize-phoenix [0.1.6]llama-index-embeddings-litellm [0.1.0]llama-index-finetuning [0.1.10]llama-index-graph-stores-neo4 [0.2.7]llama-index-llms-bedrock [0.1.10]llama-index-llms-bedrock-converse [0.1.4]llama-index-llms-upstage [0.1.4]llama-index-readers-azstorage-blob [0.1.7]llama-index-readers-file [0.1.26]llama-index-readers-iceberg [0.1.0]llama-index-readers-notion [0.1.8]list_databases method (#14488)llama-index-readers-slack [0.1.5]llama-index-readers-web [0.1.21]llama-index-retrievers-bm25 [0.1.5]llama-index-vector-stores-azureaisearch [0.1.9]llama-index-vector-stores-kdbai [0.1.8]llama-index-vector-stores-mongodb [0.1.6]Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
use default UUIDs when possible for property graph index vector stores
llama-index-core [0.10.43]get_rel_map in simple property graph store (#13888)llama-index-graph-stores-neo4j [0.2.2]Neo4jPGStore to Neo4jPropertyGraphStore (with backward compat) (#13891)llama-index-llms-openai [0.1.22]llama-index-readers-web [0.1.18]llama-index-vector-stores-opensearch [0.1.10]Allow proper setting of the vector store in property graph index
llama-index-core [0.10.42]llama-index-graph-stores-nebula [0.2.0]llama-index-llms-langchain [0.1.5]llama-index-llms-openllm [0.1.5]llama-index-llms-premai [0.1.5]llama-index-readers-google [0.2.6]pass embeddings from index to property graph retriever
llama-index-core [0.10.41]llama-index-llms-gemini [0.1.10]model kwarg for model name for gemini (#13791)llama-index-llms-mistralai [0.1.15]llama-index-llms-openllm [0.1.5]llama-index-llms-vertex [0.1.8]llama-index-readers-smart-pdf-loader [0.1.5]Added PropertyGraphIndex and other supporting abstractions. See the full guide for more details
llama-index-core [0.10.40]PropertyGraphIndex and other supporting abstractions. See the full guide for more details (#13747)AutoPrevNextNodePostprocessor to allow passing in response mode and LLM (#13771)_aget_retrieved_ids_and_texts in retrievval evaluator (#13765)self._query_transform (#13756)SimpleVectorStoreIndex (#13365)llama-index-embeddings-bedrock [0.2.0]llama-index-embeddings-oci-genai [0.1.0]llama-index-embeddings-huggingface [0.2.1]llama-index-graph-stores-neo4j [0.2.0]Neo4jPGStore for property graph support (#13747)llama-index-indices-managed-dashscope [0.1.1]llama-index-llms-oci-genai [0.1.0]llama-index-readers-feishu-wiki [0.1.1]llama-index-packs-secgpt [0.1.0]llama-index-vector-stores-hologres [0.1.0]llama-index-vector-stores-milvus [0.1.16]llama-index-vector-stores-opensearch [0.1.9]Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Add CRITIC and reflection agent integrations
llama-index-agent-introspective [0.1.0]llama-index-core [0.10.35]from_defaults() erasing summary memory buffer history (#13325)asyncio.run() in core (#13309)llama-index-embeddings-jinaai [0.1.5]llama-index-embeddings-nvidia [0.1.0]llama-index-llms-mistralai [0.1.12]llama-index-llms-nvidia [0.1.0]llama-index-postprocessor-nvidia-rerank [0.1.0]llama-index-readers-file [0.1.21]llama-index-readers-web [0.1.13]llama-index-vector-stores-vespa [0.1.0]llama-index-vector-stores-vertexaivectorsearch [0.1.0]remove error ignoring during chat engine streaming
llama-index-core [0.10.34]source_node.node_id verification to node parsers (#13109)llama-index-indices-managed-zilliz [0.1.3]llama-index-llms-huggingface [0.1.7]llama-index-llms-maritalk [0.2.0]llama-index-llms-mistral-rs [0.1.0]llama-index-llms-mymagic [0.1.7]llama-index-llms-nvidia-triton [0.1.5]llama-index-llms-ollama [0.1.3]llama-index-readers-microsoft-sharepoint [0.2.2]llama-index-readers-web [0.1.11]llama-index-readers-youtube-metadata [0.1.0]llama-index-storage-kvstore-redis [0.1.4]llama-index-vector-stores-azureaisearch [0.1.5]llama-index-vector-stores-chroma [0.1.7]llama-index-vector-stores-firestore [0.1.0]llama-index-vector-stores-kdbai [0.1.5]add() (#12515)llama-index-vector-stores-milvus [0.1.11]llama-index-vector-stores-postgres [0.1.7]Nothing published for this version
Nothing published for this version
fix async streaming response from query engine
llama-index-core [0.10.31]llama-index-agent-coa [0.1.0]llama-index-agent-lats [0.1.0]llama-index-agent-llm-compiler [0.1.0]llama-index-llms-anthropic [0.1.10]llama-index-llms-bedrock [0.1.7]llama-index-llms-fireworks [0.1.5]llama-index-llms-openai [0.1.16]llama-index-llms-watsonx [0.1.7]llama-index-packs-code-hierarchy [0.1.6]llama-index-program-openai [0.1.6]llama-index-readers-openapi [0.1.0]llama-index-readers-slack [0.1.4]llama-index-readers-web [0.1.10]llama-index-retrievers-bedrock [0.1.1]llama-index-vector-stores-awsdocdb [0.1.0]llama-index-vector-stores-databricks [0.1.2]llama-index-vector-stores-neo4j [0.1.4]llama-index-vector-stores-pinecone [0.1.5]llama-index-vector-stores-qdrant [0.2.5]llama-index-vector-stores-weaviate [0.1.5]One column per month.