NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #1472 most downloaded on PyPI
Interface between LLMs and your data
Last release 13 days 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Nothing withdrawn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
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
One column per month.
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
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
Nothing published for this version
Nothing published for this version
Nothing published for this version
NOTE: Updating to v0.12.0 will require bumping every other llama-index-* package! Every package has had a version bump. Only notable changes are below
NOTE: Updating to v0.12.0 will require bumping every other llama-index-* package! Every package has had a version bump. Only notable changes are below.
llama-index-core [0.12.0]llama-index-indices-managed-llama-cloud [0.6.1]llama-index-indices-managed-vectara [0.3.0]llama-index-llms-bedrock [0.3.0]llama-index-llms-bedrock-converse [0.4.0]llama-index-multi-modal-llms-nvidia [0.2.0]llama-index-readers-confluence [0.3.0]llama-index-readers-github [0.5.0]llama-index-vector-stores-weaviate [1.2.0]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
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
Nothing published for this version
Nothing published for this version
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
Your coding agent can read these notes before it upgrades. Set up the MCP server →