v0.4.23

LlamaIndex 0.4.23 🦙 brings some exciting new functionality:

• Upgraded LlamaIndex memory module <> langchain agent.
• Added “empty” Index - more explicitly combine prior knowledge with knowledge corpus.
• 🚢 Steamship file reader (thanks @douglas-reid)

v0.4.22.post1

v0.4.22.post1

v0.4.22

LlamaIndex 0.4.22: a LOT of quality-of-life improvements 💪:

• Fixed empty text split issue
• Reduce required deps in package (s/o Ajinkya)
• Simplify UX for custom prompts
• Simply UX for SQL Index

v0.4.21

LlamaIndex 0.4.21 🦙: a new JSON reader + better ChatGPT integrations!

• A BIG shoutout to @yisding for coming up with novel JSON parsing. Added to both LlamaIndex + LlamaHub!
• Better ChatGPT Integrations 💬

v0.4.20

LlamaIndex v0.4.20

v0.4.19

Adds streaming support!

v0.4.18

LlamaIndex v0.4.18

v0.4.17

LlamaIndex v0.4.17

v0.4.16

LlamaIndex 0.4.16:

• Elastic data loader + Opensearch based vector index! (Huge s/o @jaylmiller )
• Add child branch factor for tree index embedding queries (thanks @kpister )

v0.4.15

• Biggest update is that we’ve fixed the composability over vector stores
• Added @weaviate_io multi-threaded batch importing to decrease load time