Skip to main content

Interface between LLMs and your data

Project description

LlamaIndex Core

The core python package to the LlamaIndex library. Core classes and abstractions represent the foundational building blocks for LLM applications, most notably, RAG. Such building blocks include abstractions for LLMs, Vector Stores, Embeddings, Storage, Callables and several others.

We've designed the core library so that it can be easily extended through subclasses. Building LLM applications with LlamaIndex thus involves building with LlamaIndex core as well as with the LlamaIndex integrations needed for your application.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llama_index_core-0.12.5.tar.gz (1.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llama_index_core-0.12.5-py3-none-any.whl (1.6 MB view details)

Uploaded Python 3

File details

Details for the file llama_index_core-0.12.5.tar.gz.

File metadata

  • Download URL: llama_index_core-0.12.5.tar.gz
  • Upload date:
  • Size: 1.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.10 Darwin/24.1.0

File hashes

Hashes for llama_index_core-0.12.5.tar.gz
Algorithm Hash digest
SHA256 1d967323891920579fad3d6497587c137894df3f76718a3ec134f9201f2f4fc0
MD5 abaefca4dc9629ae4d723a764b5da9c9
BLAKE2b-256 0357d294859e663bb82db35abaa4cc83e68ee424a6dbbac45e62efbbdcc44f33

See more details on using hashes here.

File details

Details for the file llama_index_core-0.12.5-py3-none-any.whl.

File metadata

  • Download URL: llama_index_core-0.12.5-py3-none-any.whl
  • Upload date:
  • Size: 1.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.10 Darwin/24.1.0

File hashes

Hashes for llama_index_core-0.12.5-py3-none-any.whl
Algorithm Hash digest
SHA256 1fe6dd39b2dc5a945b4702d780a2f5962a553e187524a255429461dc92a664db
MD5 6541dc9120bb432608ab08073356fb64
BLAKE2b-256 577871984bb2cc8fe5c70d7986ee5034f5b10e07ecf751ada58ca1212ecc7bf7

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page