Interface between LLMs and your data
LlamaIndex (GPT Index) is a data framework for your LLM application.
PyPI:
LlamaIndex.TS (Typescript/Javascript): https://github.com/run-llama/LlamaIndexTS.
Documentation: https://docs.llamaindex.ai/en/stable/.
Twitter: https://twitter.com/llama_index.
Discord: https://discord.gg/dGcwcsnxhU.
NOTE: This README is not updated as frequently as the documentation. Please check out the documentation above for the latest updates!
We need a comprehensive toolkit to help perform this data augmentation for LLMs.
That's where LlamaIndex comes in. LlamaIndex is a "data framework" to help you build LLM apps. It provides the following tools:
LlamaIndex provides tools for both beginner users and advanced users. Our high-level API allows beginner users to use LlamaIndex to ingest and query their data in 5 lines of code. Our lower-level APIs allow advanced users to customize and extend any module (data connectors, indices, retrievers, query engines, reranking modules), to fit their needs.
Interested in contributing? See our Contribution Guide for more details.
Full documentation can be found here: https://gpt-index.readthedocs.io/en/latest/.
Please check it out for the most up-to-date tutorials, how-to guides, references, and other resources!
pip install llama-index
Examples are in the examples
folder. Indices are in the indices
folder (see list of indices below).
To build a simple vector store index using OpenAI:
import os
os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"
from llama_index import VectorStoreIndex, SimpleDirectoryReader
documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(documents)
To build a simple vector store index using non-OpenAI LLMs, e.g. Llama 2 hosted on Replicate, where you can easily create a free trial API token:
import os
os.environ["REPLICATE_API_TOKEN"] = "YOUR_REPLICATE_API_TOKEN"
from llama_index.llms import Replicate
llama2_7b_chat = "meta/llama-2-7b-chat:8e6975e5ed6174911a6ff3d60540dfd4844201974602551e10e9e87ab143d81e"
llm = Replicate(
model=llama2_7b_chat,
temperature=0.01,
additional_kwargs={"top_p": 1, "max_new_tokens": 300},
)
# set tokenizer to match LLM
from llama_index import set_global_tokenizer
from transformers import AutoTokenizer
set_global_tokenizer(
AutoTokenizer.from_pretrained("NousResearch/Llama-2-7b-chat-hf").encode
)
from llama_index.embeddings import HuggingFaceEmbedding
from llama_index import ServiceContext
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
service_context = ServiceContext.from_defaults(
llm=llm, embed_model=embed_model
)
from llama_index import VectorStoreIndex, SimpleDirectoryReader
documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(
documents, service_context=service_context
)
To query:
query_engine = index.as_query_engine()
query_engine.query("YOUR_QUESTION")
By default, data is stored in-memory.
To persist to disk (under ./storage
):
index.storage_context.persist()
To reload from disk:
from llama_index import StorageContext, load_index_from_storage
# rebuild storage context
storage_context = StorageContext.from_defaults(persist_dir="./storage")
# load index
index = load_index_from_storage(storage_context)
The main third-party package requirements are tiktoken
, openai
, and langchain
.
All requirements should be contained within the setup.py
file.
To run the package locally without building the wheel, simply run:
pip install poetry
poetry install --with dev
Reference to cite if you use LlamaIndex in a paper:
@software{Liu_LlamaIndex_2022,
author = {Liu, Jerry},
doi = {10.5281/zenodo.1234},
month = {11},
title = {{LlamaIndex}},
url = {https://github.com/jerryjliu/llama_index},
year = {2022}
}