🗂️ LlamaIndex 🦙

LlamaIndex (GPT Index) is a data framework for your LLM application. Building with LlamaIndex typically involves working with LlamaIndex core and a chosen set of integrations (or plugins). There are two ways to start building with LlamaIndex in Python:

1. Starter: pip install llama-index. A starter Python package that includes core LlamaIndex as well as a selection of integrations.

2. Customized: pip install llama-index-core. Install core LlamaIndex and add your chosen LlamaIndex integration packages on LlamaHub that are required for your application. There are over 300 LlamaIndex integration packages that work seamlessly with core, allowing you to build with your preferred LLM, embedding, and vector store providers.

Important Links

• LlamaIndex.TS (Typescript/Javascript)

• Documentation

• Twitter

• Discord

Ecosystem

• LlamaHub (community library of data loaders)
• LlamaLab (cutting-edge AGI projects using LlamaIndex)

🚀 Overview

NOTE: This README is not updated as frequently as the documentation. Please check out the documentation above for the latest updates!

Context

• LLMs are a phenomenal piece of technology for knowledge generation and reasoning. They are pre-trained on large amounts of publicly available data.
• How do we best augment LLMs with our own private data?

We need a comprehensive toolkit to help perform this data augmentation for LLMs.

Proposed Solution

That's where LlamaIndex comes in. LlamaIndex is a "data framework" to help you build LLM apps. It provides the following tools:

• Offers data connectors to ingest your existing data sources and data formats (APIs, PDFs, docs, SQL, etc.).
• Provides ways to structure your data (indices, graphs) so that this data can be easily used with LLMs.
• Provides an advanced retrieval/query interface over your data: Feed in any LLM input prompt, get back retrieved context and knowledge-augmented output.
• Allows easy integrations with your outer application framework (e.g. with LangChain, Flask, Docker, ChatGPT, or anything else).

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.

📄 Documentation

Full documentation can be found here

Please check it out for the most up-to-date tutorials, how-to guides, references, and other resources!

💻 Example Usage

The LlamaIndex Python library is namespaced such that import statements which include core imply that the core package is being used. In contrast, those statements without core imply that an integration package is being used.

# typical pattern
from llama_index.core.xxx import ClassABC  # core submodule xxx
from llama_index.xxx.yyy import (
    SubclassABC,
)  # integration yyy for submodule xxx

# concrete example
from llama_index.core.llms import LLM
from llama_index.llms.openai import OpenAI

To get started, we can install llama-index directly using the starter dependencies (mainly OpenAI):

pip install llama-index

Or we can do a more custom isntallation:

# custom selection of integrations to work with core
pip install llama-index-core
pip install llama-index-llms-openai
pip install llama-index-llms-ollama
pip install llama-index-embeddings-huggingface
pip install llama-index-readers-file

To build a simple vector store index using OpenAI:

import os

os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY"

from llama_index.core 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 models, we can leverage Ollama and HuggingFace. This assumes you've already installed Ollama and have pulled the model you want to use.

from llama_index.core import Settings, VectorStoreIndex, SimpleDirectoryReader
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from llama_index.llms.ollama import Ollama

# set the LLM
llama2_7b_chat = "meta/llama-2-7b-chat:8e6975e5ed6174911a6ff3d60540dfd4844201974602551e10e9e87ab143d81e"
Settings.llm = Ollama(
    model="llama3.1:latest",
    temperature=0.1,
    request_timeout=360.0,
)

# set the embed model
Settings.embed_model = HuggingFaceEmbedding(
    model_name="BAAI/bge-small-en-v1.5",
    embed_batch_size=2,
)

documents = SimpleDirectoryReader("YOUR_DATA_DIRECTORY").load_data()
index = VectorStoreIndex.from_documents(
    documents,
)

To query:

query_engine = index.as_query_engine()
query_engine.query("YOUR_QUESTION")

Or chat:

chat_engine = index.as_chat_engine(chat_mode="condense_plus_context")
chat_engine.chat("YOUR MESSAGE")

By default, data is stored in-memory. To persist to disk (under ./storage):

index.storage_context.persist()

To reload from disk:

from llama_index.core 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)