LLMs are powerful for knowledge
generation and reasoning, pre-trained on
publicly available data.
To augment LLMs with private data, in-
context learning has emerged as a
paradigm, where context is inserted into
the input prompt.
In-context learning takes advantage of
LLMs' reasoning capabilities to generate
a response, offering a simple and
effective way to use them for data
To perform LLM’s data augmentation in a performant, efficient,
and cheap manner, we need to solve two components:
Provides indices over your unstructured and
structured data for use with LLM’s.
These indices help to abstract away common
boilerplate and pain points for in-context learning:
Storing context in an easy-to-access format for prompt insertion.
Dealing with prompt limitations (e.g. 4096 tokens for Davinci)
when context is too big.
Dealing with text splitting.
Just Starting Out (Vector
Connecting LlamaIndex to
an External Data Source of
across multiple indices
Routing a Query to the
Using Keyword Filters
Context in your Answer
How Each Index Works
Vector Store Index
The vector store index stores each Node and a corresponding
embedding in a Vector Store.