Question: The documentation is not clear about what the project really does

[murilocurti]

What the project really does for us?

The Proposed Solution:

That’s where the LlamaIndex comes in. LlamaIndex is a simple, flexible interface between your external data and LLMs. It resolves the > following pain points:

Provides simple data structures to resolve prompt size limitations.

Offers data connectors to your external data sources.

Offers you a comprehensive toolset trading off cost and performance.

At the core of LlamaIndex is a data structure. Instead of relying on world knowledge encoded in the model weights, a GPT Index data > structure does the following:

Uses a pre-trained LLM primarily for reasoning/summarization instead of prior knowledge.

Takes as input a large corpus of text data and build a structured index over it (using an LLM or heuristics).

Allow users to query the index by passing in an LLM prompt, and obtaining a response.

Could explain what and how the project solves the problem. I suggest a drawing with a flow and explain what happens when creating the index and when a prompt is made by the user.

[RahulPrasad]

I would love to see more detailed doc +1

[logan-markewich]

Docs have been revamped lately, check them out!

I especially like the high-level concepts section https://gpt-index.readthedocs.io/en/latest/getting_started/concepts.html