Skip to content

Commit

Permalink
Update the documentation structure (#6)
Browse files Browse the repository at this point in the history
Signed-off-by: Aivin V. Solatorio <[email protected]>
  • Loading branch information
avsolatorio authored May 31, 2023
1 parent 3ad8338 commit b7f00d5
Show file tree
Hide file tree
Showing 5 changed files with 20 additions and 5 deletions.
11 changes: 10 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

LLM4Data is a Python library designed to facilitate the application of large language models (LLMs) and artificial intelligence for data and knowledge discovery. It is intended to empower users and organizations to discover and interact with development data in innovative ways through natural language.

This library contains a collection of discovery and data augmentation solutions for various data types including documents, indicators, microdata, geospatial data, and more. The current version of the library includes solutions for the WDI indicators. Additional solutions will be added in [future releases](#upcoming-features).
This library contains a collection of discovery and data augmentation solutions for various data types including documents, indicators, microdata, geospatial data, and more. The current version of the library includes solutions for the WDI indicators. Additional solutions will be added in [future releases](https://worldbank.github.io/llm4data/README.html#upcoming-features).

Built around existing [metadata standards and schemas](https://mah0001.github.io/schema-guide/), users and organizations can benefit from LLMs to enhance data-driven applications, enabling natural language processing, text generation, and more with LLM4Data. The library serves as a bridge between LLMs and development data using open-sourced libraries, offering a seamless interface to leverage the capabilities of these powerful language models.

Expand All @@ -22,6 +22,11 @@ Additional examples can be found [here](notebooks/examples/).

### Generate WDI API URL from a prompt

```{warning}
This example uses the OpenAI API. Before you proceed, make sure to set your API keys in the `.env` file.
```


```python
from llm4data.prompts.indicators import wdi

Expand Down Expand Up @@ -50,6 +55,10 @@ The URL also includes the date range, format, and source of the data. The user c

### Generate SQL queries on WDI data from a prompt

```{warning}
Make sure you have set up your environment first. The example below requires a working database engine, e.g., postgresql. If you want to use SQLite, make sure to update the `.env` file and set the environment variables.
```

While the WDI data can be loaded into a Pandas dataframe, it is not always practical to do so; for example, developing applications that can answer arbitrary data questions.

The LLM4Data library includes an SQL interface to WDI data, allowing users to query the data using SQL.
Expand Down
14 changes: 10 additions & 4 deletions docs/_toc.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,17 @@ format: jb-book
root: README

parts:
- caption: Setting up the environment
- caption: Getting started
chapters:
- file: notebooks/examples/"Setting up the environment.ipynb"
- caption: Indicators
- file: notebooks/examples/getting-started/setting-up-the-environment.ipynb
- file: notebooks/examples/getting-started/openai-api.ipynb
- file: notebooks/examples/getting-started/setting-up-database.ipynb
sections:
- file: notebooks/examples/getting-started/setting-up-database-sqlite.ipynb
- file: notebooks/examples/getting-started/setting-up-database-postgresql.ipynb
- file: notebooks/examples/getting-started/setting-up-vectorstore.ipynb
- caption: Development Data
chapters:
- file: notebooks/examples/indicators/README
sections:
- file: notebooks/examples/indicators/"Getting started with the WDI.ipynb"
- file: notebooks/examples/indicators/wdi/getting-started-with-the-wdi.ipynb
File renamed without changes.

0 comments on commit b7f00d5

Please sign in to comment.