Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add prominent note about LLM access and instructions on how to get keys #159

Merged
merged 1 commit into from
Nov 2, 2023
Merged

add prominent note about LLM access and instructions on how to get keys #159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,12 @@ With an intuitive API for quick experimentation and built-in tools for creating
production-ready application, you can quickly leverage Large Language Models (LLMs) for
your work.

!!! note

Ragna is a framework for experimenting with LLMs. It does not install one by default. To use Ragna you either need to provide API keys to a cloud LLM API, e.g. OpenAI, Anthropic, etc. or run your own LLM.

[Learn more →](references/faq.md)

[Get started](install.md){ .md-button }

## Key features
Expand Down
33 changes: 22 additions & 11 deletions docs/references/faq.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
# Frequently asked questions

## How to use the GPT assistants in Ragna?
## Where do I get API keys for the builtin assistants?

### [OpenAI](https://openai.com/)

1. Get an OpenAI API key following these instructions:
> First, create an OpenAI account or sign in. Next, navigate to the API key page and
Expand All @@ -13,18 +15,27 @@
```bash
export OPENAI_API_KEY="XXXXX"
```
3. Configure Ragna to use the `Gpt35Turbo16k` or `Gpt4` assistants in the
`ragna-s3.toml` file or with the `Rag.chat` function:

```py
from ragna.source_storages import Gpt35Turbo16k
### [Anthropic](https://www.anthropic.com)

...
1. Anthropic currently only provides API keys to business customers:
> Our API is currently being offered to a limited set of users. We hope to expand
> access in the future. Please fill out the form below to indicate your interest
>
> ~ [Claude API Access](https://www.anthropic.com/earlyaccess)
2. Set the `ANTHROPIC_API_KEY` environment variable with your Anthropic API key:
```bash
export ANTHROPIC_API_KEY="XXXXX"
```

async with rag.chat(assistant=Gpt35Turbo16k) as chat:
prompt = "Is this a question?"
answer = await chat.answer(prompt)
### [MosaicML](https://mosaicml.com)

1. MosaicML currently has a waitlist for new users:
> We are currently experiencing very high demand and have a waitlist. Please stay
> tuned for when we open for broader access.
>
> ~ [MosaicML console](https://console.mosaicml.com/)
2. Set the `MOSAICML_API_KEY` environment variable with your MosaicML API key:
```bash
export MOSAICML_API_KEY="XXXXX"
```

<!-- ## Where to share feedback with developers? -->
Loading