feat: Add chatapi.akash.network
to available list of model providers (FREE LLAMA API ACCESS!)
#1131
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Relates to: -
No Tickets
Risks
Low, new model added
Background
Most developers don't have in-house hardware to run models like LLAMA3.1-405B and so they'll have some sort of server setup. This usually costs money, however there exists a free option today: chatapi.akash.network. This is an openAI api compatible api that runs standard LLMs like llama3.1-405B and llama3.3-70B for free!
The official announcement of the public release: https://x.com/akashnet_/status/1814018478845616362
You can get your api key here: https://chatapi.akash.network
What does this PR do?
Adds a new model provider to the list of model providers
What kind of change is this?
Features
Why are we doing this? Any context or related work?
Im a big fan of the work of akash.network and I've been using this service myself for a while now. Its great to have access to bigger models for testing without risking huge token spends on your personal creditcard
Documentation changes needed?
My changes do not require a change to the project documentation. The env variables are added in the .env.example including the relevant links to where to get the key and how it works.
Testing
I tested it by following the steps below and got the following result:
Where should a reviewer start?
Follow the test steps below (should be really easy!)
Detailed testing steps
Easiest way to test is to do the following:
cp .env.example .env
in the root and set the api key herehttps://github.com/MbBrainz/eliza/blob/de87bfaa308091ff14ff488f5a446cf72b8904c4/.env.example#L234C1-L238C73
./packages/core/src/defaultCharacter.ts
tomodelProvider: ModelProviderName.AKASH_CHAT_API,
pnpm build & pnpm start
7 ✅
Discord username
MbBrainz