-
Notifications
You must be signed in to change notification settings - Fork 683
feat: add NVIDIA NIM provider #706
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.
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
Open
kexiv
wants to merge
6
commits into
mindcraft-bots:develop
Choose a base branch
from
kexiv:develop
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+58
−1
Open
Changes from all commits
Commits
Show all changes
6 commits
Select commit
Hold shift + click to select a range
47def9d
Add NVIDIA model provider and implement MiniMax integration
kexiv 4e69761
Update keys.example.json to include NVIDIA_API_KEY placeholder
kexiv 66fa73b
Update src/models/nvidia.js
kexiv e263e0e
Update src/models/nvidia.js
kexiv c999a06
Update keys.example.json
kexiv 67c56ad
Update src/models/nvidia.js
kexiv File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,56 @@ | ||
| import OpenAIApi from 'openai'; | ||
| import { getKey } from '../utils/keys.js'; | ||
| import { strictFormat } from '../utils/text.js'; | ||
|
|
||
| export class Nvidia { | ||
| // The prefix will be automatically recognized by _model_map.js | ||
| static prefix = 'nvidia'; | ||
|
|
||
| constructor(model_name, url, params) { | ||
| // Default to a standard NVIDIA NIM model name if no model_name is provided in the config | ||
| this.model_name = model_name || "meta/llama3-8b-instruct"; | ||
| this.params = params; | ||
|
|
||
| let config = {}; | ||
| // Set NVIDIA's dedicated API endpoint | ||
| config.baseURL = url || 'https://integrate.api.nvidia.com/v1'; | ||
| // Set this key in keys.json or as an environment variable | ||
| config.apiKey = getKey('NVIDIA_API_KEY'); | ||
|
|
||
| this.openai = new OpenAIApi(config); | ||
| } | ||
|
|
||
| async sendRequest(turns, systemMessage, stop_seq='***') { | ||
| let messages = [{'role': 'system', 'content': systemMessage}].concat(turns); | ||
| messages = strictFormat(messages); | ||
|
|
||
| const pack = { | ||
| model: this.model_name, | ||
| messages, | ||
| stop: stop_seq, | ||
| ...(this.params || {}) | ||
| }; | ||
|
|
||
| try { | ||
| console.log(`Awaiting NVIDIA API (${this.model_name}) response...`); | ||
| let completion = await this.openai.chat.completions.create(pack); | ||
| if (completion.choices[0].finish_reason == 'length') | ||
| throw new Error('Context length exceeded'); | ||
| console.log('Received.'); | ||
| return completion.choices[0].message.content; | ||
| } | ||
| catch (err) { | ||
| if ((err.message == 'Context length exceeded' || err.code == 'context_length_exceeded') && turns.length > 1) { | ||
| console.log('Context length exceeded, trying again with shorter context.'); | ||
| return await this.sendRequest(turns.slice(1), systemMessage, stop_seq); | ||
| } else { | ||
| console.error(err); | ||
| return 'My brain disconnected, try again.'; | ||
| } | ||
| } | ||
| } | ||
|
|
||
| async embed(text) { | ||
| throw new Error('Embeddings are not supported by NVIDIA.'); | ||
| } | ||
| } | ||
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.
Uh oh!
There was an error while loading. Please reload this page.