feat(providers): add DeepSeek as new LLM provider #2587
Conversation
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 PR adds DeepSeek as a new LLM provider to Archestra, implementing the full provider integration across LLM Proxy and Chat. Changes: - Add DeepSeek type definitions (OpenAI-compatible schemas) - Add DeepSeek adapter for LLM Proxy - Add DeepSeek routes for chat completions - Add DeepSeek to model constants and provider enums - Add @ai-sdk/deepseek dependency - Configure DeepSeek base URL and API key settings DeepSeek uses an OpenAI-compatible API at https://api.deepseek.com Closes archestra-ai#1846
Collaborator
- Add deepseek entries to error parsers/mappers in errors.ts - Add fetchDeepSeekModels function and registry entries in routes.models.ts - Add deepseek API key fallback and model fetcher - Add deepseek to displayNames and providerEnvVars in seed.ts - Add deepseek to pricesByProvider and rulesByProvider in optimization-rule.ts - Add deepseek to preferredSourcePrefixes in models-dev-client.ts
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Summary
This PR adds DeepSeek as a new LLM provider to Archestra.
Changes
@ai-sdk/deepseekdependencyAPI Key Instructions
To obtain a DeepSeek API key for testing:
Streaming Support
DeepSeek is OpenAI-compatible and supports streaming.
Feature Completeness
LLM Proxy:
Chat:
Demo Video
🎬 Video demonstration coming - will test all features with streaming and non-streaming responses.
Documentation
Testing
Closes #1846