Add Upstage AI Integration (Document Parse, Embeddings, and Generation) #314
+361
−1
Conversation
This file contains 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
…neration) Description: This PR introduces comprehensive integration with Upstage AI services, adding three new components: 1. Document Processing: - Added UpstageDocumentParseReader for converting documents to structured HTML format - Integrated with Upstage Document AI API for enhanced document parsing 2. Embedding Support: - Added UpstageEmbedder supporting 'embedding-query' and 'embedding-passage' models - Implemented vector generation for both documents and queries 3. Text Generation: - Added UpstageGenerator supporting Solar models (solar-pro, solar-mini) - Implemented streaming response generation with context handling Configuration Updates: - Added new environment variables: * UPSTAGE_API_KEY: For authentication * UPSTAGE_BASE_URL: For custom endpoint configuration (optional) - Updated README.md to reflect new capabilities and configuration options The integration is available in both production and development environments, maintaining consistent API patterns with existing integrators. Testing: - Verified document parsing functionality with various file formats - Tested embedding generation and similarity search - Validated streaming text generation with context windows - Confirmed proper error handling and rate limiting Dependencies: - No new package dependencies required - Uses existing aiohttp/httpx for API communication Documentation: - Updated README.md with new features and configuration options - Added inline documentation for all new components This integration enhances Verba's capabilities with state-of-the-art document processing, embedding, and generation features from Upstage AI.
|
To avoid any confusion in the future about your contribution to Weaviate, we work with a Contributor License Agreement. If you agree, you can simply add a comment to this PR that you agree with the CLA so that we can merge. |
I agree. Thanks!! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This PR introduces comprehensive integration with Upstage AI services, adding three new components.
They have high performance. (For more information, visit https://www.upstage.ai/ and https://www.upstage.ai/products/document-parse)
Configuration Updates:
The integration is available in both production and development environments, maintaining consistent API patterns with existing integrators.
Testing:
Dependencies:
Documentation:
This integration enhances Verba's capabilities with state-of-the-art document processing, embedding, and generation features from Upstage AI.