Bedrock Antropic #170
Merged
Bedrock Antropic #170
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
* Update __init__.py 1. Change start_server() from outside to inside the class. * Update __init__.py 1. Place start_server inside llm init --------- Co-authored-by: Cláudio Lemos <[email protected]>
* Update __init__.py 1. Change start_server() from outside to inside the class. * Update __init__.py 1. Place start_server inside llm init * Update cli.py Change how the server runs. * Update __init__.py * Update __init__.py --------- Co-authored-by: Cláudio Lemos <[email protected]>
* Add llmstudio docs * Start creating gcp guide * Update gcp-deployment draft * Finish deploy-llmstudio-on-gcp guide. * Update deploy-on-google-cloud-platform.mdx * Fix some lettering * Update deploy-on-google-cloud-platform.mdx * Update deploy-on-google-cloud-platform.mdx * Update GCP docs --------- Co-authored-by: Cláudio Lemos <[email protected]>
brunoalho99
commented
Nov 19, 2024
diogoncalves
approved these changes
Nov 19, 2024
LLMstudio Version X.X.X ### What was done in this PR: Refactored the vertexAI provider to improve code clarity and maintainability. Removed duplicated async code in OpenAI and Azure providers for better efficiency and consistency. ### How it was tested: Executed the core.py and langchain_integration.py scripts located in the examples folder to ensure functionality and compatibility after changes. ### Additional notes: Any breaking changes? No breaking changes were introduced. Any new dependencies added? No new dependencies were added. Any performance improvements? Simplified and optimized the async implementation for better code execution and maintenance.
Merged
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.
LLMstudio Version X.X.X
What was done in this PR:
Integrated Amazon Bedrock into the LLMStudio project to enhance AI capabilities.
Added support for:
Tool calling: Integrated various tool calling features to extend functionality and allow the model to use external utilities.
Function calling: Enabled structured outputs through function calling, providing a more organized and accessible result.
LangChain integration: Combined LangChain features for smoother workflow and orchestration within the model.
How it was tested:
Additional notes:
Any breaking changes?
No breaking changes anticipated, but downstream dependencies may need updating if they rely on specific output formats.
Any new dependencies added?
Added boto3 for Bedrock API communication and updated LangChain modules where required.