Refactor Orchestrator Configuration for Instance-Level Model Selection and Context Management #215
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
Xm0onh
changed the title
Comment on lines
76
to
81
| model: LLMNodeConfiguration, | ||
| tools: (StructuredToolInterface | RunnableToolLike)[], | ||
| prompts: OrchestratorPrompts, | ||
| namespace: string, | ||
| vectorStore: VectorDB, | ||
| pruningParameters?: PruningParameters, |
There was a problem hiding this comment.
should we just pass in OrchestratorConfig type, maybe call createOrchestratorConfig and pass result in?
There was a problem hiding this comment.
I found a couple of inconsistency. It's not possible right now to use OrchestratorConfig directly right now for this use case. Lm get it done in a separate PR.
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Outdated suggestions cannot be applied.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.
Closes #214 and Closes #199
This pull request introduces updates to the orchestrator configuration and context size management, refactors the code to remove unnecessary dependencies, and enhances the documentation. The most important changes include the addition of context size management, dynamic configuration for the orchestrator, and refactoring to remove the
VectorDBdependency from several nodes.Documentation Updates:
README.md, detailing how to configure pruning parameters both statically and dynamically.README.mdto include network configuration for the Taurus EVM wallet.Configuration Enhancements:
maxWindowSummaryandmaxQueueSize) in the orchestrator configuration to manage the context window size dynamically. [1] [2] [3]Code Refactoring:
VectorDBdependency frominputNode,messageSummaryNode, andworkflowSummaryNodeto simplify the node creation process. [1] [2] [3] [4]Configuration File Changes:
config.example.yamlandllm.tsto streamline the configuration files. [1] [2]These changes collectively improve the flexibility and maintainability of the orchestrator configuration and enhance the overall documentation for better usability.