Add Support for Knowledge Base Retrieval Params & Preprocessing #61
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
Comment on lines
+28
to
+31
| class LLMConfig(BaseModel): | ||
| model_name: str = Field(default=DEFAULT_LLM_MODEL, description='LLM model to use for context generation') | ||
| provider: str = Field(default=DEFAULT_LLM_MODEL_PROVIDER, description='LLM model provider to use for context generation') | ||
| params: Dict[str, Any] = Field(default={}, description='Additional parameters to pass in when initializing the LLM') |
lucas-koontz
approved these changes
Nov 22, 2024
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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 adds support for preprocessing knowledge base documents two ways:
TextChunkingConfigto split loaded documents into chunks before embeddingContextualConfigto support Contextual Retrieval (ref)It also supports passing in parameters to Knowledge Base creation to configure retrieval. Example: