This repository has been archived by the owner on Nov 13, 2024. It is now read-only.
context engine docstring #130
Merged
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
+34
| ContextEngine is responsible for providing context to the LLM, given a set of search queries. | ||
|
|
||
| Once called with a set of queries, the ContextEngine will go through the following steps: | ||
| 1. Query the knowledge base for relevant documents | ||
| 2. Build a context from the documents retrieved that can be injected into the LLM prompt | ||
|
|
||
| The context engine considers token budgeting when building the context, and tries to maximize the amount of relevant information that can be provided to the LLM within the token budget. |
igiloh-pinecone
approved these changes
Nov 1, 2023
| The context engine considers token budgeting when building the context, and tries to maximize the amount of relevant information that can be provided to the LLM within the token budget. | ||
|
|
||
| To create a context engine, you must provide a knowledge base and optionally a context builder. | ||
|
|
There was a problem hiding this comment.
Maybe we should also mention that the returned Context object could be either structured or unstructured, but it always supports a .to_text() method dumping it as formatted text?
There was a problem hiding this comment.
IMO it's too deep for putting in this layer of docstrings, it's something to look at in the context builder I think because it relevant only once you want to costumes it
Co-authored-by: igiloh-pinecone <[email protected]>
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Outdated suggestions cannot be applied.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.
context engine docstring