Skip to content

Fix typo in Multi-Vector description #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SvachutaGollavilli wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix typo in Multi-Vector description #12

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/docs/introduction/retrieval-inventory.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,10 @@ Below is a list of various retrieval techniques and resources grouped by which p
* **Query Transformation -** Augment, structure, or enhance your input query
* [**Multi-Query**](/query-transformation/multi-query) - Generate additional questions/queries based on your original query to return more holistic documents
* **Index -** Adjust your data structures and associations
* [**Multi-Vector**](/indexing/multi-vector.md) - In addition to your the normal embeddings of your documents it is sometimes helpful to have multiple _alternative_ embeddings per document. These can include embeddings of a summary, hypothetical questions, or any other custom text
* [**Multi-Vector**](/indexing/multi-vector.md) - In addition to the normal embeddings of your documents it is sometimes helpful to have multiple _alternative_ embeddings per document. These can include embeddings of a summary, hypothetical questions, or any other custom text
* [**Parent Document Retriever**](/indexing/parent-document-retriever.md) - A version of multi-vector where large chunks are further split up into smaller (child) chunks
* **Retrieval Methods -** The method in which you pull documents out of your knowledge base
* [**Top-K Similarity Search**](/retrieval-methods/top-k-search.md) - Select the top K similar documents that match your query from your vectorestore. This is the 'Hello World' example of retrieval.
* [**Maximum Marginal Relevance (MMR)**](/retrieval-methods/maximum-marginal-relevance.md) - Return similar but diverse documents. Great for when you'd like to remove redundancy in your context
* **Document Transform -** Transform your documents before using them as context with your LLM
* [**Contextual Compression**](/document-transform/contextual-compression.md) - Extract contextually relevant information from your retrieved docs. Generally used to try and to increase signal:noise ratio
* [**Contextual Compression**](/document-transform/contextual-compression.md) - Extract contextually relevant information from your retrieved docs. Generally used to try and to increase signal:noise ratio