2 Repos
Awesome GitHub RepositoriesMulti-Vector Indexing
Indexing strategies that store multiple embeddings for a single document to increase retrieval precision.
Distinct from Vector Indexing: Distinct from Vector Indexing: specifically stores multiple representations of one document rather than a single vector.
Explore 2 awesome GitHub repositories matching data & databases · Multi-Vector Indexing. Refine with filters or upvote what's useful.
Awesome Multi-Vector Indexing GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- bragai/brag-langchain
bragai/bRAG-langchain
4,028Auf GitHub ansehenbRAG-langchain is a framework for building retrieval augmented generation pipelines using LangChain to connect documents with language models. It functions as a vector store orchestrator that manages document indexing and retrieval strategies to improve context accuracy. The system implements an advanced retrieval pipeline featuring a semantic query router that directs natural language inputs to specific data sources or prompts. It includes a metadata filtering engine that translates natural language queries into structured schemas to narrow search results. The project covers hybrid search o
Stores multiple representations of a single document to improve retrieval precision across different query types.
Jupyter Notebookagentic-ragaichatbot - stanford-futuredata/colbert
stanford-futuredata/ColBERT
3,779Auf GitHub ansehenColBERT is a neural information retrieval model and dense passage retrieval framework. It functions as a search engine that uses contextual embeddings to index text passages and retrieve relevant documents based on semantic meaning rather than keyword matching. The system is distinguished by a late interaction architecture that defers the calculation of query and document similarity until the final step. It employs multi-vector indexing to store separate embeddings for every token in a document, enabling granular matching against query terms. The project covers document indexing, passage ret
Stores separate embeddings for every token in a document to allow granular matching against search queries.
Python
