Core engineer at TensorChord working on multi-vector retrieval (ColBERT MaxSim / WARP), external index builds, and RAG pipelines. Follow on GitHub (@kemingy).
-
Optimize RAG with Contextual Retrieval in PostgreSQL
In the standard approach to Retrieval Augmented Generation (RAG), a common practice is to break down large documents into smaller, more manageable chunks. This is primarily done to improve the efficiency of the retrieval process, leveraging the …
In the standard approach to Retrieval Augmented Generation (RAG), a common practice is to break down large documents into smaller, more manageable chunks. This is primarily done to improve the efficiency of the retrieval process, leveraging the …
-
Introducing Vechord: Turn PostgreSQL into your search engine in a Pythonic way.
Today, we’re thrilled to announce the release of Vechord, a new Python library designed to dramatically simplify building robust search infrastructure directly on top of the PostgreSQL database. In the rapidly evolving world of AI and large language …
Today, we’re thrilled to announce the release of Vechord, a new Python library designed to dramatically simplify building robust search infrastructure directly on top of the PostgreSQL database. In the rapidly evolving world of AI and large language …
-
VectorChord 0.3: Bringing Efficient Multi-Vector Contextual Late Interaction in PostgreSQL
We’re thrilled to announce the release of VectorChord 0.3, a major milestone that significantly boosts the performance and applicability of advanced vector search techniques directly within your Postgres database! Building on our 0.2 release, which …
We’re thrilled to announce the release of VectorChord 0.3, a major milestone that significantly boosts the performance and applicability of advanced vector search techniques directly within your Postgres database! Building on our 0.2 release, which …
-
Supercharge vector search with ColBERT rerank in PostgreSQL
Traditional vector search methods typically employ sentence embeddings to locate similar content. However, generating sentence embeddings through pooling token embeddings can potentially sacrifice fine-grained details present at the token level. …
Traditional vector search methods typically employ sentence embeddings to locate similar content. However, generating sentence embeddings through pooling token embeddings can potentially sacrifice fine-grained details present at the token level. …
-
Benefits and Steps of External Centroids Building in VectorChord
Clustering is an important component in vector search, and the k-means algorithm remains one of the most widely used techniques. However, its simplicity comes with a significant drawback: resource-intensive computation can render it impractical for …
Clustering is an important component in vector search, and the k-means algorithm remains one of the most widely used techniques. However, its simplicity comes with a significant drawback: resource-intensive computation can render it impractical for …