LintDB¶
LintDB is a multi-vector database meant for Gen AI. LintDB natively supports late interaction like colBERT and PLAID.
Key Features¶
Open Source: LintDB is released under an open-source license, allowing for community contributions and customization.
Multi vector support: LintDB stores multiple vectors per document id.
Embedded: LintDB can be embedded directly into your Python application. No need to setup a separate database.
Full Support for PLAID and ColBERT: LintDB is built around PLAID and colbert for efficient storage and lookup of token level embeddings.
Roadmap¶
LintDB’s mission is to be a full retrieval platform.
We want to extend LintDB’s features to include:
Snippet highlighting and explainability features.
Support for more algorithms for retrieval and ranking.
Increased support for document filtering.
Documentation¶
For detailed documentation on using LintDB, refer to the official documentation.
License¶
LintDB is licensed under the Apache 2.0 License. See the LICENSE file for details.
Contents: