hnsqlite
ann-benchmarks
hnsqlite | ann-benchmarks | |
---|---|---|
6 | 51 | |
143 | 4,604 | |
1.4% | - | |
5.5 | 7.7 | |
10 months ago | 5 days ago | |
Python | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hnsqlite
-
LangChain: The Missing Manual
For anyone thinking about applications of langchain and pinecone but who are looking for something more turn-key check out https://jiggy.ai
The core is actually open source as well, allowing you to take your data back out via sqlite and hnswlib (https://github.com/jiggy-ai/hnsqlite)
-
I built an open source website that lets you upload large files, such as in-depth novels or academic papers, and ask ChatGPT questions based on your specific knowledge base. So far, I've tested it with long books like the Odyssey and random research papers that I like, and it works shockingly well.
We are built on open core https://github.com/jiggy-ai. Our open source hnsqlite is light weight, easy to use. And best of all, we make it easy for you to get your data out of JiggyBase. You can download a sqlite file that contains your document text data, metadata, embedding vectors, and embedding index. This can be used directly in the open source hnsqlite package.
-
What Is a Vector Database
After working through several projects that utilized local hnswlib and different databases for text and vector persistence, I integrated open source hnswlib with sqlite to create an embedded vector search engine that can easily scale up to millions of embeddings. For self-hosted situations of under 10M embeddings and less than insane throughput I think this combo is hard to beat.
https://github.com/jiggy-ai/hnsqlite
- Show HN: Hnsqlite: hnswlib and SQLite integrated for text embedding search
-
Faiss: A library for efficient similarity search
Thanks Leobg!
For anyone else: you pass it directly in metadata see https://github.com/jiggy-ai/hnsqlite/blob/main/test/test_col...
ann-benchmarks
-
Using Your Vector Database as a JSON (Or Relational) Datastore
On top of my head, pgvector only supports 2 indexes, those are running in memory only. They don't support GPU indexing, nor Disk based indexing, they also don't have separation of query and insertions.
Also with different people I've talked to, they struggle with scale past 100K-1M vector.
You can also have a look yourself from a performance perspective: https://ann-benchmarks.com/
- ANN Benchmarks
-
Approximate Nearest Neighbors Oh Yeah
https://ann-benchmarks.com/ is a good resource covering those libraries and much more.
-
pgvector vs Pinecone: cost and performance
We utilized the ANN Benchmarks methodology, a standard for benchmarking vector databases. Our tests used the dbpedia dataset of 1,000,000 OpenAI embeddings (1536 dimensions) and inner product distance metric for both Pinecone and pgvector.
-
Vector database is not a separate database category
Data warehouses are columnar stores. They are very different from row-oriented databases - like Postgres, MySQL. Operations on columns - e.g., aggregations (mean of a column) are very efficient.
Most vector databases use one of a few different vector indexing libraries - FAISS, hnswlib, and scann (google only) are popular. The newer vector dbs, like weaviate, have introduced their own indexes, but i haven't seen any performance difference -
Reference: https://ann-benchmarks.com/
-
How We Made PostgreSQL a Better Vector Database
(Blog author here). Thanks for the question. In this case the index for both DiskANN and pgvector HNSW is small enough to fit in memory on the machine (8GB RAM), so there's no need to touch the SSD. We plan to test on a config where the index size is larger than memory (we couldn't this time due to limitations in ANN benchmarks [0], the tool we use).
To your question about RAM usage, we provide a graph of index size. When enabling PQ, our new index is 10x smaller than pgvector HNSW. We don't have numbers for HNSWPQ in FAISS yet.
[0]: https://github.com/erikbern/ann-benchmarks/
- Do we think about vector dbs wrong?
-
Vector Search with OpenAI Embeddings: Lucene Is All You Need
In terms of "All You Need" for Vector Search, ANN Benchmarks (https://ann-benchmarks.com/) is a good site to review when deciding what you need. As with anything complex, there often isn't a universal solution.
txtai (https://github.com/neuml/txtai) can build indexes with Faiss, Hnswlib and Annoy. All 3 libraries have been around at least 4 years and are mature. txtai also supports storing metadata in SQLite, DuckDB and the next release will support any JSON-capable database supported by SQLAlchemy (Postgres, MariaDB/MySQL, etc).
-
Vector databases: analyzing the trade-offs
pg_vector doesn't perform well compared to other methods, at least according to ANN-Benchmarks (https://ann-benchmarks.com/).
txtai is more than just a vector database. It also has a built-in graph component for topic modeling that utilizes the vector index to autogenerate relationships. It can store metadata in SQLite/DuckDB with support for other databases coming. It has support for running LLM prompts right with the data, similar to a stored procedure, through workflows. And it has built-in support for vectorizing data into vectors.
For vector databases that simply store vectors, I agree that it's nothing more than just a different index type.
-
Vector Dataset benchmark with 1536/768 dim data
The reason https://ann-benchmarks.com is so good, is that we can see a plot of recall vs latency. I can see you have some latency numbers in the leaderboard at the bottom, but it's very difficult to make a decision.
As a practitioner that works with vector databases every day, just latency is meaningless to me, because I need to know if it's fast AND accurate, and what the tradeoff is! You can't have it both ways. So it would be helpful if you showed plots showing this tradeoff, similar to ann-benchmarks.
What are some alternatives?
langchainrb - Build LLM-powered applications in Ruby
pgvector - Open-source vector similarity search for Postgres
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
faiss - A library for efficient similarity search and clustering of dense vectors.
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]
Milvus - A cloud-native vector database, storage for next generation AI applications
annoy - Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
tlsh
GPT4Memory
vald - Vald. A Highly Scalable Distributed Vector Search Engine
raft - RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.