motorhead
ann-benchmarks
Our great sponsors
motorhead | ann-benchmarks | |
---|---|---|
10 | 51 | |
828 | 4,588 | |
2.6% | - | |
7.7 | 8.1 | |
4 days ago | 6 days ago | |
Rust | 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.
motorhead
- Motorhead is a memory and information retrieval server for LLMs
-
Comparison of Vector Databases
Metal [1] is another one on my radar. Their API looks super simple.
Disclosures: None
[1] https://getmetal.io
-
Any Alternatives to Langchain?
Any alternatives? I found this Rust based project that might be interesting: https://github.com/getmetal/motorhead
- RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
-
Langchain question and answer without openai
you could run motorhead on docker https://github.com/getmetal/motorhead
-
How to use Enum with Vec to parse the mixed data vector from RedisSearch
The code is found using GitHub search FT.SEARCH inside https://github.com/getmetal/motorhead/blob/main/src/models.rs and adapted.
-
Memory in production
All the examples that Langchain gives are for persisting memory locally which won't work in a serverless (statelesss) environment, and the one solution documented for stateless applications, getmetal/motorhead, is a containerized, Rust-based service we would have to run ourselves.
- Show HN: Motörhead, LLM Memory Server Built in Rust
-
OpenAI Embeddings API alternative?
I've only just signed up and haven't had a chance to build anything with it yet, but this might be something to consider https://getmetal.io/
- Motörhead – memory and information retrieval server for LLMs
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?
lmql - A language for constraint-guided and efficient LLM programming.
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.
RasaGPT - 💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
Milvus - A cloud-native vector database, storage for next generation AI applications
kor - LLM(😽)
tlsh
Abstract Feature Branch - abstract_feature_branch is a Ruby gem that provides a variation on the Branch by Abstraction Pattern by Paul Hammant and the Feature Toggles Pattern by Martin Fowler (aka Feature Flags) to enable Continuous Integration and Trunk-Based Development.
vald - Vald. A Highly Scalable Distributed Vector Search Engine
rasa-haystack
pgANN - Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.