retake
NeumAI
| retake | NeumAI | |
|---|---|---|
| 4 | 2 | |
| 757 | 793 | |
| - | 4.9% | |
| 10.0 | 8.7 | |
| 8 months ago | 5 months ago | |
| Rust | Python | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
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.
retake
-
Show HN: Retake – Open-Source Hybrid Search for Postgres
https://github.com/getretake/retake/pull/198 is a refreshing change given the recent rug pulls, so thank you for that
-
We created an open-source semantic search Python package on top of Postgres
We found it difficult to do well with standard vector databases and so we ended up making a nice open-source package to layer semantic search on top of Postgres with just a few lines of code. It supports Python backends right now, always stays in sync with Postgres via Kafka, doubles as a vector store, and can be deployed anywhere.
- Show HN: Open-Source Infrastructure for Vector Data Streams
NeumAI
-
Show HN: Neum AI – Open-source large-scale RAG framework
Interesting to see that the semantic chunking in the tools library is a wrapper around GPT-4. Asks GPT for the python code and executes it: https://github.com/NeumTry/NeumAI/blob/main/neumai-tools/neu...
What are some alternatives?
bionicgpt - BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality [Moved to: https://github.com/bionic-gpt/bionic-gpt]
phidata - Build AI Assistants with memory, knowledge and tools.
nfcompose - Build REST APIs/Integrations in minutes instead of hours - NF Compose is a (data) integration platform that allows developers to define REST APIs in seconds instead of hours. Generated REST APIs are backed by postgres and support automatic consumer webhook notifications on data changes out of the box.
versatile-data-kit - One framework to develop, deploy and operate data workflows with Python and SQL.
embedditor - ⚡ GUI for editing LLM vector embeddings. No more blind chunking. Upload content in any file extension, join and split chunks, edit metadata and embedding tokens + remove stop-words and punctuation with one click, add images, and download in .veml to share it with your team.
deeplake - Database for AI. Store Vectors, Images, Texts, Videos, etc. Use with LLMs/LangChain. Store, query, version, & visualize any AI data. Stream data in real-time to PyTorch/TensorFlow. https://activeloop.ai
vectorflow - VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.
searchGPT - Grounded search engine (i.e. with source reference) based on LLM / ChatGPT / OpenAI API. It supports web search, file content search etc.
tinyvector - A tiny embedding database in pure Rust.
vektor - a mini vector database implementation that intends to be educational and interpretable
pgsync - Postgres to Elasticsearch/OpenSearch sync
llmflows - LLMFlows - Simple, Explicit and Transparent LLM Apps