picohen
Re:Launch HN: Aqua Voice (YC W24) – Voice-driven text editor
on Wednesday March 27, 2024 @02:52AM (#39836287)
check https://vetrec.io :)
Re:Show HN: Trains.fyi – a live map of passenger trains in the US and ...
on Monday November 27, 2023 @05:07PM (#38439101)
The Shinkansen is FASCINATING.
I recently went and was amazed by Tokyo's infrastructure and how they have a city under a city.
The fact that there is a bullet train at tokyo station every 10 mins or so is mind blowing
I went into a Youtube rabbit hole the other night...
Re:Show HN: Neum AI – Open-source large-scale RAG framework
on Wednesday November 22, 2023 @02:40AM (#38376164)
In fact, we will be releasing a blog post in the next few days of how we do real-time syncing for a RAG application with postgres hosted on supabase
Re:Show HN: Neum AI – Open-source large-scale RAG framework
on Wednesday November 22, 2023 @02:40AM (#38376160)
Postgres is already available :)
Re:Show HN: Neum AI – Open-source large-scale RAG framework
on Tuesday November 21, 2023 @08:16PM (#38373272)
Gotta start somewhere!
Take a look at this one as well! https://news.ycombinator.com/item?id=37824547
Re:Show HN: Neum AI – Open-source large-scale RAG framework
on Tuesday November 21, 2023 @04:42PM (#38370678)
Well, of course I'm biased on the answer :). But to give a not-so-biased answer, I would first try to understand what the project is about and whether RAG is a priority in it.
If the project is leveraging agents and LLMs without worrying too much on context/up-to-date data then Haystack could be a good option.
If the focus is to eventually use RAG then our framework could help.
Additionally, there might be a potential route where both are used, depending on the use case.
Feel free to dm if you want to chat further on this!
Re:Show HN: Neum AI – Open-source large-scale RAG framework
on Tuesday November 21, 2023 @04:35PM (#38370572)
Relevance calculations are handled by the vector db but we try to improve such relevance with the use of metadata (you will see how our components have "selectors" so that metadata can flow all the way to the vector database at the vector level and have an influence when results/scores get retrieved at search time)
Show HN: Neum AI – Open-source large-scale RAG framework
https://github.com/NeumTry/NeumAI
Over the last couple months we have been supporting developers in building large-scale RAG pipelines to process millions of pieces of data.We documented our approach in an HN post (https://news.ycombinator.com/item?id=37824547) a couple weeks ago. Today, we are open sourcing the framework we have developed.The framework focuses on RAG data pipelines and provides scale, reliability, and data...
Re:Show HN: ElectionGPT – easy-to-consume information about U.S. candi...
on Saturday October 14, 2023 @11:58PM (#37886752)
Hey! Yes! I am the creator, anything specific you wanted to know about? We published the tech-stack in this tweet https://x.com/kevin_neum/status/1712915693874958604?s=20
but essentially the way it works is:
1. Vercel and nextjs for frontend code and deployment
2. Neum to power the rag pipelines for the chatbot to query up-to-date information which we pull from a variety of sources
2.a) the text embeddings are stored in Weaviate (vector db)
3. We then create a prompt/some code with langchain to help query openai/stream the response back!
Re:Show HN: ElectionGPT – easy-to-consume information about U.S. candi...
on Saturday October 14, 2023 @11:55PM (#37886740)
our server was overloaded yesterday but we fixed it! let me know if you still have issues.
Re:Show HN: ElectionGPT – easy-to-consume information about U.S. candi...
on Saturday October 14, 2023 @11:55PM (#37886739)
Thanks! Yes. We ingest from a variety of sources. You can check in the about section of the page but essentially with Neum - Disclaimer, I'm the co-founder of Neum (https://neum.ai) - we power the RAG for the chatbot.
The bulk of the data is getting refreshed by Tweets from all of the candidates. We also pull in data from public sources such as wikipedia and ballotpedia (the bot outputs the sources used) And we also pull in from transcripts of interviews the candidates have had, again, if a piece of indo was used from any of these sources, we show it to the user
Show HN: ElectionGPT – easy-to-consume information about U.S. candidates
RAG at scale: Synchronizing and ingesting billions of text embeddings
Sync source data with vector stores in real time [video]
Efficiently sync context for your LLM application
Show HN: Neum AI – Improve your AI's accuracy with up-to-date context
While building Gen AI apps, we found that passing context to the prompt is crucial. However, the context must be accurate and up to date. If you are doing search over a vector database and that DB is not updated, then the search results are not good and the quality of your context will suffer.With this, we set to create an easy-to-use UX and a set of APIs that help you manage and synchronize...
Re:Software Development Job Postings on Indeed in the United States
on Tuesday July 18, 2023 @02:02AM (#36768437)
ChatGPT?