ibains

1. You ETL your documents into a vector database - you run this pipeline everyday to keep it up to date. You can run scalable, robust pipelines on Spark for this.

2. You have a streaming inference pipeline that has components that make API calls (agents) and between them transform data. This is Spark streaming.

Prophecy is working with large enterprises to implement generative AI use cases, but they don’t talk so much on HN.

Here’s our talk from Data+AI Summit: Build a Generative AI App on Enterprise Data in 13 Minutes https://www.youtube.com/watch?v=1exLfT-b-GM

Here’s a blog/demo https://www.prophecy.io/blog/prophecy-generative-ai-platform...

Comment · 3 years ago

Yes but this is just ETL - LlamaIndex and LangChain are re-inventing it - why use them when you have robust technology already?

1. You ETL your documents into a vector database - you run this pipeline everyday to keep it up to date. You can run scalable, robust pipelines on Spark for this.

2. You have a streaming inference pipeline that has components that make API calls (agents) and between them transform data. This is Spark streaming.

Prophecy is working with large enterprises to implement generative AI use cases, but they don’t talk so much on HN. Here’s our talk from Data+AI Summit:

Build a Generative AI App on Enterprise Data in 13 Minutes

https://www.youtube.com/watch?v=1exLfT-b-GM

Here’s a blog/demo

https://www.prophecy.io/blog/prophecy-generative-ai-platform...

Comment · 3 years ago

A lot of B2B startups can technically the cloud API to provide value added applications to Enterprises, but often the banks and healthcare companies will not want their data running through startups pipes to OpenAI pipes.

We provide a low code data transformation product (prophecy.io), and we’ll never close sales at any volume, if we have a to get an MSA that approves this. Might get easier if we become large :)

Comment · 3 years ago

Prophecy (prophecy.io) | ML Engineer | Palo Alto, CA

Work on LLMs and Knowledge Graphs fir English -> ETL data pipelines

You should have previous experience in NLP and solid programming. Shipping a project from scratch is important.

If you have only worked at large companies on tuning a small cog, it will not work

reach out to raj@

Comment · 3 years ago

https://www.prophecy.io/blog/announcing-prophecy-3-0-low-cod...

Comment · 3 years ago

are you serious? they invested in US Treasuries, the highest rated and the most conservative asset class.

Banks are in the business of lending money to home buyers, etc - how is loaning to the US Govt. criminal?

They have a cash crunch due to interest rate rise, and VC slowdown - bad risk management, but everything is above board.

Startup lines of credit should not happen from deposits, too risky an asset class

Comment · 3 years ago

Prophecy.io | Software Architect | Palo Alto, CA

Expert in Spark, Spark internals or Expert in Query Compilers.

Level variable (2-20 yrs exp), prefer 10+ years

Prophecy.io | Data Engineer | Palo Alto, CA

Expert in writing Spark code and running Spark at scale with substantial production and performance improvement experience. Work with our customers and help product design.

Level variable (2-10 yrs exp), prefer 5+ years

send mail to [email protected]

Comment · 4 years ago

Prophecy.io | Customer Success Director | Palo Alto, CA

We’re a game changing low-code data engineering platform, replacing ETL tools and modernizing the modern data stack.

You know data engineering well, have excellent customer facing experience (consulting works). You will work with our enterprise customers, coordinating with our strong data engineers to make the customers successful. Be their trusted advisor, no upsell responsibility.

email: [email protected]

Comment · 4 years ago

Its not public language, but at Risk Management Systems, I worked on Contract Definition Language- an external DSL for computable insurance, re-insurance contracts. This was used to simulate insurance losses when catastrophic events happen (earthquake, hurricane)