Launch HN: Roe AI (YC W24) – AI-powered data warehouse to query multimodal data
Roe AI is developing a query engine that allows SQL queries on unstructured data using LLMs, simplifying analysis for teams and offering a free trial with AI credits.
Roe AI, founded by Richard and Jason, is developing a query engine that enables data analysts to perform SQL queries on unstructured data types, including videos, images, webpages, and documents, using large language model (LLM) powered data processors. The platform aims to address the challenges faced by product, advertising, and marketing teams in extracting insights from unstructured multimodal data, which typically requires complex analysis processes. Roe AI simplifies this by allowing users to execute queries with just a few lines of SQL. The system utilizes multimodal LLMs for data extraction and classification, features a user-friendly interface for data exploration, and includes a semantic index builder for multimodal data. The founders draw on their extensive experience in data analysis, having transitioned from traditional methods to more streamlined approaches like those offered by Snowflake. Roe AI is currently in its early stages, offering a free trial with $50 in AI credits for processing unstructured data. While the product is not open-sourced due to its complexity, the team is open to feedback and suggestions for improvement.
- Roe AI enables SQL queries on unstructured data using LLMs.
- The platform simplifies complex data analysis processes for various teams.
- It features a user interface and semantic index builder for multimodal data.
- The product is in early development, offering free trials with AI credits.
- Feedback from users is encouraged to enhance the platform.
Related
Big tech wants to make AI cost nothing
Meta has open-sourced its Llama 3.1 language model for organizations with fewer than 700 million users, aiming to enhance its public image and increase product demand amid rising AI infrastructure costs.
Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers
Josh and Tom are developing Undermind, a search engine for complex scientific research, using large language models to enhance search accuracy and comprehensiveness, inviting user feedback for improvements.
An Open Course on LLMs, Led by Practitioners
A new free course, "Mastering LLMs," offers over 40 hours of content on large language models, featuring workshops by 25 experts, aimed at enhancing AI product development for technical individuals.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Launch HN: Release (YC W20) – Orchestrate AI Infrastructure and Applications
Release.ai, founded by Erik, Tommy, and David, offers a platform for orchestrating AI applications, providing free GPU cycles, prioritizing data security, and featuring a workflow engine with deployment templates.
- Users express interest in the product's potential but suggest improvements, such as adding a video demonstration.
- There are questions about the technical aspects, including how the LLM processes video files and the integration with existing data sources.
- Some commenters compare Roe AI's solution to existing technologies like PostgreSQL and express doubts about the necessity of a SQL interface for AI engineers.
- There is a discussion about the target audience, with inquiries about whether the tool is more suited for data engineers or analysts.
- Overall, the community is optimistic about the product's evolution and its potential to bridge gaps in data analysis.
13 commentsFYI your <title> tag needs to be updated.
At DataChain, we are solving this by creating a Python API that translates to SQL under the hood, which is pretty easy now with Pydantic. https://github.com/iterative/datachain
WDYT?
If this tool could parse drug patents and draw molecular structures with associated data, I know we would pay 200k/yr+ for that service, and there's a market for it.
In my own field, there's an incredibly important application to parse patents and scientific papers, but this would require specific image=>text models in order to get the required information out with high fidelity. Do you guys have plans to enable user supplied workflows where perhaps image patches can be sent to bespoke encoders, or finetunes?
Are you doing transcription + sending frames to a vision or is there a third party service for this?
Seems like the type of thing that would be very useful in helping build data pipelines on semi-structured data.
Related
Big tech wants to make AI cost nothing
Meta has open-sourced its Llama 3.1 language model for organizations with fewer than 700 million users, aiming to enhance its public image and increase product demand amid rising AI infrastructure costs.
Launch HN: Undermind (YC S24) – AI agent for discovering scientific papers
Josh and Tom are developing Undermind, a search engine for complex scientific research, using large language models to enhance search accuracy and comprehensiveness, inviting user feedback for improvements.
An Open Course on LLMs, Led by Practitioners
A new free course, "Mastering LLMs," offers over 40 hours of content on large language models, featuring workshops by 25 experts, aimed at enhancing AI product development for technical individuals.
Using Agents to Not Use Agents: How we built our Text-to-SQL Q & A system
Ask-a-Metric is a WhatsApp-based AI tool for SQL queries in the development sector, improving accuracy and efficiency through a pseudo-agent pipeline, achieving under 15 seconds response time and low costs.
Launch HN: Release (YC W20) – Orchestrate AI Infrastructure and Applications
Release.ai, founded by Erik, Tommy, and David, offers a platform for orchestrating AI applications, providing free GPU cycles, prioritizing data security, and featuring a workflow engine with deployment templates.